Anonymization of Sensitive Quasi-Identifiers for l-Diversity and t-Closeness

Anonymization of Sensitive Quasi-Identifiers for l-Diversity and t-Closeness

ABSTRACT:

A number of studies on privacy-preserving data mining have been proposed. Most of them assume that they can separate quasi-identifiers (QIDs) from sensitive attributes. For instance, they assume that address, job, and age are QIDs but are not sensitive attributes and that a disease name is a sensitive attribute but is not a QID. However, all of these attributes can have features that are both sensitive attributes and QIDs in practice. In this paper, we refer to these attributes as sensitive QIDs and we propose novel privacy models, namely, (l1, …, lq)-diversity and (t1, …, tq)-closeness, and a method that can treat sensitive QIDs. Our method is composed of two algorithms: an anonymization algorithm and a reconstruction algorithm. The anonymization algorithm, which is conducted by data holders, is simple but effective, whereas the reconstruction algorithm, which is conducted by data analyzers, can be conducted according to each data analyzer’s objective. Our proposed method was experimentally evaluated using real data sets.

PROJECT OUTPUT VIDEO: (Click the below link to see the project output video):

EXISTING SYSTEM:

Many studies regarding anonymized databases of personal information have been proposed. Most existing methods consider that the data holder has a database in the form of explicit identifiers, quasi-identifiers (QIDs), or sensitive attributes, where explicit identifiers are attributes that explicitly identify individuals (e.g., name), QIDs are attributes that could be potentially combined with other directories to identify individuals (e.g., zip code and age), and sensitive attributes are personal attributes of a private nature (e.g., disease and salary)

DISADVANTAGES OF EXISTING SYSTEM:

The values of Disease are protected by frequency l-diversity, but other attributes are not protected. In practice, the age, address, and job of a person might be considered as private information. In this case, we should consider that these attributes have features of both QIDs and sensitive attributes k-anonymity cannot protect against “attribute disclosure.”

PROPOSED SYSTEM:

Our contributions are as follows: (1) we propose new privacy models, namely, (l1; : : : ; lq)-diversity and (t1; : : : ; tq)-closeness, which can treat databases containing several sensitive QIDs; (2) we propose a simple but effective general anonymization algorithm for (l1; : : : ; lq)-diversity and (t1; : : : ; tq)-closeness, which is conducted by data holders; and (3) we propose a novel reconstruction algorithm that can decrease the reconstructed error between the reconstructed and the original values according to each data analyzer’s purpose.

ADVANTAGES OF PROPOSED SYSTEM:

Our approach can reduce information loss, even when the number of attributes is large, because the randomization of attribute value is executed for each attribute independently. Furthermore, we can ensure that, even if the data analyzer knows all the sensitive QID values of the whole database except for one record, the sensitive QID values of the record are protected.

The dominant approach to anonymize databases for l-diversity and t-closeness is based on a generalization. The generalization approach is easily understandable for data analyzers. Moreover, because the truthfulness of each record is preserved, we can obtain some information from each record.

SYSTEM ARCHITECTURE:

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS: 

  • System : Pentium Dual Core.
  • Hard Disk : 120 GB.
  • Monitor : 15’’ LED
  • Input Devices : Keyboard, Mouse
  • Ram : 1 GB

SOFTWARE REQUIREMENTS: 

  • Operating system : Windows 7.
  • Coding Language : JAVA/J2EE
  • Tool : Netbeans 7.2.1
  • Database : MYSQL

REFERENCE:

Yuichi Sei, Member, IEEE, Hiroshi Okumura, Takao Takenouchi, Akihiko Ohsuga, Member, IEEE, “Anonymization of Sensitive Quasi-Identifiers for l-Diversity and t-Closeness”, IEEE Transactions on Dependable and Secure Computing, 2017.

Cooperative Communications with Wireless Energy Harvesting over Nakagami-m Fading Channels

Cooperative Communications with Wireless Energy Harvesting over Nakagami-m Fading Channels

ABSTRACT:

In this paper, a dual-hop decode-to-forward cooperative system is considered where multiple relays with finite energy storage and can harvest energy from the destination. In our analysis, the relays are spatially randomly located with invoking stochastic geometry. In an effort to improve spectral efficiency, an optimal source-relay link (OSRL) scheme is employed. Assuming Nakagami-m fading, two different scenarios are considered: 1) the single-antenna source with perfect channel state information (CSI); and 2) the multiple-antenna source with transmit antenna selection and imperfect CSI. In both scenarios, the destination node is equipped with a single transmit antenna to forward power via frequency radio signal to the relay candidates. For improving the system performance, multiple antennas at the destination are considered to process the multiple copies of the received signal from the best relay. For characterizing the performance of the proposed scenarios, exact closed-form analytical expressions for the outage probability are derived. To obtain further insights, we carry out diversity gain analysis by adopting asymptotic relative diversity. We also derive the exact closed-form analytical expression for the system throughput. Finally, simulation results are presented to corroborate the proposed analysis and to show that: i) The system performance is improved by enlarging the area of the circle and the density of the relays. ii) The energy storage size has impacts on the performance of considered networks, which determines the maximal transmit power at relays.

EXISTING SYSTEM:

  1. Ding. Et. All, the OP of a cooperative network with multiple source destination pairs and one EH relay was characterized by taking the spatial randomness of user locations into consideration. Assuming spatial randomness of relays in SWIPT systems, the work in “Wireless information and power transfer in cooperative networks with spatially random relays” analyzed the system outage performance, in which different relay selection techniques were analyzed.

DISADVANTAGES OF EXISTING SYSTEM:

Most of the existing literature laid a solid foundation for the role of cooperative SWIPT in Rayleigh fading, and the impact of cooperative SWIPT in Nakagami-m fading has not been well understood

PROPOSED SYSTEM:

In this paper we analyze the outage performance of a cooperative system with spatially random wireless powered DF relays and finite energy storage over Nakagami-m fading channels, where the destination is equipped with multiple antennas and adopt maximal ratio combining (MRC) scheme to process multiple received signals.

The OSRL Process Assuming Perfect CSI: We consider a scenario where all relays are equipped with multiple antennas and adopt MRC scheme, while the source is a single-antenna device.

Compared to existing which a single antenna was considered at the relay nodes, it is of great significance of identifying the effect of multiple antennas and MRC scheme, which can improve the system performance in presence of EH.

Transmit Antenna Selection with Imperfect CSI: We consider a source equipped with multiple antennas and employing TAS scheme, while the spatially random relays are single-antenna-devices. For the TAS process, imperfect CSI is assumed.

ADVANTAGES OF PROPOSED SYSTEM:

Nakagami-m fading channel can reduce to multiple types of channel with the different parameter settings

SYSTEM ARCHITECTURE:

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS: 

  • System : Pentium Dual Core.
  • Hard Disk : 120 GB.
  • Monitor : 15’’ LED
  • Input Devices : Keyboard, Mouse
  • Ram : 1 GB

SOFTWARE REQUIREMENTS: 

  • Operating system : Windows 7.
  • Coding Language : MATLAB
  • Tool : MATLAB R2013A

REFERENCE:

Jia Ye, Hongjiang Lei, Member, IEEE, Yuanwei Liu, Member, IEEE, Gaofeng Pan, Member, IEEE, Daniel Benevides da Costa, Senior Member, IEEE, Qiang Ni, Senior Member, IEEE, and Zhiguo Ding, Senior Member, IEEE, “Cooperative Communications with Wireless Energy Harvesting over Nakagami-m Fading Channels”, IEEE Transactions on Communications, 2017.

A 30-W 90% Efficiency Dual-Mode Controlled DC–DC Controller With Power Over Ethernet Interface for Power Device

A 30-W 90% Efficiency Dual-Mode Controlled DC–DC Controller With Power Over Ethernet Interface for Power Device

ABSTRACT:

A dual-mode controlled dc–dc controller with power over Ethernet (PoE) interface for power device (PD) is presented that is designed to support drawing power either from an Ethernet cable or from an external auxiliary supply support (ASS). PoE interface supports all the functions that comply with the IEEE802.3af/at standard. Based on band gap reference structure, a detection comparator is provided to detect input voltage without extra voltage reference. Using a low offset voltage amplifier, a low loss current-limiting technique is proposed to achieve a high precision current-limit point. Based on a high-speed comparator and two timing capacitors, an oscillator (OSC) is implemented for better accuracy, and provides the maximum duty cycle (Dmax) and external frequency synchronization. The chip is fabricated in a 0.5-µm 65 V BCD process and occupies a die size (with pads) of 1.79 × 2.76 mm2. The experimental results are measured for an active clamp forward converter with a wide range of dc input voltages from 33 to 57 V, an output voltage of 12 V, and an output power of 30 W. The chip achieves peak power efficiency of 90% and 90.63% on DC and ASS, respectively. The load regulation at different input voltages can be measured to be within ±0.11%. Measurements further show that the peak-to-peak ripple voltage of the chip is 161 mV and the recovery time is less than 1.2 ms for the 2-A load step.

EXISTING SYSTEM:

RECENTLY, the power over Ethernet (PoE) system has been one of the most popular topics, and it has wide ranging prospects in the global networking market. The PoE represents a standardized system to transfer data along with electrical power on Ethernet cabling without any extra power cable or adapter, greatly reducing the overall installation and maintenance cost. Due to the advantages of saving space, flexibility, and cost in application, the PoE system can be widely applied to video and Voice over Internet Protocol telephones, RFID readers, multiband access points, security cameras, and so on. With the development of new application areas and markets for the PoE system, research and design of the PoE system has been proposed to satisfy more demanding applications. Meanwhile, the PoE system needs to be highly stable in its various applications, due to high operating voltage and high power, which increases the need for further research and design of the PoE system.

Since industrial products require more power and higher conversion efficiency [2], it became necessary to deliver a higher power level. The IEEE802.3af standard was replaced by IEEE802.3at which supports power levels up to 25.5 W and increases the operating current from 350 to 720 mA. According to the IEEE802.3af/at, devices compliant with IEEE802.3af and IEEE802.3at are referred to as type 1 and type 2 devices, respectively. A typical PoE system consists of power sourcing equipment (PSE) and a power device (PD) [2]. A typical example of the architecture of the PoE system is shown in Fig. 1. From Fig. 1, the data are transferred through CAT-5 network cable to the application, while the PSE injects power into the cable. The PD therefore receives both data and power via the cable. In order to ensure that the desired power can be transmitted safely and smoothly over an Ethernet cable, both the PSE and PD need to have appropriate power management ICs to manage and control the entire power transmission process. The power management ICs of the PD include a PoE interface and dc–dc controller and are the interface between the Ethernet cable and IP devices. The PoE interface is responsible for the communication with PSE and supports all the functions that comply with the IEEE802.3af/at standard. Meanwhile, the dc–dc controller employs voltage conversion to regulate the output voltage to the desired level.

DISADVANTAGES:

  • More Power Consumption
  • Technology used 500nm.

PROPOSED SYSTEM:

Due to security and the cost of the system, flyback and forward converters are normally applied in PoE systems. The prototype converter targets high-efficiency conversion at all load conditions supporting synchronous flyback topology and active clamp forward (ACF) topology. The ACF topology is clearly described and analyzed [9] – [12], and thus its related content will not be described with detailed theory analysis in this paper. The system diagram of the proposed high-efficiency converter is shown in Fig. 2. It mainly consists of bypass capacitor C1, transient suppressor diodes D0 and D1, type- π filter, main MOSFET Q1, auxiliary MOSFET Q2, lowside active clamp (LSAC) circuit, amplifier U1, optocoupler U2, synchronous rectifiers SR1 and SR2, type-II compensation network, output capacitor CO , output inductor L O , type-2 PSE indicator, and control IC.

As shown in Fig. 2, the LSAC circuit is used to produce output voltage levels below SG. U1 and U2 provide output regulation feedback for a current mode control. The type-II compensator is used to achieve optimized loop bandwidth and fast transient responses. Type-2 PSE indicator can indicate that the connected PD is a type-2 PD. Through the DE and CL pins, the PoE detection signature and the class current are provided, respectively.

The blanking time, dead time, and switching frequency are programmed through the BK, DT, and FS pins, respectively. The secondary-side regulation scheme is adopted to monitor the output voltage, and the optocoupler feedback is transfer to the FB pin to generate the pulse width-modulated (PWM) signal. VH and VL pins are the bias rail and the internal high-voltage regulator output, respectively. PG and VSS pins are two-event classification indicator and the system low potential input, respectively. The GND, VOUT, and SG pins are the power ground of the driver, the drain of NS3, and the analog ground of the dc–dc controller, respectively (they are tied together on the circuit board). In addition, SG pin is the floating analog ground. The chip integrates a hotswap MOSFET to isolate the grounds of the PoE interface and dc–dc controller [13]. After startup, VOUT falls from VDD to nearly VSS as CIN is charged, and then the current of the chip is limited. This scheme deals with the problem of different grounds of PoE and dc–dc controller and limits the current of the chip.

ADVANTAGES:

  • Less Power Consumption
  • Technology used 130nm.

SOFTWARE IMPLEMENTATION:

  • Tanner

Excavating the Hidden Parallelism Inside DRAM Architectures With Buffered Compares

Excavating the Hidden Parallelism Inside DRAM Architectures With Buffered Compares

ABSTRACT:

We propose an approach called buffered compares, a less-invasive processing-in-memory solution that can be used with existing processor memory interfaces such as DDR3/4 with minimal changes. The approach is based on the observation that multibank architecture, a key feature of modern main memory DRAM devices, can be used to provide huge internal bandwidth without any major modification. We place a small buffer and a simple ALU per bank, define a set of new DRAM commands to fill the buffer and feed data to the ALU, and return the result for a set of commands (not for each command) to the host memory controller. By exploiting the under-utilized internal bandwidth using ‘compare-n-op’ operations, which are frequently used in various applications, we not only reduce the amount of energy inefficient processor–memory communication, but also accelerate the computation of big data processing applications by utilizing parallelism of the buffered compare units in DRAM banks. We present two versions of buffered compare architecture–full scale architecture and reduced architecture–in trade of performance and energy. The experimental results show that our solution significantly improves the performance and efficiency of the system on the tested workloads.

EXISTING SYSTEM:

WITH the emergence of big data applications, the centroid of computing paradigm is shifting toward data from computation. Big data applications are characterized by inherent large memory footprint, small or modest amount of computation, and high degree of parallelism. Together with the trend of increasing number of cores in a system, external memory bandwidth requirement of a system has steadily increased. However, in contrast to the rapidly growing computing power and bandwidth requirement, actual bandwidth and energy efficiency of off-chip channels are not improving as much, so called the memory wall problem [3].

All these circumstances endorse the movement toward the resurgence of near-data processing (NDP) or processing in memory (PIM) [4]–[6], which offloads certain computations to processing units placed at or near the memory. One straightforward way to implement NDP is to add fully functional cores atop DRAM dies utilizing 3-D stacking. However, integrating cores with DRAM incurs numerous issues, including thermal problems [7]. Typically, memory chips do not have strong cooling capability as processor chips do. Also, memories are in general more vulnerable to high temperature. Therefore, the power budget of the cores integrated with DRAM devices would be very limited. There are also other problems such as cache coherence, virtual memory support, and overhead in mapping applications.

By contrast, we leverage existing memory systems to realize NDP with minimal changes to the current ecosystem. Thus, our approach adds minimal amount of computing capability to the memory die for offloading memory-intensive operations while leaving complex or unbounded controls to the processor and the memory controller. However, considering the gap between internal and external bandwidth of multibank DRAM, the approach tries to maximally exploit the excessive internal bandwidth.

To achieve this goal, we focus on compare instructions, mainly targeting table/index scan in in-memory databases [8]. For example, table scan depicted in Fig. 1 searches for a specific data in the given table. It is a fundamental operation of databases and critical to the performance, especially for column store databases [9], [10]. By executing compare operations of table scan at the memory side, a great amount of data read from the memory can be reduced. When scanning a table, there is a key that we search for. The key is compared with the items (called targets) stored in the table. In the conventional system [Fig. 1(a)], a processor: ① fetches the target data stored in a table, ② performs a compare with the key, and ③ outputs the compare results. However, we need to know only whether each target data matches the key, and the actual value except the match result is totally unnecessary. If we perform the compares at the memory side [Fig. 1(b)], we: ① send the key to the memory instead of reading the targets, ② do the comparisons, and ③ read the result after the comparisons are over. In this way, we can reduce the memory bandwidth, and the benefit gets larger as there are more target data to read.

 

DISADVANTAGES:

  • More Memory Bandwidth
  • More Power

PROPOSED SYSTEM:

We propose a novel buffered compare scheme, a kind of PIM technique that performs compare-n-op operations inside DRAM banks to speed up many applications and amplify effective memory bandwidth. In contrast to existing PIM techniques, the buffered compare operations have deterministic latency so that they can be treated as simple extensions of ordinary DRAM commands, which leaves the DRAM as a ‘passive’ device (a device that does not invoke any event by itself). Also, without any caches or complicated pipelines of ordinary cores, the buffered compare approach incurs minimal overhead to existing DRAM dies.

To perform buffered compares, for each DRAM bank, we place a key buffer that usually holds the fixed search key, an arithmetic unit, and another small buffer that holds the results. We use buffered compares to perform such operations within banks, greatly reducing the traffic/latency of the offchip channel. Thus, it speeds up the system, especially when the off-chip bandwidth is saturated. Simulation results show that our scheme achieves up to 15.5× speedup and significant energy reduction, at the expense of a minimal increase in the DRAM die area on the tested workloads. Our key contributions are as follows.

1) We identify that abundant internal bandwidth unused in modern DRAM architecture provides the opportunity to exploit this extra bandwidth with NDP.

2) We propose buffered compare architecture that performs compare-n-op operations inside DRAM to provide parallelism and off-chip bandwidth savings with lightweight logic.

 3) We suggest a way to solve the system integration issues of buffered compare, including programming model, coherence, memory protection, and data placement.

4) We investigate six workloads that utilize buffered compares to enhance system performance and energy effi- ciency. We also present a detailed circuit-level analysis of buffered compare units (BCUs) on performance, power, and area overheads.

INTEGRATING BUFFERED COMPARES TO SYSTEMS

  1. Challenges for Processing-in-Memory Integration Even though we tried to add minimal overhead to the existing architecture and protocol, there are still some hurdles to overcome to integrate buffered compare to the system. In this section, we will briefly address the challenges and describe the solutions in the following sections. First, a programming model is needed to expose buffered compare to the end-users, where we prefer the programmer not to be aware of the detailed DRAM parameters, such as size of a DRAM row or the number of banks in a rank. It would not only make the programming difficult, but also make the code dependent on the system configuration. The second issue comes with the cache coherence. Because the processor cache might have a copy of the data, it has to be kept coherent with the memory side. While one solution would be to implement a coherence protocol between them, it would incur too much overhead and offset the benefit from using PIM. Virtual memories give another challenge to buffered compare. Unlike other PIM approaches, buffered compare does not require address translation at the memory side. However, because of virtual memories, contiguous range of data might be split over multiple physical pages. Another problem comes from the data placement. In modern DRAM architectures, a rank is usually composed of multiple devices to increase the width of a memory channel. A word is usually interleaved over all the devices within the rank. This raises a problem to buffered compare operations as a full word is needed for processing at a BCU. Finally, changes are required to the memory controllers. Unlike normal reads/writes, the buffered compare operations are performed over a specified address range, and the memory controller should be carefully to support them.

ADVANTAGES:

  • Effective and less Memory Bandwidth
  • Less Power

SOFTWARE IMPLEMENTATION:

  • Modelsim
  • Xilinx 14.2

Single Image Super-Resolution via AdaptiveTransform-Based Nonlocal Self-Similarity Modeling and Learning-Based Gradient Regularization

Single Image Super-Resolution via AdaptiveTransform-Based Nonlocal Self-Similarity Modelingand Learning-Based Gradient Regularization

ABSTRACT:

Single image super-resolution (SISR) is a challenging work, which aims to recover the missing information in an observed low-resolution (LR) image and generate the corresponding high-resolution (HR) version. As SISR problem is severely ill-conditioned, effective prior knowledge of HR images is necessary to well pose the HR estimation. In this paper, an effective SISR method is proposed via the local structure-adaptive transform based nonlocal self-similarity modeling and learning-based gradient regularization (LSNSGR). The LSNSGR exploits both the natural and learned priors of HR images, thus integrating the merits of conventional reconstruction-based and learning based SISR algorithms. More specifically, on the one hand, we characterize nonlocal self-similarity prior (natural prior) in transform domain by using the designed local structure-adaptive transform; on the other hand, the gradient prior (learned prior) is learned via the jointly optimized regression (JOR) model. The former prior is effective in suppressing visual artifacts, while the latter performs well in recovering sharp edges and fine structures. By incorporating the two complementary priors into the MAP based reconstruction framework, we optimize a hybrid L1- and L2-regularized minimization problem to achieve an estimation of the desired HR image. Extensive experimental results suggest that the proposed LSNSGR produces better HR estimations than many state-of-the-art works in terms of both perceptual and quantitative evaluations.

EXISTING SYSTEM:

  • In Existing paper, they presented a unified frame based on collaborative representation (CR) for single-image super-resolution (SR), which learns low-resolution (LR) and high-resolution (HR) dictionaries independently in the training stage and adopts a consistent coding scheme (CCS) to guarantee the prediction accuracy of HR coding coefficients during SR reconstruction.
  • The independent LR and HR dictionaries are learned based on CR with l2-norm regularization, which can well describe the corresponding LR and HR patch space, respectively.
  • Furthermore, a mapping function is learned to map LR coding coefficients onto the corresponding HR coding coefficients. Propagation filtering can achieve smoothing over an image while preserving image context like edges or textural regions.

DISADVANTAGES OF EXISTING SYSTEM:

  • In existing, artifacts were introduced and more fine details were degraded.

PROPOSED SYSTEM:

To suppress artifacts and restore more fine details in the super-resolved image, we propose a SISR method via local structure-adaptive transform-based NLSS modeling and learning-based gradient regularization (LSNSGR). On the one hand, by characterizing the NLSS prior with the proposed local structure-adaptive transform, the local structure and NLSS priors are combined together; on the other hand, aiming at integrating the advantages of reconstruction- and learning based SISR methods, the estimated gradient field is utilized to construct a regularization term. In sum, the main contributions of our work are four-folds:

  • We propose to characterize the NLSS property in transform domain by using the developed local structure adaptive transform. Further, a regularization term, which can be easily applied to solve various image restoration problems, is constructed based on the proposed local structure-adaptive NLSS model.
  • We present to use the jointly optimized regression (JOR) model to estimate the gradient field of the desired HR image, which serves as a gradient regularization term in SR process.
  • With the MAP-based SR framework, an effective SISR algorithm is developed by incorporating the local structure adaptive NLSS model and gradient constraint. In addition, the Split Bregman Iteration (SBI) is imitated to optimize the proposed minimization problem effectively.
  • Benefiting from the complementary properties of nonlocal self-similarity model and gradient constraint, the artifacts in super-resolved image can be removed, and the local structures and sharp edges can be well recovered. Extensive experiments validate the state-of-the-art performance of the developed SISR scheme.

ADVANTAGES OF PROPOSED SYSTEM:

  • By contrast, the proposed method LSNSGR is more effective in both suppressing artifacts as well as recovering sharp edges.
  • Our framework also performs better than all of the compared methods as a whole. It can be observed that the proposed LSNSGR achieves the highest average PSNR, SSIM, and IFC values. Therefore, we can believe that our method produces more reliable HR estimations.
  • Our results are more visually pleasant.

SYSTEM ARCHITECTURE:

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

  • System : Pentium Dual Core.
  • Hard Disk : 120 GB.
  • Monitor : 15’’LED
  • Input Devices : Keyboard, Mouse
  • Ram :1GB

SOFTWARE REQUIREMENTS:

  • Operating system : Windows 7.
  • Coding Language : MATLAB
  • Tool : MATLAB R2013A

REFERENCE:

Honggang Chen, Student Member, IEEE, Xiaohai He, Member, IEEE,Linbo Qing, Member, IEEE, and Qizhi Teng, Member, IEEE, “Single Image Super-Resolution via AdaptiveTransform-Based Nonlocal Self-Similarity Modelingand Learning-Based Gradient Regularization”, IEEETransactions on Multimedia, 2017.

 

SRLSP: A Face Image Super-Resolution Algorithm Using Smooth Regression with Local Structure Prior

SRLSP: A Face Image Super-Resolution Algorithm Using Smooth Regression with Local Structure Prior

ABSTRACT:

The performance of traditional face recognition systems is sharply reduced when encounter with low-resolution (LR) probe face image. To obtain much more detailed facial features, some face super-resolution (SR) methods have been proposed in the past decade. The basic idea of face image SR is to generate a high-resolution (HR) face image from an LR one with the help of a set of training examples. It aims at transcending the limitations of optical imaging systems. In this paper, we regard face image SR as an image interpolation problem for domain specific images. A missing intensity interpolation method based on smooth regression with local structure prior (LSP), named SRLSP for short, is presented. In order to interpolate the missing intensities in a target HR image, we assume that face image patches at the same position share similar local structures, and use smooth regression to learn the relationship between LR pixels and missing HR pixels of one position-patch. Performance comparison with the state-of-the-art SR algorithms on two public face databases and some real-world images shows the effectiveness of the proposed method for face image SR in general. In addition, we conduct a face recognition experiment on the Extended Yale-B face database based on the super-resolved HR faces. Experimental results clearly validate the advantages of our proposed SR method over the state-of-the-art SR methods in face recognition application.

EXISTING SYSTEM &DISADVANTAGES:

  • Global face based parameter estimation methods take a face image as a whole and model it by some classical face models, such as principal component analysis (PCA), locality preserving projections (LPP), nonnegative matrix factorization (NMF) and canonical correlation analysis (CCA).
  • These approaches are easy to implement and their performances are reasonably good. However, they often fail to recover the fine details of a face.

PROPOSED SYSTEM:

In this paper we propose a novel face image SR method, namely smooth regression with local structure prior (SRLSP for short). On one hand, it adopts reconstruction constraints to ensure consistency between the reconstructed image and the input image; on the other hand, it adaptively utilizes both external and internal examples for the face image SR task. More specifically, it uses the statistical properties (by smooth regression) of the facial images in a training set as well as patch structure information (by local structure prior (LSP)) of the input LR face image to infer the missing HR pixel information. In the training phase, we extract LR patches (illustrated as black circles) and missing HR pixels (illustrated as white circles) to form the training pairs. In the testing phase, we introduce a smooth regression model to construct the relationship between an LR patch and missing HR pixels with LSP. Thus, the missing HR pixel information can be predicted by the learned SRLSP model. The proposed method has the following distinct features:

  • Instead of learning a linear regression function for the entire face, we choose to learn a smooth mapping for each position-patch by introducing a weight matrix. Therefore, the learned smooth regression can be tuned towards a specific region (position-patch) of the input LR face image.
  • By exploiting the structure prior of human face, the proposed method is able to obtain more reasonable and reliable reconstruction results from external and internal examples than these methods that learn statistical properties from an external training set only.
  • Traditional local patch representation-based face SR methods use strong regularization of “same representation” for learning. In our method, we relax the “same representation” assumption to learn the regression relationship between LR and HR images, thus providing more flexibility to the learned regression function.
  • Since our proposed method is an interpolation-based approach, it meets all the reconstruction constraints needed to ensure the consistency between reconstructed HR image and input LR image. Therefore, the reconstructed results are credible.

ADVANTAGES OF PROPOSED SYSTEM:

  • Face recognition results also validate the advantages of our proposed SR method over the state-of-the art SR methods in a face recognition application scenario.

SYSTEM ARCHITECTURE:

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

  • System : Pentium Dual Core.
  • Hard Disk : 120 GB.
  • Monitor : 15’’LED
  • Input Devices : Keyboard, Mouse
  • Ram :1GB

SOFTWARE REQUIREMENTS:

  • Operating system : Windows 7.
  • Coding Language : MATLAB
  • Tool : MATLAB R2013A

REFERENCE:

Junjun Jiang, Member, IEEE, Chen Chen, Jiayi Ma, Member, IEEE, Zheng Wang, ZhongyuanWang, Member, IEEE, and Ruimin Hu, Senior Member, IEEE, “SRLSP: A Face Image Super-Resolution AlgorithmUsing Smooth Regression with Local Structure Prior”, IEEE TRANSACTIONS ON MULTIMEDIA, 2017.

 

Neighborhood Matching For Image Retrieval

Neighborhood Matching For Image Retrieval

ABSTRACT:

In the last few years large-scale image retrieval has attracted a lot of attention from the multimedia community. Usual approaches addressing this task first generate an initial ranking of the reference images using fast approximations that do not take into consideration the spatial arrangement of local features in the image (e.g. the Bag-of-Words paradigm). The top positions of the rankings are then re-estimated with verification methods that deal with more complex information, such as the geometric layout of the image. This verification step allows pruning of many false positives at the expense of an increase in the computational complexity, which may prevent its application to large-scale retrieval problems. This paper describes a geometric method known as Neighborhood Matching (NM), which revisits the keypoint matching process by considering a neighborhood around each keypoint and improves the efficiency of a geometric verification step in the image search system. Multiple strategies are proposed and compared to incorporate NM into a large-scale image retrieval framework. A detailed analysis and comparison of these strategies and baseline methods have been investigated. The experiments show that the proposed method not only improves the computational efficiency, but also increases the retrieval performance and outperforms state-of-theart methods in standard datasets, such as the Oxford 5k and 105k datasets, for which the spatial verification step has a significant impact on the system performance.

EXISTING SYSTEM:

  • In existing paper, they proposed a new algorithm for image re-ranking in web image search applications.
  • The existing method focuses on investigating the following two mechanisms: 1) Visual consistency. In most web image search cases, the images that closely related to the search query are visually similar. These visually consistent images which occur most frequently in the first few web pages will be given higher ranks.
  • 2) Visual saliency. From visual aspect, it is obvious that salient images would be easier to catch users’ eyes, and it is observed that these visually salient images in the front pages are often relevant to the user’s query.

DISADVANTAGES OF EXISTING SYSTEM:

  • Re-ranking methods are often computationally expensive and significantly increase the retrieval time, they are commonly used only for a subset of images (the top-ranked images).

PROPOSED SYSTEM:

This paper focuses on the spatial verification step of a partial or near-duplicate image search system. We build our model on the neighborhood matching (NM) method. Rather than simply using NM as a filtering stage that eliminates false correspondences between images, we use NM for the geometrical verification step in large-scale image retrieval. The goal of our approach is to demonstrate that the computational complexity of this stage can be significantly reduced for a given performance level. There are two main contributions in this paper:

  • We have developed several strategies that incorporate the NM method into the image retrieval framework. They will be compared in terms of both retrieval performance and computational efficiency and we will show that some of them not only reduce the computational complexity at a given depth in the re-ranking step (measured as the number of images being re-ranked), but also improve the performance with respect to the traditional solutions.
  • We provide a detailed analysis of the use the NM techniques to the image retrieval problem and describe the most appropriate configurations. We will also demonstrate that our NM-based re-ranking step can be combined with other techniques involved in processing, such as extensions or improvements of the computation of the initial ranking, or query expansion methods working using geometrically-verified images.

ADVANTAGES OF PROPOSED SYSTEM:

  • We have proposed several alternative approaches to take advantage of the benefits of NM in image retrieval. Specifically, we have designed various strategies for using NM to reduce the number of potentially false matches that are passed to RANSAC in the geometrical verification step.
  • We have addressed different image retrieval tasks using the Oxford 5k, Oxford 105k and INRIA Holidays datasets and shown how the use of NM leads to a much better performance complexity compromise, producing improvements about 5% in terms of mAP with respect to the baseline approach based on RM for equivalent complexity levels.
  • Furthermore, we have compared an improved version of the proposed method with several state-of-the-art methods showing that our method outperforms other methods based on the BoW paradigm in the Oxford 5k and 105k datasets,

SYSTEM ARCHITECTURE:

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

  • System : Pentium Dual Core.
  • Hard Disk : 120 GB.
  • Monitor : 15’’LED
  • Input Devices : Keyboard, Mouse
  • Ram :1GB

SOFTWARE REQUIREMENTS:

  • Operating system : Windows 7.
  • Coding Language : MATLAB
  • Tool : MATLAB R2013A

REFERENCE:

Iv´an Gonz´alez-D´ıaz, Member, IEEE, Murat Birinci, Fernando D´ıaz-de-Mar´ıa, Member, IEEE, and Edward J.Delp, Life Fellow, IEEE , “Neighborhood Matching For Image Retrieval”, IEEETransactions on Multimedia, 2017.

 

Words Matter: Scene Text for Image Classification and Retrieval

Words Matter: Scene Text for Image Classification and Retrieval

ABSTRACT:

Text in natural images typically adds meaning to an object or scene. In particular, text specifies which business places serve drinks (e.g. cafe, tea house) or food (e.g. restaurant,pizzeria), and what kind of service is provided (e.g. massage,repair). The mere presence of text, its words and meaning are closely related to the semantics of the object or scene. This paper exploits textual contents in images for fine-grained business place classification and logo retrieval. There are four main contributions. First, we show that the textual cues extracted by the proposed method are effective for the two tasks. Combining the proposed textual and visual cues outperforms visual only classification and retrieval by a large margin. Second, to extract the textual cues, a generic and fully unsupervised word box proposal method is introduced. The method reaches state-of-the art word detection recall with a limited number of proposals.Third, contrary to what is widely acknowledged in text detection literature, we demonstrate that high recall in word detection is more important than high f-score at least for both tasks considered in this work. Last, this paper provides a large annotated text detection data set with 10K images and 27601 word boxes.

PROJECT OUTPUT VIDEO: (Click the below link to see the project output video):

EXISTING SYSTEM:

  • Most of the time, the stores use text to indicate what type of food (pizzeria, diner), drink (tea, coffee) and service(dry cleaning, repair) that they provide. This text information is helpful even for human observers to understand what type of business place it is. For instance, the images of two different business places (pizzeria and bakery) have a very similar appearance. However, they are different types of business places.
  • It is only possible with text information to identify what type of business places these are. Moreover,text is also useful to identify similar products (logo) suchas Heineken, Foster and Carlsberg.
  • The common approach to text recognition in images is todetect text first before they can be recognized. Thestate-of-the-art word detection methods focus on obtaining a high f-score by balancing precisionand recall.
  • Existing word detectionmethods usually follow a bottom-up approach. Character candidatesare computed by a connected componentor a sliding window approach.
  • Candidate character regions are further verified and combinedto form word candidates. This is done by using geometric,structural and appearance properties of text and is based onhand-crafted rules or learning schemes

DISADVANTAGES OF EXISTING SYSTEM:

  • Unfortunately, there exists no single best method for detecting words with high recall due to large variations in text style, size and orientation.
  • Weak classifiers are used.
  • Poor F-Score.

PROPOSED SYSTEM:

  • In this paper, we focus on classification of different business places, e.g., bakery, cafe and bookstore. Various business places have subtle differences in visual appearances.
  • We exploitthe recognized text in images for fine-grained classificationof business places. Automatic recognition and indexing ofbusiness places will be useful in many practical scenarios.
  • We propose amultimodal approach which uses recognized text and visualcues for fine-grained classification and logo retrieval.
  • We propose to combine character candidates generated by different state-of-the-art detection methods. To obtain robustness against varying imaging conditions, we use color spaces containing photometric invariant properties such as robustness against shadows, highlights and specular reflections.
  • The proposed method computes text lines and generates word box proposals based on the character candidates. Then, word box proposals are used as input of a state-of-the-art word recognition method to yield textual cues. Finally, textual cues are combined with visual cues for fine-grained classification and logo retrieval.

ADVANTAGES OF PROPOSED SYSTEM:

  • For instance, it can be used to extract information from Google street view images and Google Map can use the information to provide recommendations of bakeries, restaurants close to the location of the user.
  • Instead of using the f-score, our aimis to obtain a high recall. A high recall is required becausetextual cues that are not detected will not be considered inthe next (recognition) phase of the framework.
  • The proposedmethod reaches state-of-the-art results on both tasks. Second,to extract the word-level textual cues, a generic, efficientand fully unsupervised word proposal method is introduced.The proposed method reaches state-of-the-art word detectionrecall with a limited number of proposals. Third, contrary towhat is widely acknowledged in text detection literature, weexperimentally show high recall in word detection is moreimportant than high f-score at least for both applicationsconsidered in this work.

SYSTEM ARCHITECTURE:

MODULES:

  1. Word Level Textual Cue Encoding
  2. Visual Cue Encoding
  3. Classification and Retrieval

MODULES DESCRIPTION:

Word Level Textual Cue Encoding:

It having following steps,

  1. Image Acquisition
  2. Color Channel Generation
  3. Character Detection
  4. Word Proposal Generation & Word Recognition
  5. Image Acquisition:

Images are acquired from Gallery.

  1. Color Channel Generation:

In that stage, RGB image is converted into HSV image. After that Hue, Saturation and Intensity channels are extracted for further process.  Especially intensity channel is used for character detection.

  1. Character Detection:

For character detection, we proposed two methods such as MSER region detection and text saliency generation. V channel is used for MSER region detection. In that text region is not detected properly. Another method is saliency map generation for text detection. Finally text saliency was extracted.

  1. Word Proposal Generation & Word Recognition:

Word detection and recognition done by using morphological operation and optical character recognition method. It has following steps,

Stage 1:

In this stage text saliency image acquisition and word region detection are performed. For the first, a text saliency image is taken as input. The image taken is in the RGB format. Then the image is converted to gray scale image. After converting the RGB image to gray image.

Stage 2:

In this stage word extraction and word segmentation is performed. For that morphological dilation and erosion operations are performed to fill holes. After applying morphological operations, local thresholding is applied to covert gray image into binary image. In order to get further contrast enhancement, intensity range of the pixel values are scaled between 0 to 1. In certain situations if some unwanted gaps and holes are present in the word region. Then region growing segmentation is performed to segment characters from the word region.

Stage 3:

In this stage word recognition is done using template matching. Each segmented character is matched with character templates stored in database. Finally the word was recognized.

Visual cue Encoding:

This stage is implemented for visual features extraction. SURF feature descriptor is used for visual features extraction. Strongest key points are extracted by SURF.

Classification and Retrieval:

The classification process is done over the recognized word and visual features. Based on the recognized word and features, classification and similar images retrieval are explored.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

  • System : Pentium Dual Core.
  • Hard Disk : 120 GB.
  • Monitor : 15’’LED
  • Input Devices : Keyboard, Mouse
  • Ram :1GB

SOFTWARE REQUIREMENTS:

  • Operating system : Windows 7.
  • Coding Language : MATLAB
  • Tool : MATLAB R2013A

REFERENCE:

SezerKaraogluy, Ran Taoy, Theo Gevers and Arnold W. M. Smeulders, “Words Matter: Scene Text for Image Classificationand Retrieval”, IEEE Transactions on Multimedia, 2017.

 

Hierarchical Guidance Filtering-Based Ensemble Classification for Hyperspectral Images

Hierarchical Guidance Filtering-Based Ensemble Classification for Hyperspectral Images

ABSTRACT:

Joint spectral and spatial information should be fully exploited in order to achieve accurate classification results for hyperspectral images. In this paper, we propose an ensemble framework, which combines spectral and spatial information in different scales. The motivation of the proposed method derives from the basic idea: by integrating many individual learners, ensemble learning can achieve better generalization ability than a single learner. In the proposed work, the individual learners are obtained by joint spectral-spatial features generated from different scales. Specially, we develop two techniques to construct the ensemble model, namely, hierarchical guidance filtering (HGF) and matrix of spectral angle distance (mSAD). HGF and mSAD are combined via a weighted ensemble strategy. HGF is a hierarchical edge-preserving filtering operation, which could produce diverse sample sets. Meanwhile, in each hierarchy, a different spatial contextual information is extracted. With the increase of hierarchy, the pixels spectra tend smooth, while the spatial features are enhanced. Based on the outputs of HGF, a series of classifiers can be obtained. Subsequently, we define a low-rank matrix, mSAD, to measure the diversity among training samples in each hierarchy. Finally, an ensemble strategy is proposed using the obtained individual classifiers and mSAD. We term the proposed method as HiFi-We. Experiments are conducted on two popular data sets, Indian Pines and Pavia University, as well as a challenging hyperspectral data set used in 2014 Data Fusion Contest (GRSS_DFC_2014). An effectiveness analysis about the ensemble strategy is also displayed.

EXISTING SYSTEM:

  • In existing paper, they proposed a novel method using independent component analysis (ICA) and edge-preserving filtering (EPF) via an ensemble strategy for the classification of hyperspectral data.
  • First, several subsets are randomly selected from the original feature space.
  • Second, ICA is used to extract spectrally independent components followed by an effective EPF method, to produce spatial features. Two strategies (i.e., parallel and concatenated) are presented to include the spatial features in the analysis.
  • The spectral-spatial features are then classified with a random forest or a rotation forest classifier.

DISADVANTAGES OF EXISTING SYSTEM:

  • In existing, they combined independent component analysis and EPF via an ensemble strategy. However, since EPF is still a kind of smoothing filtering method, it is difficult to determine what level of filtering is the most appropriate.
  • Stronger smoothing could result in better spatial representation, but at the same time lead to more loss of spectral information.

PROPOSED SYSTEM:

In this paper, we present a novel ensemble learning-based HSI classification method, which is composed of joint spectral-spatial features of different scales. First, in order to exploit the joint spectral-spatial information, we propose a hierarchical feature extraction strategy, hierarchical guidance filtering (HGF). HGF is an extension of guided filtering (GF) and rolling guidance filtering (RGF), which is able to generate a series of joint spectral-spatial features. Spatial contextual information of different scales is obtained by the filtering in different hierarchies. Second, instead of using complicated optimization techniques, we define a metric matrix, matrix of spectral angle distance (mSAD), to evaluate the feature quality in each hierarchy. Based on the obtained hierarchical features and the evaluation results, a popular ensemble strategy, the weighted voting, is employed to determine the final classification results. We term the proposed method as HiFi-We.

The initial motivations of this paper include two aspects. First, we want to combine the joint spectral-spatial information in different scales. The classification model should be determined from a more representative feature space. Second, spectral-spatial features extracted from different scales should have different contributions. More reliable and qualified features should get higher confidence. The solution comes as no surprise: we propose the HGF to obtain a series of spectral-spatial features from different scales; then, we design an ensemble model to simultaneously utilize these features; a new weighting method, mSAD, is also developed.

The major contributions of HiFi-We can be summarized as follows.

1) A new ensemble-based HSI classification method is proposed, where joint spectral-spatial information of different scales is combined.

2) We develop the HGF to extract more various spectral-spatial features.

3) The mSAD is designed and used to generate the weight coefficients in the ensemble model.

ADVANTAGES OF PROPOSED SYSTEM:

  • To evaluate the performance of the proposed method, we conduct contrast experiments with some state-of-the-art methods on two popular data sets and a challenging data set. The results indicate that the proposed method works well, and the effectiveness is verified via statistical evaluation.

SYSTEM ARCHITECTURE:

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

  • System : Pentium Dual Core.
  • Hard Disk : 120 GB.
  • Monitor : 15’’LED
  • Input Devices : Keyboard, Mouse
  • Ram :1GB

SOFTWARE REQUIREMENTS:

  • Operating system : Windows 7.
  • Coding Language : MATLAB
  • Tool : MATLAB R2013A

REFERENCE:

Bin Pan, Zhenwei Shi, Member, IEEE, and Xia Xu, “Hierarchical Guidance Filtering-Based Ensemble Classification for Hyperspectral Images”, IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2017.

 

Higher Order Dynamic Conditional Random Fields Ensemble for Crop Type Classification in Radar Images

Higher Order Dynamic Conditional Random Fields Ensemble for Crop Type Classification in Radar Images

ABSTRACT:

The rising food demand requires regular agriculture land-cover updates to support food security initiatives. Agricultural areas undergo dynamic changes throughout the year, which manifest varying radar backscatter due to crop phenology. Certain crops can show similar backscatter if their phenology intersects, but vary later when their phenology differs. Hence, classification techniques based on single-date remote sensing images may not offer optimal results for crops with similar phenology. Moreover, methods that stack images within a cropping season as composite bands for classification limit discrimination to one feature space vector, which can suffer from overlapping classes. Nonetheless, phenology can aid classification of crops, because their backscatter varies with time. This paper fills this gap by introducing a crop sequence-based ensemble classification method where expert knowledge and TerraSAR-X multitemporal image-based phenological information are explored. We designed first-order and higher order dynamic conditional random fields (DCRFs) including an ensemble technique. The DCRF models have a duplicated structure of temporally connected CRFs, which encode image-based phenology and expert-based phenology knowledge during classification. On the other hand, our ensemble generates an optimal map based on class posterior probabilities estimated by DCRFs. These techniques improved crop delineation at each epoch, with higher order DCRFs (HDCRFs) giving the best accuracy. The ensemble method was evaluated against the conventional technique of stacking multitemporal images as composite bands for classification using maximum likelihood classifier (MLC) and CRFs. It surpassed MLC and CRFs based on class posterior probabilities estimated by both first-order DCRFs and HDCRFs.

EXISTING SYSTEM:

  • In existing paper, they presented a method for the multitemporal and contextual classification of georeferenced optical remote sensing images acquired at different epochs and having different geometrical resolutions.
  • The method is based on Conditional Random Fields (CRFs) for contextual classification. The CRF model is expanded by temporal interaction terms that link neighboring epochs via transition probabilities between different classes.
  • In order to be able to deal with data of different resolution, the class structure at different epochs may vary with the resolution. The goal of the multitemporal classification is an improved classification performance at all individual epochs, but also the detection of land-cover changes, possibly using lower resolution data.

DISADVANTAGES OF EXISTING SYSTEM:

  • In existing, noted that incorrect determination of transition matrix could lead to erroneous transfer of information to other epochs consequently reducing classification accuracy.

PROPOSED SYSTEM:

The main aim of this paper is to design a spatial–temporal dynamic ensemble technique for crop type classification from a sequence of multitemporal radar images. For this reason, the following specific contributions are made: 1) to design

a suitable spatial interaction model, expanded from contrast sensitive model, to moderate changes in class labels based on data evidence; 2) to propose a dynamic temporal interaction model to integrate image- and expert-based phenological information during crop classification; and 3) to design an ensemble framework to generate an optimal season crop map. We adopted DCRFs for sequence crop classification. The framework allows reasoning via the Bayesian theory in a principled statistical manner under uncertainty. We incorporate DCRFs into CRFs as a temporal classifier template. This forms a robust spatial–temporal sequence crop classifier template termed as DCRFs, because: 1) of a dynamic probabilistic relational model between nodes in the sequence; 2) DCRFs captures temporal phenomena, encodes complex relationships in all possible classes, and data including uncertainty in a principled manner; and 3) the model is a conditional distribution that factorizes according to an undirected graphical model whose structure and parameters are repeated over a sequence. The DCRF models (first order and higher order) estimate class posterior probabilities, which are then adopted to generate an optimal crop land-cover map using a proposed classifier ensemble model.

ADVANTAGES OF PROPOSED SYSTEM:

  • Our max F1-score model performed better than other existing ensembles and also compared with stacking multitemporal images for classification.
  • In addition, the designed technique detected changes in crop parcels. This presents the possibility of using it to monitor changes in agricultural areas, i.e., due to farm management or natural disasters like wind destruction of crops.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

  • System : Pentium Dual Core.
  • Hard Disk : 120 GB.
  • Monitor : 15’’LED
  • Input Devices : Keyboard, Mouse
  • Ram :1GB

SOFTWARE REQUIREMENTS:

  • Operating system : Windows 7.
  • Coding Language : MATLAB
  • Tool : MATLAB R2013A

REFERENCE:

Benson KipkemboiKenduiywo, Damian Bargiel, and UweSoergel, Member, IEEE, “Higher Order Dynamic Conditional Random FieldsEnsemble for Crop Type Classificationin Radar Images”, IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2017.