A Feature-Enriched Completely Blind Image Quality Evaluator

  • November 19, 2015
  • Blog
No Comments

A Feature-Enriched Completely Blind Image Quality Evaluator


Existing blind image quality assessment (BIQA) methods are mostly opinion-aware. They learn regression models from training images with associated human subjective scores to predict the perceptual quality of test images. Such opinion-aware methods, however, require a large amount of training samples with associated human subjective scores and of a variety of distortion types. The BIQA models learned by opinion-aware methods often have weak generalization capability, hereby limiting their usability in practice. By comparison, opinion-unaware methods do not need human subjective scores for training, and thus have greater potential for good generalization capability. Unfortunately, thus far no opinion-unaware BIQA method has shown consistently better quality prediction accuracy than the opinion-aware methods. Here, we aim to develop an opinion unaware BIQA method that can compete with, and perhaps outperform, the existing opinion-aware methods. By integrating the features of natural image statistics derived from multiple cues, we learn a multivariate Gaussian model of image patches from a collection of pristine natural images. Using the learned multivariate Gaussian model, a Bhattacharyya-like distance is used to measure the quality of each image patch, and then an overall quality score is obtained by average pooling. The proposed BIQA method does not need any distorted sample images nor subjective quality scores for training, yet extensive experiments demonstrate its superior quality-prediction performance to the state-of-the-art opinion-aware BIQA methods.


  • A majority of existing BIQA methods are “opinion aware”, which means that they are trained on a dataset consisting of distorted images and associated subjective scores. Representative methods belonging to this category include and they share a similar architecture. In the training stage, feature vectors are extracted from the distorted images, then a regression model is learned to map the feature vectors to the associated human subjective scores. In the test stage, a feature vector is extracted from the test image and then fed into the learned regression model to predict its quality score.
  • In Moorthy and Bovik proposed a two-step framework for BIQA, called BIQI. In BIQI, given a distorted image, scene statistics are at first extracted and used to explicitly classify the distorted image into one of n distortions; then, the same set of statistics are used to evaluate the distortion-specific quality. Following the same paradigm, Moorthy and Bovik later extended BIQI to DIIVINE using a richer set of natural scene features.
  • Both BIQI and DIIVINE assume that the distortion types in the test images are represented in the training dataset, which is, however, not the case in many practical applications. By assuming that the statistics of DCT features can vary in a predictable way as the image quality changes, Saad et al.proposed a BIQA model, called BLIINDS, by training a probabilistic model based on contrast and structure features extracted in the DCT domain.


  • Existing trained BIQA models have been trained on and thus are dependant to some degree on one of the available public databases. When applying a model learned on one database to another database, or to real-world distorted images, the quality prediction performance can be very poor.


  • We have proposed an effective new BIQA method that extends and improves upon the novel “completely blind” IQA concept introduced in the new model IL-NIQE.
  • Extracts five types of NSS features from a collection of pristine naturalistic images, and uses them to learn a multivariate Gaussian (MVG) model of pristine images, which then serves as a reference model against which to predict the quality of the image patches.
  • For a given test images ,its patches are thus quality evaluated, then patch quality scores are averaged, yielding an over the quality score.
  • We demonstrate that “completely blind” opinion-unaware IQA models can achieve more robust quality prediction performance than opinion-aware models. Such a model and algorithm can be used in innumerable practical applications. We hope that these results will encourage both IQA researchers and imaging practitioners to more deeply consider the potential of opinion-unaware “completely blind” BIQA models.


  • IL-NIQE yields much better quality prediction performance.





  • System : Pentium IV 2.4 GHz.
  • Hard Disk : 40 GB.
  • Floppy Drive : 44 Mb.
  • Monitor : 15 VGA Colour.
  • Mouse :
  • Ram : 512 Mb.


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


Lin Zhang, Member, IEEE, Lei Zhang, Senior Member, IEEE, and Alan C. Bovik, Fellow, IEEE, “A Feature-Enriched Completely Blind Image Quality Evaluator”, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 24, NO. 8, AUGUST 2015.

Fields marked with an * are required



Please, let us know the best time to contact you by phone (if provided).

I would like to get new blog posts by email