No Reference Image and Video Quality Assessment

The Quality Assessment research at LIVE is being conducted in collaboration with CPS

Introduction

No-Reference Quality Assessment is a relatively new research direction, with promising applications but little progress. Objective quality assessment is a very complicated task, and even full-reference QA methods have had only limited success in making accurate quality predictions. Researchers therefore tend to break up the problem of NR QA into smaller, domain-specific problems by targeting a limited class of artifacts. The most common being the blocking-artifact, which is usually the result of block-based compression algorithms running at low bit rates. At LIVE we have conducted research into NR QA for blocking distortion as well as pioneering research into NR measurement of distortion introduced by Wavelet based compression algorithms based on Natural Scene Statistics modeling.

No-Reference Quality Assessment algorithm for Block-Based compression artifacts

Perhaps the most common distortion type that one comes across in real-world applications is the distortion introduced by lossy compression algorithms, such as JPEG (for images) or MPEG/H.263 (for videos). These compression algorithms are based on reduction of spatial redundancies using the block-based Discrete Cosine Transform (DCT). When these algorithms are constrained to increase the amount of compression, a visible 'blocking' artifact can be seen.

Blocking resulting from DCT based compression algorithms running at low bit rates has a very regular profile. It manifests itself as an edge every 8 pixels (for the typical block-size of 8 x 8 pixels), oriented in the horizontal and vertical directions. The strength of the blocking artifact can be measured by estimating the strength of these block-edges. At LIVE, we have developed frequency domain algorithms for measuring blocking artifact in images compressed by JPEG, with the algorithm having no information about the reference image.

Relevant Publications

1. Z. Wang, H. R. Sheikh and A. C. Bovik, "No-reference perceptual quality assessment of JPEG compressed images", Proc. IEEE International Conference on Image Processing, pp. 477-480, Rochester, New York, September 22-25, 2002.
2. L. Lu, Z. Wang, A. C. Bovik and J. Kouloheris, "Full-Reference Video Quality Assessment Considering Structural Distortion and No-Reference Quality Evaluation of MPEG Video", Proc. IEEE International Conference on Multimedia and Expo, vol. 1, pp. 61-64, Lausanne, Switzerland, August 26-29, 2002.
3. S. Liu and A. C. Bovik, "DCT domain blind measurement of blocking artifacts in DCT-coded images", Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 3, pp. 1725-1728, Salt Lake City,Utah, May 07-11, 2001.
4. Z. Wang, A. C. Bovik, and B. L. Evans, "Blind measurement of blocking artifacts in images", Proc. IEEE International Conference on Image Processing, vol. 3, pp. 981-984, Vancouver, Canada, September 10-13, 2000.

No-Reference Quality Assessment for JPEG2000 Compressed Images using Natural Scene Statistics.

Not all compression algorithms are block-based. Recent research in image and video coding algorithms has revealed that a greater compression can be achieved for the same visual quality if the block-based DCT approach is replaced by a Discrete Wavelet Transform (DWT). JPEG2000 is a recent image compression standard that uses DWT for image compression. However, DWT based algorithms also suffer from artifacts at low bit rates, specifically, from blurring and ringing artifacts. Blurring and ringing artifacts are image dependent, unlike the blocking artifact, whose spatial location is predictable. This makes the task of quantifying distortion resulting from DWT based compression algorithms (such as the JPEG2000) much harder to quantify. At LIVE we have proposed a unique and innovative solution to the problem. We propose to use Natural Scene Statistics models to quantify the departure of a distorted image from "expected" natural behavior.

Software Release

• Please click here for software release 

Relevant Publications  

1. H. R. Sheikh, A. C. Bovik, and L. K. Cormack, "No-Reference Quality Assessment Using Natural Scene Statistics: JPEG2000," IEEE Transactions on Image Processing, vol. 14, no. 12, December 2005.
2. H. R. Sheikh, A. C. Bovik, and L. Cormack, "Blind Quality Assessment of JPEG2000 Compressed Images Using Natural Scene Statistics," Proc. IEEE Asilomar Conf. on Signals, Systems, and Computers, Nov. 2003, Pacific Grove, CA.
3. H.R. Sheikh, Z. Wang, L. K. Cormack and A.C. Bovik, "Blind quality assessment for JPEG2000 compressed images," Proc. Thirty-Sixth Annual Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, California, November 03-06, 2002.
   

Back to Quality Assessment Research page