Image & Video Quality Assessment at LIVE

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

Introduction to Image and Video Quality Assessment

Subjective Image and Video Quality Assessment Research at LIVE

• Video Quality Assessment Research at LIVE
  On-going video quality assessment research at LIVE includes development of algorithms for objective quality assessment of video, as well as construction of a video quality assessment database to complement our image quality assessment database. Below are two videos which describe this broad effort. Click on the images below to watch the video. Alternatively, the videos may be downloaded for offline view here and here.
  
  

  
  

• LIVE Image Quality Assessment Database
  Download an image database containing distorted images and their subjective evaluations. 
• Objective Quality Assessment research using this database
  • Information Theoretic approaches to Image Quality Assessment research at LIVE
  • No-Reference Quality Assessment research for JPEG2000 images at LIVE
  • Structural Similarity Index (SSIM) research at LIVE

Objective Quality Assessment Research at LIVE

• Full-Reference Quality Assessment: 
  Information theoretic methods, structural similarity based image quality assessment and foveated image quality index.
• No-Reference Quality Assessment
  Quality assessment of block transform-based image coding and quality prediction using natural scene statistics.

Software Release

• Visual Information Fidelity (VIF) measure for Image Quality Assessment. Download here. You need Steerable Pyramid toolbox to run it.
  • H.R. Sheikh.and A.C. Bovik, "Image information and visual quality," Image Processing, IEEE Transactions on, vol.15, no.2,pp. 430- 444, Feb. 2006.  
• Pixel domain version of VIF. A computationally simpler, multi-scale pixel domain implementation of VIF whose performance is slightly worse than the Wavelet domain version above can be downloaded here. Read More.
• Information Fidelity Criterion for Image Quality Assessment Using Natural Scene Statistics. Download here. Note: Visual Information Fidelity (VIF) is an extension and improvement. You need Steerable Pyramid toolbox to run it.
  • H.R. Sheikh, A.C. Bovik and G. de Veciana, "An information fidelity criterion for image quality assessment using natural scene statistics," Image Processing, IEEE Transactions on , vol.14, no.12pp. 2117- 2128, Dec. 2005.
• No Reference Image quality assessment for JPEG2000. Download here.
  • 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.
• Structural Similarity Index (SSIM). Visit SSIM's new page for a Matlab implementation of the metric. A LabView implementation of the SSIM index can be downloaded here.
  • Z. Wang, A.C. Bovik, H.R. Sheikh and E.P. Simoncelli, "Image quality assessment: from error visibility to structural similarity," Image Processing, IEEE Transactions on , vol.13, no.4pp. 600- 612, April 2004.

Image and Video Quality Assessment Links

• Video Quality Experts Group
• Data Compression info: plenty of useful information on loss-less and lossy data compression.
• If you want your web page linked to ours, submit your link here.

The Quality Assessment web pages are being maintained by Kalpana Seshadrinathan