• DocumentCode
    1137399
  • Title

    Image enhancement in the JPEG domain for people with vision impairment

  • Author

    Tang, Jinshan ; Kim, Jeonghoon ; Peli, Eli

  • Volume
    51
  • Issue
    11
  • fYear
    2004
  • Firstpage
    2013
  • Lastpage
    2023
  • Abstract
    An image enhancement algorithm for low-vision patients was developed for images compressed using the JPEG standard. The proposed algorithm enhances the images in the discrete cosine transform domain by weighting the quantization table in the decoder. Our specific implementation increases the contrast at all bands of frequencies by an equal factor. The enhancement algorithm has four advantages: 1) low computational cost; 2) suitability for real-time application; 3) ease of adjustment by end-users (for example, adjusting a single parameter); and 4) less severe block artifacts as compared with conventional (post compression) enhancements. Experiments with visually impaired patients show improved perceived image quality at moderate levels of enhancement but rejection of artifacts caused by higher levels of enhancement.
  • Keywords
    discrete cosine transforms; image enhancement; medical image processing; vision defects; JPEG; block artifacts; compressed images; discrete cosine transform; image enhancement; improved perceived image quality; low-vision patients; vision impairment; Computational efficiency; Decoding; Discrete cosine transforms; Frequency; Image coding; Image enhancement; Image quality; Quantization; Standards development; Transform coding; Algorithms; Communication Aids for Disabled; Computer Terminals; Humans; Hypermedia; Image Enhancement; Image Interpretation, Computer-Assisted; Television; Video Recording; Vision, Low; Visually Impaired Persons;
  • fLanguage
    English
  • Journal_Title
    Biomedical Engineering, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0018-9294
  • Type

    jour

  • DOI
    10.1109/TBME.2004.834264
  • Filename
    1344204