Skip to main navigation Skip to search Skip to main content

Towards a comprehensive assessment of wound-composition using color-image processing

  • Rohit Nayak*
  • , Pramod Kumar
  • , Ramesh R. Galigekere
  • *Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    This paper reports the results of our work on assessing wound-composition based on color-image processing. A knowledge-base (reference-clusters in the 3D color space) of different categories of wound-tissue and pigmentation was built, using about 9000 pixels from 48 images of various wounds. The HSI model was used for the purpose. We address 8 categories of wound-tissue and pigmentation, many more than those reported so far in the literature. The knowledge base was used subsequently for assessing wound-composition, through classification based on Mahalanobis distance. The results of experiments to test the efficacy of the algorithm are encouraging.

    Original languageEnglish
    Title of host publication2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings
    PublisherIEEE Computer Society
    Pages4185-4188
    Number of pages4
    ISBN (Print)9781424456543
    DOIs
    Publication statusPublished - 01-01-2009
    Event2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt
    Duration: 07-11-200910-11-2009

    Publication series

    NameProceedings - International Conference on Image Processing, ICIP
    ISSN (Print)1522-4880

    Conference

    Conference2009 IEEE International Conference on Image Processing, ICIP 2009
    Country/TerritoryEgypt
    CityCairo
    Period07-11-0910-11-09

    All Science Journal Classification (ASJC) codes

    • Software
    • Computer Vision and Pattern Recognition
    • Signal Processing

    Fingerprint

    Dive into the research topics of 'Towards a comprehensive assessment of wound-composition using color-image processing'. Together they form a unique fingerprint.

    Cite this