Perceptual Image Indexing and Retrieval

M Mirmehdi, R Perissamy

Research output: Contribution to journalArticle (Academic Journal)peer-review

5 Citations (Scopus)


We describe a perceptual approach to generating features for use in indexing and retrieving images from an image database. Salient regions that immediately attract the eye are large color regions that usually dominate an image. Features derived from these will allow search for images that are similar perceptually. We compute color features and Gabor color texture features on regions obtained from a multiscale representation of the image, generated by a multiband smoothing algorithm based on human psychophysical measurements of color appearance. The combined feature vector is then used for indexing all salient regions of an image. For retrieval, those images are selected that contain more similar regions to the query image by using a multipass retrieval and ranking mechanism. Matches are found using the L2 metric. The results demonstrate that the proposed method performs very well.
Translated title of the contributionPerceptual Image Indexing and Retrieval
Original languageEnglish
Pages (from-to)460 - 475
Number of pages15
JournalJournal of Visual Communication and Image Representation
Volume13 (4)
Publication statusPublished - Dec 2002


Dive into the research topics of 'Perceptual Image Indexing and Retrieval'. Together they form a unique fingerprint.

Cite this