Slashdot Mirror

← Back to Stories (view on slashdot.org)

Google VisualRank for Image Search

Posted by ScuttleMonkey on from the they-don't-quite-own-the-world-yet dept.

Google researchers are claiming that a newly developed approach to visual search may do for image searching what PageRank did for text search. "The research paper, 'PageRank for Product Image Search,' is focused on a subset of the images that the giant search engine has cataloged because of the tremendous computing costs required to analyze and compare digital images. To do this for all of the images indexed by the search engine would be impractical, the researchers said. Google does not disclose how many images it has cataloged, but it asserts that its Google Image Search is the 'most comprehensive image search on the Web.'"

3 of 63 comments (clear)

  1. Excellent! by Tree131 · · Score: 3, Funny

    Sweet!!! More exact pr()n searches!!! Wohooo!!!!

  2. Re:paper reference by Rui+Lopes · · Score: 3, Informative

    http://www2008.org/papers/fp506.html No DOI currently available, but pdf link is in the page.

    --
    var sig = function() { sig(); }
  3. findimagedupes image similarity algorithm by Danny+Rathjens · · Score: 4, Interesting
    I noticed this nifty little program in debian called findimagedupes. The algorithm for fingerprinting the files for comparing similarity is neat. From the man page:

    To calculate an image fingerprint:
    1. 1) Read image.
    2. 2) Resample to 160x160 to standardize size.
    3. 3) Grayscale by reducing saturation.
    4. 4) Blur a lot to get rid of noise.
    5. 5) Normalize to spread out intensity as much as possible.
    6. 6) Equalize to make image as contrasty as possible.
    7. 7) Resample again down to 16x16.
    8. 8) Reduce to 1bpp.
    9. 9) The fingerprint is this raw image data.
    To compare two images for similarity:
    1. 1) Take fingerprint pairs and xor them.
    2. 2) Compute the percentage of 1 bits in the result.
    3. 3) If percentage exceeds threshold, declare files to be similar.