Revision as of 07:56, 15 March 2011 edit Citation bot 1 (talk \| contribs) Bots 130,044 edits mNo edit summary ← Previous edit		Revision as of 05:43, 16 December 2011 edit undo Stuartyeates (talk \| contribs) Extended confirmed users, New page reviewers, Pending changes reviewers, Rollbackers 73,779 edits Disambiguated: SIFT → Scale-invariant feature transform Next edit →
Line 65: * [[Difference of Gaussians]] * Edge based operator, described in the study Using these 4 detectors, approximately 700 features were detected per image. These features were then encoded as [[~~SIFT\|~~Scale-invariant feature transform]] descriptors, and vector quantized to match one of 350 words contained in a codebook. The codebook was precomputed from features extracted from a large number of images spanning numerous object categories. ==== Possible object locations ====

Object categorization from image search: Difference between revisions