PCA-SIFT: A more distinctive representation for local image descriptors

DMCA

PCA-SIFT: A more distinctive representation for local image descriptors (2004)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Yan Ke , Rahul Sukthankar

Citations:

571 - 6 self

BibTeX

@INPROCEEDINGS{Ke04pca-sift:a,
    author = {Yan Ke and Rahul Sukthankar},
    title = {PCA-SIFT: A more distinctive representation for local image descriptors},
    booktitle = {},
    year = {2004},
    pages = {506--513},
    publisher = {}
}

OpenURL

Abstract

Stable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid [14] recently evaluated a variety of approaches and identified the SIFT [11] algorithm as being the most resistant to common image deformations. This paper examines (and improves upon) the local image descriptor used by SIFT. Like SIFT, our descriptors encode the salient aspects of the image gradient in the feature point's neighborhood; however, instead of using SIFT's smoothed weighted histograms, we apply Principal Components Analysis (PCA) to the normalized gradient patch. Our experiments demonstrate that the PCAbased local descriptors are more distinctive, more robust to image deformations, and more compact than the standard SIFT representation. We also present results showing that using these descriptors in an image retrieval application results in increased accuracy and faster matching.

Keyphrases

local image descriptor distinctive representation image deformation increased accuracy object recognition algorithm fundamental component image gradient pcabased local descriptor standard sift representation salient aspect weighted histogram normalized gradient patch image retrieval application result principal component analysis feature point many image registration faster matching common image deformation present result stable local feature detection

DMCA