Abstract
Stable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid (June 2003) recently evaluated a variety of approaches and identified the SIFT [D. G. Lowe, 1999] 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 PCA-based 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.
Keywords
Scale-invariant feature transformArtificial intelligencePattern recognition (psychology)Feature (linguistics)Principal component analysisHistogramComputer scienceComputer visionSalientFeature extractionImage (mathematics)Representation (politics)Matching (statistics)Feature detection (computer vision)MathematicsImage processing
Affiliated Institutions
Related Publications
ORB: An efficient alternative to SIFT or SURF
Feature matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods rely on costly descriptors for detection a...
From Bits to Images: Inversion of Local Binary Descriptors
Local Binary Descriptors are becoming more and more popular for image matching tasks, especially when going mobile. While they are extensively studied in this context, their abi...
Natural Feature Detection on Mobile Phones with 3D FAST
In this paper, we present a novel feature detection approach designed for mobile devices, showing optimized solutions for both detection and description. It is based on FAST (Fe...
Video Google: a text retrieval approach to object matching in videos
We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a s...
Multi-Image Matching Using Multi-Scale Oriented Patches
This paper describes a novel multi-view matching framework based on a new type of invariant feature. Our features are located at Harris corners in discrete scale-space and orien...
Publication Info
- Year
- 2004
- Type
- article
- Volume
- 2
- Pages
- 506-513
- Citations
- 3204
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
3204
OpenAlex
Cite This
Ke Yan,
Rahul Sukthankar
(2004).
PCA-SIFT: a more distinctive representation for local image descriptors.
, 2
, 506-513.
https://doi.org/10.1109/cvpr.2004.1315206
Identifiers
- DOI
- 10.1109/cvpr.2004.1315206