Authors:
Afra'a Ahmad Alyosef
and
Andreas Nürnberger
Affiliation:
Otto von Geruicke University Magdeburg, Germany
Keyword(s):
Image Near Duplicate Retrieval, SIFT Descriptor, RC-SIFT 64D, Feature Extraction.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Data Engineering
;
Feature Selection and Extraction
;
Geometry and Modeling
;
Image Understanding
;
Image-Based Modeling
;
Information Retrieval
;
Information Retrieval and Learning
;
Ontologies and the Semantic Web
;
Pattern Recognition
;
Software Engineering
;
Theory and Methods
Abstract:
The scale invariant feature transformation algorithm (SIFT) has been designed to detect and characterize local features in images. It is widely used to find similar regions in affine transformed images, to recognize similar objects or to retrieve near-duplicates of images. Due to the computational complexity of SIFT based matching operations several approaches have been proposed to speed up this process. However, most approaches lack significant decrease of matching accuracy compared to the original descriptor. We propose an approach that is optimized for near-duplicate image retrieval tasks by a dimensionality reduction process that differs from other methods by preserving the information around the keypoints of any region patches of the original descriptor. The computation of the proposed Region Compressed (RC) SIFT−64D descriptors is therefore faster and requires less memory for indexing. Most important, the obtained features show at the same time a better retrieval performance an
d seem to be even more robust. In order to prove this, we provide results of a comparative performance analysis using the original SIFT−128D, reduced SIFT versions, SURF−64D and the proposed RC-SIFT−64D in image near-duplicate retrieval using large scale image benchmark databases.
(More)