Scale-Invariant Feature Extraction by VQ-Based Local Image Descriptor

SIFT (scale invariant feature transform) feature is identified as being invariant to common image deformations caused by the rotation, scaling, and illumination. In this paper, instead of using SIFT's smoothed weighted orientation histograms, we apply vector quantization (VQ) histogram as an alternate representation for local image descriptor. Experimental results demonstrate that the VQ-based local descriptors are more robust to image deformations.