Abstract—Scale Invariant Feature Transform (SIFT) features are identified as being invariant to common image deformations caused by the rotation, scaling, and illumination. In this paper, we apply VQ histogram as an alternate representation for SIFT features. Experimental results demonstrate that SIFT features using VQ-based local descriptors are more robust to image deformations and lead to better image retrieval results than original SIFT algorithm.

Index Terms—SIFT features, vector quantization histogram, local descriptor, image retrieval.

Qiu Chen, Feifei Lee, and Tadahiro Ohmi are with New Industry Creation Hatchery Center, Tohoku University, Sendai, 980-8579 Japan (e-mail:qiu@fff.niche.tohoku.ac.jp).
Koji Kotani is with Department of Electronics, Graduate School of Engineering, Tohoku University, Sendai, 980-8579 Japan.

Cite: Qiu Chen, Koji Kotani, Feifei Lee, and Tadahiro Ohmi, "SIFT Features Using Vector Quantization histogram for Image Retrieval," International Journal of Computer and Electrical Engineering vol. 4, no. 5, pp. 688-692, 2012.