Rotated k-means hashing for image retrieval problems

Hamming embedding is shown to be efficient for solving large scale image retrieval problems. The k-means hashing is applied to find compact binary codes for hashing. On the other hand, the iterative quantization hashing has been proposed to find better hash codes by minimizing the quantization error between binary hash code and hash function output values of images. The k-means hashing distorts the hypercube of binary codes to minimize quantization error while the iterative quantization hashing rotates the feature vector of images to minimize the quantization error. The proposed rotated k-means hashing combines the distortion of hypercube with the rotation of feature vector of images for further minimization of quantization error. Experimental results show the RKMH preserves good similarities among images.