Image Retrieval Based on BoVW and Hashing

Currently, this paper propose an image retrieval method based on BoVW and hashing.Firstly, select an appropriate binary hashing algorithm, which map the similar local feature points into similar binary hash codes.Second, play k-means on the binary hash codes and generate the visual vocabulary with binary visual word.Finally, the image is represented with the word frequency vector of visual words, and image retrieval is achieved based on the word frequency vector.Experimental results on SIFT-1Mand Caltech-256 data sets show that the proposed method can reduce the visual vocabulary generation time and take up less storage space.