The binary image retrieval based on the improved shape context
He Yan, Lei Yang, Yichun Zhang, Xiaoyu Wu, Yun Zhang · 2014
Considering the requirement for a more objective result of image retrieval, the features of image itself attract more and more attentions of researchers. Recently, the shape context of images is widely applied in image matching for its good invariance of translation and scale, as well as its good robust for small geometric distortion. Thus, the features of shape context are introduced in this paper to conduct the retrieval of binary images. However, due to the lack of rotation invariance, a kind of improved feature of shape context is proposed, which ensures the rotation invariance by means of looking for the direction where the most sampling points are included. Through experiment we can find that in the case of the same recall rate, the precision rate of the algorithm in this paper is obviously better than the traditional algorithm of shape context. Furthermore, the calculating time of the proposed algorithm is reduced compared with the way in which rotation invariance is introduced in the images that are rotated many times. Therefore, the overall performance is improved, obtaining more satisfying result of retrieval.