Recently, due to the existence of semantic gap between image visual features and human concepts, the semanticof image auto-annotation has become an important topic. Firstly, by extract low-level visual features of the image, andthe corresponding Hash method, mapping the feature into the corresponding Hash coding, eventually, transformed thatinto a group of binary string and store it, image auto-annotation by search is a popular method, we can use it to design andimplement a method of image semantic auto-annotation. Finally, Through the test based on the Corel image set, and theresults show that, this method is effective.
展开▼