Based on color histogram, a new search method is presented in this paper. Firstly, the image is divided into background and target through the threshold. And then the target image is split into fan-shaped isometric region. Calculate the third-order moment as feature vectors and realize image retrieval by the similarity comparing between the images. This method not only rules out background interference, but also reflects the position of the goals. Experimental results show that this improved approach is better than the simple use of color histogram in an accurate survey.
展开▼