Abstract:

A new method for mudattaching wheel images detection is proposed.By introducing a new definition of combining similarity of images(CSI), Edge Histogram Similarity Comparison(EHSC) algorithm is proposed by combining image edge and histogram features. Firstly, wavelet transformation is used to extract edge feature of images.Thus,wavelet feature similarity between realtime images and reference map is calculated.Then,the similarity between realtime images and reference map is calculated by the improved histogram intersection method.Finally,the images of satisfying threshold condition are selected. The simulation experiment result shows that the method has the advantage of strong robustness,low overhead of time and higher accuracy.It can improve the efficiency of detecting mudattaching wheel images efficiently.Key words:

Key words: wheel mud-attaching detection, edge detection;histogram intersection;EHSC algorithm;similarity comparison