Similarity Based Picking Images Containing Whole Wheel

Examining wheel images is needed for train's safe running. Based on computation of image similarity, a method is introduced to pick a few available images for examination from a series of train's images, in which the whole and clear wheels are contained. First, histogram is calculated and histogram intersection is adopted to evaluate the histogram similarity between the standard image and candidates, then a multi-resolution decomposition using Haar wavelet is applied, several statistical features of wheel edge based on wavelet coefficients are obtained and similarity comparison on the features is undertaken. These two kinds of similarity are combined to synthetically predict the similarity between two images. Finally, those images satisfying threshold are picked for examination. Experiments show useful wheel images can be acquired efficiently by this method.