Shoe sole pattern image clustering method based on collaborative network structure

Abstract

The invention provides a shoe sole pattern image clustering method based on a collaborative network structure. The system comprises a shoe sample or suspect sole pattern learning network connected with category information based on characteristic layer difference loss and an on-site sole pattern unsupervised clustering network. Pre-training is carried out through data sets with different attributes, feature subspace provided by supervised learning of shoe pattern or suspect sole pattern mass data can be utilized to restrict clustering learning of on-site sole patterns or unmarked suspect pattern features, and therefore the clustering process is based on the evidence. Besides, a pre-training strategy of supervised and unsupervised network cooperative training is provided based on the sequence of the training models so that the cooperative effect between the networks can be more effectively reflected and the clustering precision of the sole pattern image can be enhanced.

Description

technical field [0001] The present invention relates to a clustering method, in particular to a shoe sole pattern image clustering method based on a collaborative network structure. Background technique [0002] There are currently three types of sole pattern data: [0003] The first category is the pattern data of the suspect’s shoe soles. These are images of the pattern of the suspect’s shoe soles obtained through special acquisition equipment. The images are of high quality and consistent with the patterns at the crime scene, but the categories are insufficient and the quantity cannot be guaranteed; [0004] The second type is shoe pattern data. These data are downloaded from the website for buying shoes and obtained through pre-processing and segmentation. The status is very different, and there are only similarities in visual effects; [0005] The third category is on-site pattern data. These data are based on the shoe print images extracted from real crime scenes bas...

AI Technical Summary

Problems solved by technology

[0011] According to the technical problems of inaccurate solution of clustering features and unsatisfactory clustering results proposed above, a clustering method of shoe sole pattern images based on collaborative network structure is provided

Images