Convolutional neural network-based physical characteristic recognition and classification-based clothing recommendation system

Abstract

The invention relates to a convolutional neural network-based physical characteristic recognition and classification-based clothing recommendation system. The system comprises an automatic customer information acquisition module, a clothing style recommendation module and a clothing information management module, wherein the automatic customer information acquisition module is used for obtaining photos of customers through a man-machine interaction manner, extracting physical features of the customers in the extracted photos by adoption of a CNN-SVM multi-classifier algorithm-based image recognition technology, and taking the physical features as input information of the clothing style recommendation module; the clothing style recommendation module is used for carrying out personalized clothing style recommendation by adoption of an expert system technology according to the physical features of the customers, and generating clothing recommendation lists; and the clothing information management module is used for completing order payment management on the basis of the generated clothing recommendation lists. According to the system, clothing recommendation can be completed accordingto the physical features of the customers.

Description

technical field [0001] The invention relates to the technical field of clothing recommendation, in particular to a clothing recommendation system based on convolutional neural network recognition and classification of body features. Background technique [0002] With the rapid development of the economy and the rise of Internet technology, online consumption is more and more sought after by the majority of consumer groups, breaking the original single offline retail mode in the clothing field, and online shopping has become a trend of the times. The most basic consideration when purchasing clothing is whether the clothing matches the physical characteristics of the customer, including choosing the right style of clothing according to one's body shape, choosing the right color of clothing according to one's skin color, etc. It should not be a problem for non-clothing matching experts easy thing. In order to increase the purchasing rate of customers, strengthen their purchasi...

AI Technical Summary

Problems solved by technology

However, these recommendation systems have data sparsity, cold start problems, and scalability problems. When a new customer or item is just added to the system, there is a lack of corresponding annotation information and customer rating records, and the evaluation matrix will be sparse, and it is impossible to accurately calculate the customer (item). ), which affects the recommendation accuracy

Secondly, some recommendation systems use human-computer interaction to obtain customer physical characteristics information. Since customers themselves are not clear about the type of their own external characteristics, the physical characteristics obtained are artificially subjective and inaccurate.

Furthermore, due to the manual input of feature information by customers, there are problems such as unclear semantic description and inconvenient operation, which cannot achieve the effect of convenient operation and fast and automatic acquisition of feature data

Since most clothing recommendation systems recommend clothing based on customer preferences, and customers have uneven knowledge of clothing expertise, the selected clothing is not professional and may not be suitable for customers from the perspective of clothing expertise. If it is only based on customer preferences and Score recommended clothing, which is subjective and cannot provide customers with suitable clothing recommendations

Images