Garment image retrieval system and method through indirect relevance feedback without checking source

Abstract

The present invention provides a garment image retrieval system and method through indirect relevance feedback without a checking source. The method comprises: obtaining a large number of garment pictures and clustering the garment pictures according to the types and colors; for each picture collected by a garment picture collection module, according to multiple features selected in the type, extracting a vector with a fixed length by using a deep neural network, and according to each feature, calculating the similarity between the pictures; and according to the similarity between pictures obtained in the garment picture feature extraction and similarity calculation step, through the Bayesian feedback structure algorithm, after the user clicks a picture most similar to a target picture ateach time, adjusting the weight of the selected features, then returning the weight to the user recommended garment picture, and finding out the target picture of the user through iteration. The system and method provided by the present invention solve the problem that a user cannot find out a target garment picture under the condition that there is no checking source of the garment pictures and only basic types and colors can be given out.

Description

technical field [0001] The invention relates to the fields of computer vision and data mining, in particular to a clothing image retrieval system and method through indirect correlation feedback without source checking. Background technique [0002] With the development of network technology, online payment and logistics distribution and people's more demand for the network, online shopping malls, especially the online shopping platforms provided by enterprises for consumers (B2C), have developed rapidly in recent years. This shopping mode saves time and space for merchants and users, greatly improves transaction efficiency, and also has many advantages such as various types of goods, no shopping time limit, and low shopping cost. [0003] Buying clothes online is a major force in online shopping. Many major online shopping platforms use clothes as a major source of profit, and there are even vertical shopping sites that focus on a certain type of clothes. At the same time,...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the defects in the prior art, the object of the present invention is to provide a clothing image retrieval method and method without searching source through indirect correlation feedback, so as to solve the problem of searching only through text or pictures and without searching in the existing method. The problem of weight change is not considered during source retrieval. Through multiple iterations and feedback to model the user's target picture and variable weight features, the target picture in the user's mind can be searched without searching the source

Images