Fine-grained convolutional neural network-based clothes recommendation method

Abstract

A fine-grained convolutional neural network-based clothes recommendation method. First clothes pictures of various types and pictures that do not contain clothes are collected from an e-commerce website, and pictures of the two categories are labeled. Then a convolutional neural network is initialized, the labeled pictures are used to train the convolutional neural network. A recommendation process first uses a segmentation-based target area selection method to select a candidate shape area that is possible to contain clothes in a picture input by a user, and searches for the closest picture in a training picture database through a specific distance function and indexes the corresponding clothes type labeling. Depth characteristics of all clothes areas are extracted, linking and recommendation grading are performed, and finally a recommendation result is returned to the user. The extracted depth characteristics have very good invariance for rotation, translation and scale changes, and in addition, the recommendation method based on the segmentation-based target area and the adjacent picture improves recommendation accuracy to some extent.

Description

technical field [0001] The invention belongs to the field of target detection and recommendation, and relates to a method for detecting and recommending clothes from Internet e-commerce pictures. Background technique [0002] At present, with the rapid development of Internet e-commerce, such as Taobao, JD.com, and Amazon, people often face the problem of too many goods and no choice when choosing clothes online. How to improve the existing e-commerce recommendation method and effectively filter the products through the user's purchasing habits, so as to ensure that the clothes that are more in line with the user's purchasing habits and dressing and matching habits can be recommended. It has become a problem that e-commerce giants spend a lot of money and manpower at this stage. [0003] Affected by scale transformation, clothing models, different scenes, occlusion, complex background interference, etc., it is a challenging task to accurately identify and recommend clothes ...

AI Technical Summary

Problems solved by technology

On the other hand, traditional clothing detection methods usually use multi-scale sliding windows to traverse the image to find clothing targets. This method increases the number of windows that need to be judged, and the real-time performance is poor.

Images