Implementation method and system for user dressing detection, medium and terminal

Abstract

The invention provides an implementation method and system for user dressing detection, a medium and a terminal. The method comprises the following steps: acquiring a work clothes image set and a to-be-detected user image; performing feature extraction on each work clothes image in the work clothes image set to obtain a first feature vector corresponding to each work clothes image; based on the to-be-detected user image, obtaining a second feature vector corresponding to the to-be-detected user dressing on the to-be-detected user image; calculating the similarity between the second feature vector and each first feature vector so as to detect the dressing of the to-be-detected user according to the similarity; whether the user wears the work clothes or not is judged by calculating the similarity between the dressing of the to-be-detected user and the work clothes image, so that the situation that an algorithm network needs to be retrained along with updating or expansion of the work clothes can be effectively avoided, and the method is suitable for various work clothes styles and has industry application adaptability and batch popularization capacity; and a unified algorithm networkcan be utilized to adapt to various application scenes.

Description

technical field [0001] The invention belongs to the technical field of user attire detection, and in particular relates to an implementation method, system, medium and terminal for user attire detection. Background technique [0002] With the rapid development of artificial intelligence and computer vision technology, the scope of technology applications has gradually spread from the field of security monitoring to civilian, shopping malls, events, stores and other scenarios; among them, in store application scenarios, business executives need to conduct regular monitoring of stores. Shop patrolling, among which the attire of the store staff is one of the key items to be checked during the shop patrolling. [0003] At present, the existing user clothing detection methods mainly rely on the classification of images; the specific method is to first detect the human body through the pedestrian detector and send it to the classification network for recognition. Usually, the main...

AI Technical Summary

Problems solved by technology

[0005] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a method, system, medium and terminal for user attire detection, which is used to solve the problem of frequent training and classification of user attire detection in the prior art. Model, troublesome operation, time-consuming and labor-intensive, and poor adaptability of classification models

Images