Multi-shape hanger identification method for clothes production system

Abstract

The invention discloses a multi-shape clothes hanger identification method for clothes production system, the method comprising the following steps: using a camera to collect a clothes hanger image, and carrying out preprocessing and edge extraction for the collected clothes hanger image so as to obtain a target clothes hanger; complementing edge information of the target clothes hanger through aclosed filter; adopting a K-means method for clustering to segment the target clothes hanger; respectively extracting an edge image of the target clothes hanger and an image after K-means clustering;carrying out outer contour extraction on the edge image of the target clothes hanger by utilizing an acquisition boundary tracking method; taking the outer contour of the clothes hanger as a filling boundary, and filling the shapes of clothes hangers in various shapes by using a flooding filling method. The extracted clothes hangers in different shapes are stored into a database, and matching is carried out according to the Euclidean distance to realize autonomous identification of the clothes hangers in different shapes. According to the invention, the problem of low efficiency of manual identification in the conveying process of clothes hangers with different shapes under the complex background of an existing clothes production system is solved.

Description

technical field [0001] The invention belongs to the technical field of clothing hanger detection and machine vision, and in particular relates to a method for recognizing multi-shaped hangers in a clothing production system. Background technique [0002] With the strict requirements of the garment processing industry on production efficiency, hanger recognition in a complex background is one of the important processes in the garment assembly line production. Especially in the process of moving clothes hangers of different shapes, relying on manual detection and classification will seriously affect the processing efficiency. Therefore, the realization of automatic recognition research on hangers of different shapes can improve the efficiency of garment processing line production, and of course indirectly promote the development of automation. [0003] How to improve the identification and classification of different types of hangers in the complex production workshop is one ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a multi-shape hanger recognition method in a garment production system, which solves the problem of low efficiency caused by manual identification in the transmission process of different shapes of hangers under the complex background of the existing garment production system

Images