Fabric warp and weft density detection system and method based on u-net network

Abstract

The invention discloses a fabric warp and weft density detection system and method based on a u-net network, and aims to solve the problem of complex texture and color fabric warp and weft density detection, and can adopt u-for fabric with complex texture and color. According to the method for carrying out image segmentation by the net network, an average value is automatically counted through animage distance transformation algorithm, and the method is an automatic measuring instrument which is reliable, high in accuracy and small in error and can be checked by human eyes simultaneously. Compared with the prior art, the method has the positive effects that firstly, the accuracy of warp and weft density statistics of the fabric is improved, and the method can be applied to the fabric withcomplex textures and colors; secondly, the warp and weft density change condition can be monitored in real time in the fabric production process; And thirdly, the mode that yarns need to be counted manually in a traditional detection method is solved, and the labor cost is greatly reduced.

Description

technical field [0001] The present invention relates to the field of image processing and deep learning, in particular to a system and method based on a deep learning network that can be applied to fabrics such as denim and has the function of automatically counting warp and weft threads. Background technique [0002] Fabric warp and weft density detection usually uses fabric decomposition method, fabric analysis mirror method and mobile fabric density mirror method. The above methods all need to be completed by manually counting the number of yarns. These methods will cause workers to produce missed and false detections during the detection process, which seriously reduces the production efficiency of the textile process. In order to overcome the shortcomings of low efficiency, high cost and low degree of automation in the production process of the textile industry, machine vision technology is introduced into the warp and weft density detection process. However, the resea...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the prior art, the present invention provides a fabric warp and weft density detection system and method based on the u-net network, aiming to solve the problem of complex texture and color fabric warp and weft density detection, for complex texture and color fabrics can be Using the u-net network for image segmentation, and automatically counting the average value through the image distance transformation algorithm, it is a reliable, high-precision, small error, automatic measuring instrument that can be checked by human eyes at the same time

Images