Automatic Work Reporting System for Digital Printing Factory Based on Machine Vision
Aimed at the challenges of exiting manual reporting management in textile production,a machine vision-based automat-ic reporting system was developed for a digital textile printing factory.This system intelligently matches the patterns of the fabrics currently in production with the design patterns in the order database,enabling rapid and accurate management of production orders.Firstly,the system client uses an industrial camera to capture the real-time images of printed fabrics on the production line,and the images is filtered and normalized for the pre-processing.Then,these images are transmitted to the server system via HTTP protocol,and based on the neural network model of Vision Transformer,the feature extraction and multi-layer feature fusion are carried out.And then,the images are matched with the pattern design in the order database to identify the orders needed to be reported.Finally,it displays and confirms that the matching results are managed in the database and returned to the client for,the reporting results.Experimental results demonstrate that this automatic reporting system achieves a TOP-3 match rate of 90.4％,meeting the needs of factory fabric production.
digital printing factoryautomatic reportingmachine visionvision transformerpattern matching
万方数据
维普
