Textile cloth surface flaw detection device based on YOLO neural network

Abstract

The invention discloses a textile cloth surface flaw detection device based on a YOLO neural network, which comprises a textile cloth surface flaw detection device and a cloth flaw detection system, and is characterized in that the textile cloth surface flaw detection device comprises a fixed bottom plate, rollers are arranged at the two ends of the fixed bottom plate, rotating shafts are connected to the interiors of the two sets of rollers through bearings, connecting plates are fixed to the two ends of each rotating shaft, the connecting plates are fixed to a fixing bottom plate, two sets of supporting rods are fixed to the two sides of the fixing bottom plate, an upper fixing plate is arranged above the fixing bottom plate, and the upper fixing plate is fixed to the supporting rods; two sets of fixed sliding rods are fixed to the bottom of the upper fixed plate, one sides of the two sets of fixed sliding rods are slidably connected with movable plates, cameras are fixed to the bottom faces of the movable plates, and one sides of the rollers are electrically connected with motors. The device has the advantages of being high in practicability and capable of automatically recognizing the flaws on the surface of the cloth.

Description

Technical field [0001] The present invention relates to a surface defect detection apparatus BACKGROUND textile cloth, textile cloth specifically based surface defect detection apparatus YOLO Neural Network. Background technique [0002] Currently in the textile and garment manufacturers primarily through a professional inspector cloth fabric inspection equipment standing in front of fabric defects found by the naked eye and then marked defects, with the continuous optimization of computer vision detection technology, intelligent test distribution system will greatly reduce the manual inspection labor intensity, improve the efficiency and accuracy of the production process quality control fabric, woven fabric and the conventional surface defect detection apparatus are limited by low contrast between the defects and the non-defect region, the textile industry can not meet the production accuracy and real requirements, therefore, a strong practical design and automatic identificati...

AI Technical Summary

Problems solved by technology

[0002] At present, in textile and garment production enterprises, professional cloth inspectors stand in front of the cloth inspection equipment to find the defects of the cloth surface with the naked eye and then mark the defects. With the continuous optimization of computer vision inspection technology, the intelligent cloth inspection system will greatly reduce manual inspection. labor intensity, improve the efficiency and accuracy of fabric quality monitoring in the production process, and the existing textile cloth surface defect detection devices are limited by the low contrast between defect and non-defect areas, which cannot meet the accuracy and real-time requirements of textile industry production. Therefore, it is necessary to design a textile fabric surface flaw detection device based on YOLO neural network that is practical and can automatically identify fabric surface flaws

Images