Prefabricated bay window defect detection system based on improved Faster R-CNN

Abstract

The invention discloses a prefabricated bay window defect detection system based on an improved Faster RCNN, and the system comprises an image collection device and a background PC, the image collection device comprises a screw rod, the left and right ends of the surface of the screw rod are in threaded connection with sliding nuts, and the left and right sides of the sliding nuts are fixedly connected with extension rods. The surface of the extension rod is sleeved with a first fixing sleeve, a second fixing sleeve and a third fixing sleeve in the direction from the position close to the leadscrew to the position away from the lead screw, and springs are fixedly connected between the first fixing sleeve and the second fixing sleeve and between the second fixing sleeve and the third fixing sleeve and located on the surface of the extension rod. The invention relates to the technical field. According to the prefabricated bay window defect detection system based on the improved Faster RCNN, through the arrangement of the screw rod, the extension rod, the first fixing sleeve, the second fixing sleeve, the third fixing sleeve, the springs and the industrial camera, image acquisition can be conducted on prefabricated bay windows of different specifications, and the position of the industrial camera in each collection group can be adjusted in a self-adaptive mode.

Description

technical field [0001] The invention relates to the technical field, in particular to a prefabricated bay window defect detection system based on improved Faster R-CNN. Background technique [0002] With the development of computer technology and image processing technology, machine vision inspection technology has been widely used in industrial defect detection. For example: Celik et al. combined the image algorithm based on double-threshold binarization, wavelet transform and morphological operation with the feed-forward neural network to realize defect detection; Afshar et al. used statistical methods to detect the edge of the defect, and then adopted multi-strategy support The vector machine is used as a classifier to identify defects; Guo Hui et al. proposed a defect detection based on gray-level co-occurrence matrix and hierarchical clustering algorithm. [0003] In recent years, deep learning technology, as an important branch of machine learning, has become increasi...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a prefabricated bay window defect detection system based on the improved Faster R-CNN, which solves the problems of heavy workload, low detection efficiency and high false detection rate of the traditional manual visual detection method. Machine vision detection methods usually use industrial cameras to collect images. This type of detection model is relatively simple, requiring manual feature engineering or manual selection of some key parameters, which is greatly affected by human subjectivity, resulting in low generalization ability of the detection method and unable to cope with There are many types of defects in prefabricated bay windows, complex production environment and other uncontrollable factors

Images