A Surface Defect Detection Method Based on Fusion of Gray Level and Depth Information

Abstract

The invention relates to an on-line detecting method for surface defects of an object and a device for realizing the method. The accuracy for the detection and the distinguishing of the defects is improved through the fusion of grey and depth information, and the method and the device can be applied to the detection of the object with a complicated shape and a complicated surface. A grey image and a depth image of the surface of the object are collected by utilizing the combination of a single colored area array CCD (charge-coupled device) camera and a plurality of light sources with different colors, wherein obtaining of the depth information is achieved through a surface structured light way. The division and the defect edge extraction of the images are carried out through the pixel level fusion of the depth image and the grey image, so that the area where the defects are positioned can be detected more accurately. According to the detected area with the defects, the grey characteristics, the texture characteristics and the two-dimensional geometrical characteristics of the defects are extracted from the grey image; the three-dimensional geometrical characteristics of the defects are extracted from the depth image; further, the fusion of characteristic levels is carried out; and a fused characteristic quantity is used as the input of a classifier to classify the defects, thereby achieving the distinguishing of the defects.

Description

technical field [0001] The invention relates to an online detection method for object surface defects and a device for realizing the method, especially for product surface detection with complex shapes or surface conditions, which can improve the accuracy of defect detection. Background technique [0002] The automatic detection technology of surface defects began in the 1970s. By the end of the 20th century, developed countries such as Germany, the United States, and Japan had developed machine vision online surface inspection systems with practical value. According to the types of data processed, machine vision inspection technology can be divided into detection based on binary images, grayscale images, color images and depth images. The current surface detection system generally uses grayscale image detection methods. The grayscale image detection method collects the grayscale image of the surface of the object through the camera, processes the grayscale image according t...

AI Technical Summary

Problems solved by technology

[0003] (1) The grayscale image detection method is suitable for object surface detection with a single background. For a surface with a complex background, it is difficult to judge the area where the defect is located from the background through the grayscale information, so a large number of missed detections and false detections will occur, affecting Reliability of test results

[0004] (2) The grayscale image detection method is suitable for the surface detection of planar objects. For objects with regular or irregular surfaces, the grayscale image detection method will cause shadows or even occlusions, which will affect the detection effect and cause missed detection.

[0007] (1) Defect detection by depth image is only suitable for defects with depth changes. For some defects without depth, such as spot defects, it cannot be detected by depth image

[0008] (2) Some interfering substances on the surface of the object will also cause changes in the depth of the surface. Using the depth image detection method will identify these interfering objects as defects, resulting in misidentification

[0009] (3) The current depth image acquisition method cannot achieve high resolution, therefore, it is difficult to detect some small defects, such as cracks, imprints, etc., through depth images

[0011] Traditional information fusion often refers to the information fusion of multiple sensors. If grayscale information and depth information are obtained through separate cameras, not only the number of cameras needs to be increased, but also the images collected by different cameras need to be registered, which increases the system cost. complexity of

Images