Surface Defects Inspection System Based on Machine Vision

2010 ◽  
Author(s):  
Xiaoyan Deng ◽  
Xiaojuan Ye ◽  
Jinsheng Fang ◽  
Chun Lin ◽  
Lei Wang
Keyword(s):  
Machine Vision ◽  
Surface Defects ◽  
Inspection System ◽  
Defects Inspection

Surface Defect Inspection and Classification of Segment Magnet by Using Machine Vision Technique

2011 ◽  
Vol 339 ◽  
pp. 32-35 ◽  
Author(s):  
Hong Hai Jiang ◽  
Guo Fu Yin
Keyword(s):  
Image Processing ◽  
Machine Vision ◽  
Surface Defects ◽  
Processing System ◽  
Support Vector ◽  
Inspection System ◽  
Low Contrast ◽  
Constituent Material ◽  
Canny Edge

In this paper, we propose a machine vision based approach for detecting and classifying irregular low-contrast surface defects of segment magnet. The constituent material of it is ferrite which varies from silver gray to black in color .For this reason, the defects embedded in a low-contrast surface show no big different from its surrounding region, and even worse, all the surfaces and chamfers of segment magnet must be inspected. Our system is able to analyze all surfaces under inspection, to discover and classify its defects by means of image processing algorithms and support vector machine (SVM). A working prototype of the system has been built and tested to validate the proposed approach and to reproduce the difficult issues of the inspection system. The developed prototype includes three subsystems: an array of several CCD area cameras (Fig.1); a controllable roller LED light source(Fig.1); and a PC-based image processing system. The detection of the defects is performed by means of Canny edge detection, morphology and other feature extraction operations. The image processing and classification results demonstrate that the proposed method can identify surface defects effectively.

Machine Vision Inspection of In Vitro Diagnostic Kits

2013 ◽  
Vol 753-755 ◽  
pp. 2164-2169
Author(s):  
Jiang Ping Mei ◽  
Yi Liu
Keyword(s):  
Machine Vision ◽  
Surface Defects ◽  
Detection Threshold ◽  
Inspection System ◽  
Strip Surface ◽  
Diagnostic Kits ◽  
Vision Inspection ◽  
In Vitro Diagnostic ◽  
Machine Vision Inspection

A machine vision-based inspection system was proposed to inspect the defects of in-vitro diagnostic kits in the production line. The proposed system consisted of two sub-systems, which inspect the strip surface defects and strip assembly defects respectively. The procedure to inspect five types of major defects was determined by the application of image processing and analysis techniques such as image enhancement, edge detection, threshold segmentation, and morphology. The proposed system was implemented using 300 defect samples. Experimental results show the proposed system is effective and efficient.

An Inspection System for Sorting Fruit with Machine Vision

1996 ◽  
Author(s):  
Michael Delwiche ◽  
Yael Edan ◽  
Yoav Sarig
Keyword(s):  
Machine Vision ◽  
Fruits And Vegetables ◽  
Significant Contribution ◽  
Surface Defects ◽  
Error Rates ◽  
Agricultural Products ◽  
Commercial Application ◽  
Inspection System ◽  
Structured Illumination ◽  
Quality Classification

Concepts for real-time grading of fruits and vegetables were developed, including multi-spectral imaging with structured illumination to detect and distinguish surface defects from concavities. Based on these concepts, a single-lane conveyor and inspection system were designed and evaluated. Image processing algorithms were developed to inspect and grade large quasi-spherical fruits (peaches and apples) and smaller dried fruits (dates). Adjusting defect pixel thresholds to achieve a 25% error rate on good apples, classification errors for bruise, crack, and cut classes were 51%, 42%, and 46%, respectively. Comparable results for bruise, scar, and cut peach clases were 48%, 22%, and 58%, respectively. Acquiring more than two images of each fruit and using more than six lines of structured illumination per fruit would reduce sorting errors. Doing so, potential sorting error rates for bruise, crack, and cut apple classes were estimated to be 38%, 38%, and 33%, respectively. Similarly, potential error rates for the bruitse, scar, and cut peach classes were 9%, 3%, and 30%, respectively. Date size classification results were good: 68% within one size class and 98% within two size classes. Date quality classification results were not adequate due to the problem of blistering. Improved features were discussed. The most significant contribution of this research was the on-going collaboration with producers and equipment manufacturers, and the resulting transfer of research ideas to expedite the commercial application of machine vision for postharvest inspection and grading of agricultural products.

Research of Inspection System Based on Machine Vision for Steel Rod Surface Defects

2011 ◽  
Vol 418-420 ◽  
pp. 1878-1881
Author(s):  
Jian Chuan Zhang ◽  
Wu Bin Li ◽  
Chang Hou Lu
Keyword(s):  
Machine Vision ◽  
Gradient Method ◽  
Surface Defects ◽  
Inspection System ◽  
Time Saving ◽  
Open Operation ◽  
Surface Image ◽  
Local Gradient

A new algorithm based on local gradient is proposed to inspect steel rod surface defects. The local gradient method can weaken the effect of noise in steel rod surface image. Then the open operation of morphology theory is employed to remove the retaining noise. Experiments show that this algorithm is effective to inspect steel rod surface defects and is time-saving.

Sign in / Sign up

Export Citation Format

Share Document