A machine vision system was developed to inspect the quality of rice seeds. Five varieties of Jinyou402, Shanyou10, Zhongyou207, Jiayou and IIyou were evaluated. The images of both sides of rice seed with black backg...A machine vision system was developed to inspect the quality of rice seeds. Five varieties of Jinyou402, Shanyou10, Zhongyou207, Jiayou and IIyou were evaluated. The images of both sides of rice seed with black background and white background were acquired with the image processing system for identifying external features of rice seeds. Five image sets consisting of 600 original images each were obtained. Then a digital image processing algorithm based on Hough transform was developed to inspect the rice seeds with incompletely closed glumes. The algorithm was implemented with all image sets using a Matlab 6.5 procedure. The results showed that the algorithm achieved an average accuracy of 96% for normal seeds, 92% for seeds with fine fissure and 87% for seeds with incompletely closed glumes. The algorithm was proved to be applicable to different seed varieties and insensitive to the color of the background.展开更多
A motion control system for a parallel robot with image positioning was implemented in this paper. The system is composed of a machine vision device, a delta robot and a linear stage, and the concerned hardware, softw...A motion control system for a parallel robot with image positioning was implemented in this paper. The system is composed of a machine vision device, a delta robot and a linear stage, and the concerned hardware, software and working methods were developed completely and verified successfully. During the phase of machine vision, the image of object was captured by camera, and then the process of smoothing filter, threshold algorithm and edge detection, was applied so as to obtain the edges of image. Finally, DV-GHT （Displacement Vector Generalized Hough Transformation） algorithm was used to recognize the center of multiple and arbitrary 2-D shapes objects. After the center of objects was recognized, the objects were delivered to the workspace of a delta robot by a motorized stage. Through the coordinate transformation between the camera and the robot system, the information of center can be converted to control commands for every working motors. Following, the delta robot picks up objects to the specified position sequentially by the trajectory planning and tracking controls. The software of C＋＋/CLI is used to achieve the phase of motion controls and the program of DV-GHT is used to detect and conduct the positions for four different characteristics of the objects simultaneously so as to indicate the delta robot to classify the objects successfully.展开更多
基金Project supported by the National Natural Science Foundation ofChina (No. 60008001) and the Natural Science Foundation of Zhe-jiang Province (No. 300297), China
文摘A machine vision system was developed to inspect the quality of rice seeds. Five varieties of Jinyou402, Shanyou10, Zhongyou207, Jiayou and IIyou were evaluated. The images of both sides of rice seed with black background and white background were acquired with the image processing system for identifying external features of rice seeds. Five image sets consisting of 600 original images each were obtained. Then a digital image processing algorithm based on Hough transform was developed to inspect the rice seeds with incompletely closed glumes. The algorithm was implemented with all image sets using a Matlab 6.5 procedure. The results showed that the algorithm achieved an average accuracy of 96% for normal seeds, 92% for seeds with fine fissure and 87% for seeds with incompletely closed glumes. The algorithm was proved to be applicable to different seed varieties and insensitive to the color of the background.
文摘A motion control system for a parallel robot with image positioning was implemented in this paper. The system is composed of a machine vision device, a delta robot and a linear stage, and the concerned hardware, software and working methods were developed completely and verified successfully. During the phase of machine vision, the image of object was captured by camera, and then the process of smoothing filter, threshold algorithm and edge detection, was applied so as to obtain the edges of image. Finally, DV-GHT （Displacement Vector Generalized Hough Transformation） algorithm was used to recognize the center of multiple and arbitrary 2-D shapes objects. After the center of objects was recognized, the objects were delivered to the workspace of a delta robot by a motorized stage. Through the coordinate transformation between the camera and the robot system, the information of center can be converted to control commands for every working motors. Following, the delta robot picks up objects to the specified position sequentially by the trajectory planning and tracking controls. The software of C＋＋/CLI is used to achieve the phase of motion controls and the program of DV-GHT is used to detect and conduct the positions for four different characteristics of the objects simultaneously so as to indicate the delta robot to classify the objects successfully.
