Research On Automatic Detection System Of Defection Products Based On Shape Informations

Visual function is influenced significantly by aging. The aging-related visual Have Implemented a machine vision solution of automatic detection system of defection products of long ball studs based on shape informations.The solution first gets the centre of the circle on the bulb based on the long ball studs's shape information, then use the physical parameters of the workpiece to position the image coordinate of the place which needs to be recognized, so it efficiently lowers the recognition difficulty later on.The places with obvious characters that not to be influenced by where they placed, are designed homologous direct feature extraction algorithm to recognize whether processed;While the places without obvious characters or characters that may be changed, we use a machine learning algorithm that simulating object recognition mechanism of human visual cortex to automatic extact characters and use the SVM algorithm to recognize.It proves to be that the solution can fast and efficiently recognize whether the workpieces are acceptable with the running conditions of the system,and it almost reachs the discrimination of human eyes with a error rate of only about 0.5% . Main work in this paper includes:1. Design of general scheme of the system,including the hardware selection about the industrial camera,the camera shot,the light source,the background etc.2. After analysis and comparison and considering the speed of the detecting,we use a probabilistic Hough transform algorithm to detect the circle to obtain the center and the radius.3. Present a position algorithm to the places which need to be recognized based on the shape informations of the long ball studs.4. Design the direct feature extraction algorithms to recognize whether processed about the places(e.g. whorl,groove,bevel edge,etc) with obvious characters that not to be influenced by where they placed.5. Use a machine learning algorithm that simulating object recognition mechanism of human visual cortex to automatic extract characters to the places without obvious characters or characters may be changed, and then use the SVM algorithm to recognize.