PCB Infrared Image Segmentation Based On Active Contour

Printed circuit board infrared image is characterized by much noise and chipheating area crossing, the existing image segmentation algorithms is largely forvisible image or medical image, which are difficult for infrared image segmentationeffectively, in order to be suit to the segmentation and extraction of circuit boardinfrared image, the traditional image segmentation must be optimized and improved.Firstly, this paper introduces traditional Snake Model and finds out the contourproblems in traditional modal through analysis of the simulation result. Next, severalpopular improved methods,such as Balloon Fore Model, GVF Model and CV Model,are studied and improved for the characteristics of circuit board infrared image. Thesimulation results show that the defects of traditional Snake Model has been improvedobviously, but there are initial contour relying on artificial selection andmultiple-objective extraction problems in the improved Model.Combining Region Grow Algorithm and GVF-Snake Model, this paper presentsa multi-objective and self-adjective extraction algorithm for chip area which canextract multiple chip area automatically without artificial participation. This algorithmtakes advantage of heating characteristic of PCB infrared image and selects the seedpoint for regional growth as initial contour curve self-adaptively. Then GVF-SnakeModel is used to make initial contour converge to chip core heating area. Thesimulation results show that the selection of initial contour can accelerate convergespeed of contour curves. The present model can extract multiple chip heating areaeffectively with high precision and fast speed, which is worthy of engineeringapplication. Furthermore, this present algorithm is an accelerated parallel algorithm,whose operating speed can be further optimized in future research.