The Study Of Image Segmentation Algorithm Based On Otsu Method

Image segmentation is one of the basic and important technique in computer vision.Image segmentation is the process and related methods to segment an image into different sub-images with different chareacters and derive some interested objects.It is a key step from image process to image analysis,and it plays an improtant role in image engineering.The quality of the segmentation will directly affect the performance of the vision system.So the study on the image segmentation is always one of the key points in the image segmentation technique study,many image segmentation algorithms are advanced,and it is widely used in computer vision,pattern recognition and medicine image processing.Threshold image segmentation method is in common use in the image segmentation.It distinguishs the image into objects and background by picking threshold,so the threshold picking is the key technique.The Otsu method is often used as one of the threshold image segmentation methods,based on histogram,choose threshold by analyse image gray level information.But this method is ineffective in getting better segmentation when facing complex image,such as image with low SNR or gray level discrepancy and tiny area(It's histogram show an obvious discrepancy in double-peak,even single-peak),the algorithm's effect decrease,even occur errors.This paper studies the genetic algorithm,based on Otsu method,focus on a new gary image segmentation method that combine the Otsu method and the genetic algorithm.The Otsu method not only consider the gray information of the image,but also the related information of domain space,to ensure the accuracy of image segmentation,and the genetic algorithm is used to increase the speed of operation.This paper put a test on the validity of this algorithm,and introduce the adapting method in programming to select the arithmetic operators,in order to increase the precision.It has practically done gary image segmentation work and the experimental result has been recorded.This method is a complementarity to the image threshold segmentation method,as the test result shows,this algorithm is feasible and credible,give an ideal image segmentation outcome,and more fast and steady than conventional method.It has great potential in the domain of image processing.