Research Of Image Segmentation Based On Fuzzy Set Theory

Image segmentation is just to divide an image into different sub-images with different characters and extract some interested objects. It is the most essential and important content of research on low-lever computer vision, and is a key technique for image analysis, understanding and description because the quality of segmentation results affects the quality of succeeding analysis, recognition and explaining. Image segmentation is applied in a lot of fields such as computer vision, image coding, pattern recognition, medical image and so on.Images themselves are very uncertain and inaccurate. It is found that fuzzy theory is able to give a good description of such uncertainties and image segmentation is just the classification of image pixels. In recent years, some experts are making efforts to apply the fuzzy clustering method in image segmentation, and it is more effective than the traditional image processing method. However, there are still some problems with classical image segmentation based on Fuzzy theory.Based on the above reasons, the fuzzy entropy and fuzzy C-means (FCM) clustering algorithm which is the foundation of fuzzy theory and popular in image segmentation is studied, and new ideas are presented in view of some drawbacks of FCM algorithm and Fuzzy entropy of image segmentation. The main research results can be concluded as follows:First, a new fuzzy entropy method is proposed for the image of target and background are seriously overlapped and the single histogram modal. The new method introduces the cost function combining the characteristics of images, uses it to reconstruct the approximate ideal Images, and then use the new fuzzy entropy to segment the reconstructed image. Experiment results show that effect is good.Second, based on the traditional fuzzy C means clustering algorithm, this paper puts forward a new method combining the pixels'spatial information and fuzzy C means clustering algorithm. The new method can overcome situation of the non-ideal segment result because of the lack of important pixel space information, and in the algorithm an important parameter m is improved, with the algorithm operating, m decreases constantly, so algorithm can make a smooth convergence.Finally, the large amount of calculation of the image data brings inconvenience to the practical application, especially, the larger the image size is, the greater amount of calculation, so the calculation speed of fuzzy C means algorithm is restricted. To solve this problem, this paper introduces the fuzzy C-means algorithm combined with genetic algorithm, it can optimize the calculation speed of the fuzzy C-means algorithm.