Generalized Fuzzy Enhancement Based Recognizing Method for Planar Objects

On the basis of the generalized image enhancement algorithm using fuzzy sets and improved labeling method, a new recognizing method for planar objects is proposed. Firstly, a generalized iterative fuzzy enhancement algorithm is proposed which consists of a three-stage procedure, i.e., image filtering, fuzzy enhancement and gray-level transformation. A canonical form of membership function in the stage of fuzzy enhancement is proposed which remains the advantages of the original fuzzy enhancement and the gray level transformation while transforming the membership function of the gray scale to [0, 1], and therefore is suitable for handling the enhancement problems of the images that have less gray levels and low contrast. Secondly, a new objective image quality assessment criterion is suggested according to the statistical features of the gray-level histogram of images to control the iterative procedure of the proposed image enhancement algorithm. Thirdly, an improved labeling method for image segmentation is given. Using this novel labeling method in image segmentation, it is not necessary to determine an equivalence table that needs to be listed in the usual sequential component algorithm. Computer simulation results for a degraded gray image show that this proposed recognizing method is efficient.