Segmentation for Plate Microscopic Image

With the rapid development of the Computer-To-Plate (CTP) technology, the detection and control of the dot area coverage on the plate become one of the key technologies to control quality during printing and copy processes. With regards to the characteristic of low contrast in plate image and fuzzy dot edge, the Fuzzy C-Means (FCM) clustering algorithm is proposed to segment the microscopic image on the plate in this paper. In order to obtain better result, the comparison among the FCM clustering algorithm, the weighted FCM clustering algorithm based on two-dimensional histograms, and the weighted FCM clustering algorithm based on two-dimensional histograms and adaptive smoothing factor m is carried out. Experimental results are given to demonstrate more accurate segmentation of the plate microscopic image with the help of specially designed pre-processing method on the weighted FCM clustering algorithm based on two-dimensional histograms and adaptive smoothing factor m.