Investigations of color image segmentation based on connectivity measure, shape priority and normalized fuzzy graph cut.

A vital ingredient of image analysis and vision-based systems is color image segmentation studies. Because color images contain more information than gray images, they are more fascinating to segment. Finding the features and associated information of a certain object becomes a difficult operation as a result of the underlying data for color images. Segmentation is highly challenging since color images have a diversity of color image and intensities. In this study, we employ shape priority of color image and connectivity measure as just a thresholding theme to distinguish an object from the surrounding. To introduce a normalized fuzzy graph cut measure based on the common S membership function in order to enhance the segmentation of color images. The execution of the suggested technique, also known as the S-fuzzy normalized graph cut (S-FNGC) approach. The structural imperfections in color images have been handled using the S-fuzzy normalized graph cut. In this algorithm, a system of S fuzzy sets is used to provide information about the specific feature of participation of a particular object in the boundary of the image. In the color image segmentation, the trouble of wrongly segmentation and segmentation with low accuracy can identify with the aid of using this approach. This proposed set of rules is as compared with the mask threshold, Gabor filter, some adaptive techniques like Genetic algorithm (GA), and K-Means clustering algorithm. Moreover, we take a look at that during maximum cases, our set of rules offers the lowest error rate and misclassification error values that enhance the segmentation manner of color images.