A Novel Segmentation of Scanned Compound Images using Fuzzy Logic

The paper proposes a new segmentation method for image classification with understanding. Analysis of the scanned compound image and medical image segmentation is greatly interrelated with the removal of accurate text/graphics, picture and removal of the anatomic structures of them, and the most important assignment is how to split the regions of interests from the background layer and foreground layer successfully. This research paper proposes a fuzzy rule based bit-plane method to repeatedly divide the background or mask of images and to place the region of interest of compound document images and also suitable for medical images. This segmentation algorithm contains the following procedure such as, classification, fuzzy rule firing, and fuzzy inference. The proposed innovative metrics are used to calculate the exact accuracy of the segmentation scheme. Since the investigation, it is experimental that the proposed metrics are most appropriate for the evaluation of segmentation accuracy. The experimental results achieved from this work, prove that the proposed system performs segmentation effectively and successfully for the different module of compound images and different module of medical images.