IJARCCE - Computer and Communication Engineering

Abstract

As we know that image thinning plays an important role in image processing, It is also equally important to propose an efficient image thinning algorithm with an objective, to minimize the amount of information to be processed by preserving the important information required to preserve the topological and geometrical properties of the thinned image, thereby enhancing the later processing procedure. This can be achieved by an efficient image independent thinning algorithm. This algorithm process the image in two-passes, in first pass of this algorithm, the entire image is thinned to two pixels thick and in second pass; the two pixel width image is further thinned to one pixel thick without any discontinuities in the resultant image. I. INTRODUCTION Thinning algorithms are developed to address wide variety of problems in thinning. These thinning algorithms are classified based on the approaches used for thinning (Lam, Lee & Suen, 1992). Based on these approaches thinning algorithms are classified as iterative and non-iterative thinning algorithms. With Non-iterative thinning algorithms skeleton can be obtained in a single pass (With the methodologies like distance transforms and run-length coding). But this algorithm, does not consider the surrounding pixels while making decisions for deletion or to retain. Whereas Iterative thinning algorithms considers the surrounding pixels while making decision for deletion or to retain pixels. The iterative thinning algorithms are further categorized as sequential (boundary pixels are processed one by one, layer by layer) and parallel (all the boundary pixels are processed simultaneously layer by layer). Sequential algorithms consume less amounts of memory. In contrast, parallel algorithms require more memory compared to sequential algorithms but are much faster in processing. Parallel algorithms process all the border pixels at once.