Adaptive Approach of Patch Size Selection Using GA in Exemplar Based Image In-painting

A Conference on Wireless Communication and Android Apps "WiCAA–15" 1. INTRODUCTION The Image in-painting is a hot spot in computer graphics and an active area in research in image processing. Image in-painting is also known as image disocclusion or completion. Object removal from images is an image manipulation technique that has a long history. The purpose of removing objects varies from remove undesired object to improve the quality of the image, to airbrushing out political enemies from portraits of important events. Modern photographical manipulations, such as red eye removal from pictures, also utilized this technique. The process of removing objects from images starts with mask out the undesired object, making the area where the object previously occupies a gap. Then the gap will be filled using graphical techniques such as in-painting. The main goal of this process is to fill the missing region/restoring lost part of an image based on the background information. And this process reconstruct image in such a way so that the change cannot be noticeable by an observer. Image in-painting technique is used in so many fields like preservation of heritage films and television and for special effects production. It is used to restore old/damaged photographs, object removal from an image without affecting the image, image coding [3], [4] and transmission [5] (recovery of the missing blocks) etc. Following are the Mostly used in-painting methods:-1. Geometry-based method 2. Exemplar-based method We can also call Geometry based methods as structure in-painting methods. In this method missing region is filled by diffusing the image information from the known region into the missing region at the pixel level. This type of algorithm is basically based on PDE (partial differential equation). Geometry-based in-painting methods shows good result in propagating smooth level line or gradients or filling the non-textured target region. This method is generally used when the inpainted region is small. The drawback of this method is, it introduces blurring artifacts in textured or when filling large missing region. The second category is exemplar-base in-painting algorithm. It provide an efficient approach for reconstructing large target regions. Basically it consists of two main steps: The first step is of priority assignment and the second step consists of the selection of the best matching exemplar and update all the priorities. Exemplar based in-painting iteratively synthesizes the target region, by the most similar patch in source region. They provide good results in recovering …