Object Removal by Hierarchical Super-Resolution Based Inpainting T. Vikram Computers and Communications Jawaharlal Nehru Technological University Kakinada, India Dr. A. M. Prasad Professor, ECE Dept. Jawaharlal Nehru Technological University Kakinada, India Abstract— This paper introduces novel frame work for Object Removal by means of inpainting. In this method, first the object in the required target area is removed by inpainting. The output thus obtained is given as input to a super-resolution algorithm to recover details on missing areas. Exemplar-based inpainting is used to remove objects that are not required. It is desirable to use a Super-resolution algorithm since inpainting produces a low resolution (LR) image. In this paper a regularization method based on morphologic operations is used for SR image reconstruction. It is always desirable to generate a high resolution (HR) image as it shows more intricate details. Index Terms—Object Removal, Inpainting, Exemplar, Super-resolution I. INTRODUCTION Inpainting is the process of reconstructing lost or deteriorated parts of an image. The process of inpainting utilizes the background information to fill the missing or target region of image [1]. Initially inpainting is used for scratch removal. The other applications include object removal, text removal and other automatic modification of images. The idea of object removal is to remove objects from digital photographs and fill the hole with the information extracted from the surrounding area. Existing methods of inpainting can be classified into two main categories namely Diffusion and Exemplar based approaches [6].The diffusion based approach tends to introduce some blur when the target region or area of removal to be filled is large .Exemplar based approach uses the background information i.e. these methods sample and copy best matching texture patches from the known image neighborhood [2]-[5]. In this method diffusion based inpainting and texture synthesis are combined. Exemplar based techniques effectively generate new texture by sampling and copying color values from the source [2]. The technique presented here combines the strength of both approaches into a single efficient algorithm. Exemplar based inpainting is capable of propagating both structure and texture information. Although tremendous progress has been made in the past years on inpainting, difficulties exist when the hole or the area of object to be removed is very large and the computational time required in general is high. These two problems are addressed by considering a two-step or hierarchical approach [6] in which inpainting is performed on a input image and a super resolution algorithm is used to construct a high resolution (HR) image. Super-resolution (SR) imaging aims to overcome or compensate the limitation or shortcomings of the image acquisition device/system and/or possibly ill-posed acquisition conditions to produce a higher-resolution image based on a set of images that were acquired from the same scene. With rapid progress in image processing for visual communications and scene understanding, there is a strong demand for providing the viewer with high-resolution imaging not only for providing better visualization (fidelity issue) but also for extracting additional information details (recognition issue). A HR image makes it easy to achieve a better classification of regions in a multi-spectral remote sensing image or to assist radiologist for making diagnosis based on a medical imagery. Super-resolution refers to creating an enhanced high resolution (HR) image from one or more low resolution (LR) images [7]. The approach used in this paper is based on regularization frame work. Another class of super resolution methods generates an HR image from a single LR image or a frame [7]. These methods are referred to as Example-based SR or image hallucination. In example based SR, correspondences between HR and LR patches are learned [6] from a group of HR-LR patches known as Dictionary and then applied to a low resolution image to recover its higher resolution version. In this paper we use a non-linear regularization method based on multiscale morphology for edge preserving SR reconstruction [8]. In this method we consider Super Resolution image reconstruction as a deblurring problem and solve the inverse problem using Bregman iterations. The HR image is estimated based on some prior knowledge about the image in the form of regularization. A new regularization method based on multiscale morphological filters is proposed. Morphological operators are used for extracting structures from images. Image segmentation, image denoising and image fusion can be done successfully using morphological operations. Better results can be obtained by combining bregman iteration [9] and morphologic regularization. The rest of the paper is organized as follows. Section II gives the overview of algorithm for the proposed method. In Section III, algorithm for Exemplar-Based Inpainting is explained in detail. This section presents the different steps of International Journal of Engineering Research & Technology (IJERT) ISSN: 2278-0181 www.ijert.org IJERTV3IS090040 (This work is licensed under a Creative Commons Attribution 4.0 International License.) Vol. 3 Issue 9, September- 2014 16