Survey Report on Various Image Inpainting Methods

Inpainting is derived from art restoration ,also called re-touching. Image Inpainting refers to the application of sophisticated algorithms to replace lost or corrupted parts of the image data. The main aim of inpainting is to fill scratches in the image or photos as well as to remove larger objects from them. The main objective of inpainting is to reconstruct the missing region in such a way that the observer does not comes to know that the image has been manipulated. Application of image inpainting include interpolation, photo restoration, zooming and super resolution, etc. In this paper several image inpainting techniques are explained with its pros and cons.

International Journal of Engineering Research and, 2020

Various factors affect the image that causes image deterioration. The art of restoration of deteriorated parts of image is known as image inpainting. The image inpainting is mainly categorized in 2 sections: Diffusion based and Exemplarbased image inpainting. This paper contains the overview of various techniques of image inpainting its advantages and limitations. Based on the Existing techniques, a new technique is proposed for image inpainting to overcome the drawbacks of existing system.

Image Inpainting is the art of filling in missing data in an image. The purpose of inpainting is to reconstruct missing regions in a visually plausible manner so that it seems reasonable to the human eye. There have been several approaches proposed for the same. The objective of this paper is to review three such methods – Texture synthesis, Convolution and Exemplar based Algorithm. Texture synthesis can be used to fill in holes in images, create large non-repetitive background images and expand small pictures. Convolution based image inpainting algorithms are very rapid, however in many cases; they don't provide adequate results in sharp details such as edges. Exemplar-based methods provide impressive results in recovering textures and repetitive structures. However, their ability to recreate the geometry without any example is limited and not well understood. This paper summarizes the combination of these algorithms and proposes a new Hybrid Inpainting Algorithm for inpainting large as well as small regions in less time. Future aspects of the study are also discussed.

IJSRD, 2014

Image inpainting is the process of filling of missing region so as to preserve its overall continuity. Image inpainting is manipulation and modification of an image in a form that is not easily detected. Digital image inpainting is relatively new area of research, but numerous and different approaches to tacked the inpainting problem have been proposed since the concept was first introduced. This paper compares two separate techniques viz, Exemplar based inpainting technique and Wavelet based inpainting technique, each portraying a different set of characteristics. This paper proposes a novel exemplar-based inpianting algorithm based upon the color distribution analysis. Color distribution is proposed to determine the confidence of the target patches situated on the boundary of the missing region by measuring the variation of variances of neighboring source patches. A review and analysis for different method were analysed which are explained below and image inpainting using TV model weighted method are analysed. Finally, the results of numerical experiments comparing this approach to inpainting to numerous others will be presented.

Digital Inpainting becomes very popular topic of research in image processing in today’s world of technology. It is much application, which includes graphical object, in film postproduction, removing superimposed text like subtitles, dates, time, and removing the complete object from image, which is unwanted in image. While completing the missing region of image, information required is filled by using structural information available in nearby area of that image. This filling done in such manner that it is difficult to find the area restored with image Inpainting. The viewer that is unaware of this fact saw that image is normal. This image Inpainting finds the pixel with maximum match to complete the image. In this paper various Inpainting algorithms are discuss.

International Journal of Computer Applications, 2012

Image inpainting was historically done manually by painters for removing defect from paintings and photographs. Fill the region of missing information from a signal using surrounding information and re-form signal is the basic work of inpainting algorithms. Here in this paper we have studied and reviewed many different algorithms present for doing image inpainting and explain their approach. We have briefly explain some algorithms for video inpainting applications. This paper contain work done in the field of image inpainting and guide newcomers who are willing to work in image inpainting field.

Image Inpainting is the process of reconstructing or retouching an image. It has a wide range of applications including region filling, object removal, denoising, compression, etc. It is an important work done in the field of image processing. This research work has been carried out to reconstruct an old image by filling the spatial information from the surroundings in the damaged portion such as scratches, tampered pages, missing areas and holes. This paper provides details regarding image inpainting using exemplar based method for both structure and texture reconstruction.

International Journal of Computer Engineering in Research Trends

The process of restoring missing areas of an image is referred to as "image inpainting." It is a significant challenge in the field of computer vision and a crucial feature that is utilized in a wide variety of image and graphics programs. Although image inpainting, also known as the art of repairing old and worn images, has been around for a couple of years, it has recently gained even more popularity due to recent developments in image processing techniques. Image inpainting can be thought of as the art of restoring old and worn images. Automatic image inpainting has become an important and challenging area of research in image processing due to the advancement of tools for image processing and the flexibility of digital image editing. Automatic image inpainting has found important applications in computer vision and is also becoming an important image processing application. Due to its high significance and effectiveness in a variety of image processing applications such as, for example, object removal, image restoration, manipulation, re-targeting, compositing, and image-based rendering, researchers have studied the image inpainting problem intensively over several decades. The process of eliminating or filling in a missing area in an image is referred to as "image inpainting," It is defined as in-depth knowledge of the image details in terms of its structure and texture. It is considered to be one of the most challenging subjects in image processing. This article presents a survey of most image inpainting techniques and summarizes them, along with comparisons that include the benefits and drawbacks of each method. These comparisons and summaries can assist researchers in evaluating their own proposed techniques against existing ones.

2014

Image inpainting is the process of filling in missing parts of damaged images based on information gathered from surrounding areas. In addition to problems of image restoration, inpainting can also be used in wireless transmission and image compression applications. This paper gives comparative study of different Image Inpainting Techniques. The proposed work includes the PDE based inpainting algorithm and Texture synthesis based inpainting algorithm.

International Journal of Emerging Trends in Engineering Research , 2021

Image inpainting is the process of reconstruction of the damaged image and removal of unwanted objects in an image. In the image inpainting process patch priority and selection of best patch plays a major role. The patch size is also considered for producing good results in the image inpainting. In this paper patch priority is obtained by introducing a regularization factor (ɷ). The best patch selection is acquired by using the Sum of Absolute Difference (SAD) distance method. The results of inpainting are investigated with adjustable patch sizes of 5×5, 7×7, 9×9, 11 × 11, and 13 × 13 for the proposed method. The performance of these adjustable patch sizes is observed by using Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE). The best suitable patch size for good inpainting is announced based on the values of PSNR and MSE.