Comparison of computational image inpainting methods

Kurt, Cande
Image processing plays an important role in today’s world. It has been using in medicine, quality control, defense industry, fine arts to ease for our lives. There are many applications in these fields such as tumor detection, license plate detection, edge detection, recognition of handwritten digits, filtering for noise reduction, restoring old photographs, and the like. The aim of image processing can be divided into five groups: visualization to observe the objects that are not visible, image sharpening or restoration to create a better visual, image retrieval to seek for the image of interest, measurement of pattern and image recognition to analyze the objects in an image. Inpainting, also known as image restoration or completion is one of the hot topics of image processing. The basic idea of image inpainting is filling lost or missing parts of an image using information from the neighboring of background with different techniques. In this research, performances of widely used image in painting algorithms, Partial Differential Equations (PDE), Kriging and Artificial Neural Networks (ANNs) are compared to those of Multivariate Adaptive Regression Splines (MARS) and Conic Multivariate Adaptive Regression Splines (CMARS) which are novel in this domain. According to the results, the PDE method overperforms the others while the rest have similar performances; particularly, with respect to Structural Similarity Index (SSMI) criterion which represents human visual evaluation.
Citation Formats
C. Kurt, “Comparison of computational image inpainting methods,” M.S. - Master of Science, 2018.