Comparison of computational image inpainting methods

Download
index.pdf
2018
Kurt, Cande
Show full item record
226
views
250
downloads
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.
Image processing., Artificial intelligence., Multivariate analysis., Regression analysis., Differential equations, Partial.
http://etd.lib.metu.edu.tr/upload/12622809/index.pdf
https://hdl.handle.net/11511/27832
Graduate School of Natural and Applied Sciences, Thesis

Suggestions

Comparison of whole scene image caption models
Görgülü, Tuğrul; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2021-2-10)
Image captioning is one of the most challenging processes in deep learning area which automatically describes the content of an image by using words and grammar. In recent years, studies are published constantly to improve the quality of this task. However, a detailed comparison of all possible approaches has not been done yet and we cannot know comparative performances of the proposed solutions in the literature. Thus, this thesis aims to redress this problem by making a comparative analysis among six diff...
Hierarchical representations for visual object tracking by detection
Beşbınar, Beril; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2015)
Deep learning is the discipline of training computational models that are composed of multiple layers and these methods have improved the state of the art in many areas such as visual object detection, scene understanding or speech recognition. Rebirth of these fairly old computational models is usually related to the availability of large datasets, increase in the computational power of current hardware and more recently proposed unsupervised training methods that exploit the internal structure of very lar...
Image Captioning with Unseen Objects
Berkan, Demirel; Cinbiş, Ramazan Gökberk; İkizler Cinbiş, Nazlı (2019-09-12)
Image caption generation is a long standing and challenging problem at the intersection of computer vision and natural language processing. A number of recently proposed approaches utilize a fully supervised object recognition model within the captioning approach. Such models, however, tend to generate sentences which only consist of objects predicted by the recognition models, excluding instances of the classes without labelled training examples. In this paper, we propose a new challenging scenario that ta...
Contrast Enhancement of Microscopy Images Using Image Phase Information
Çakır, Serhat; Atalay, Rengül; ÇETİN, AHMET ENİS (2018-01-01)
Contrast enhancement is an important preprocessing step for the analysis of microscopy images. The main aim of contrast enhancement techniques is to increase the visibility of the cell structures and organelles by modifying the spatial characteristics of the image. In this paper, phase information-based contrast enhancement framework is proposed to overcome the limitations of existing image enhancement techniques. Inspired by the groundbreaking design of the phase contrast microscopy (PCM), the proposed ima...
Comparison of histograms of oriented optical flow based action recognition methods
Erciş, Fırat; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2012)
In the task of human action recognition in uncontrolled video, motion features are used widely in order to achieve subject and appearence invariance. We implemented 3 Histograms of Oriented Optical Flow based method which have a common motion feature extraction phase. We compute an optical flow field over each frame of the video. Then those flow vectors are histogrammed due to angle values to represent each frame with a histogram. In order to capture local motions, The bounding box of the subject is divided...
Citation Formats
C. Kurt, “Comparison of computational image inpainting methods,” M.S. - Master of Science, Middle East Technical University, 2018.
METU IIS - Integrated Information Service open@metu.edu.tr