A New Image Inpainting Approach based on Criminisi Algorithm

Abstract

In patch-based inpainting methods, the order of filling the areas to be restored is very important. This filling order is defined by a priority function that integrates two parameters: confidence term and data term. The priority, as initially defined, is negatively affected by the mutual influence of confidence and data terms. In addition, the rapid decrease to zero of confidence term leads the numerical instability of algorithms. Finally, the data term depends only on the central pixel of the patch, without taking into account the influence of neighboring pixels. Our aim in this paper is to propose an algorithm to solve the problems mentioned above. This algorithm is based on a new definition of the priority function, a calculation of the average data term obtained from the elementary data terms in a patch and an update of the confidence term slowing its decrease and avoiding convergence to zero. We evaluated our method by comparing it with algorithms in the literature. The results show that our method provides better results both visually and in terms of the Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity index (SSIM).

Authors and Affiliations

Nouho Ouattara, Georges Laussane Loum, Ghislain Koffi Pandry, Armand Kodjo Atiampo

Keywords

Related Articles

Impacts of Unbalanced Test Data on the Evaluation of Classification Methods

The performance of a classifier in a supervised machine learning problem is popularly evaluated by using the accuracy, precision, recall, and F1-score. These parameters could evaluate very well classifiers in the case th...

Implementation of Location Base Service on Tourism Places in West Nusa Tenggara by using Smartphone

The study is aimed to create an application that can assist users in finding information about tourism places in West Nusa Tenggara, Indonesia. West Nusa Tenggara is one of the provinces in Indonesia and one of the secon...

Multidimensional Neural-Like Growing Networks - A New Type of Neural Network

The present paper describes a new type of neural networks - multidimensional neural-like growing networks. Multidimensional neural-like growing networks are a dynamic structure, which varies depending on the external inf...

Design of Traffic Flow Simulation System to Minimize Intersection Waiting Time

This paper designs a traffic simulation system for minimizing intersection waiting time. We use SUMO simulator which is widely used as a traffic flow simulation tool for traffic flow simulation. Using the SUMO simulator...

An autonomous intelligent gateway for wireless sensor network based on mobile node

One of the recent tendencies for Wireless Sensor Networks (WSNs) that significantly increases their performance and functionality is the utilization of mobile nodes. This paper describes the software architecture of an i...

Download PDF file
  • EP ID EP596834
  • DOI 10.14569/IJACSA.2019.0100655
  • Views 90
  • Downloads 0

How To Cite

Nouho Ouattara, Georges Laussane Loum, Ghislain Koffi Pandry, Armand Kodjo Atiampo (2019). A New Image Inpainting Approach based on Criminisi Algorithm. International Journal of Advanced Computer Science & Applications, 10(6), 423-433. https://europub.co.uk/articles/-A-596834