Constructing Ghost Free High Dynamic Range Images Using Convolutional Neural Network and Structural Similarity Index
Journal Title: Journal of Independent Studies and Research - Computing - Year 2017, Vol 15, Issue 2
Abstract
A foreign object, commonly called as a ghost artifact, is integrated in the HDR output image when there is a moving object in the photography scene. The problem is persisting even after numerous models proposed by researchers. The most advanced techniques for capturing HDR photographs are still struggling with the produced output till date. The majority of the existing techniques are unable to tackle the situation where luminance varies in the input images. This ultimately causes the algorithms to compromise on quality by reducing the input images. In this research, two techniques are presented that help in getting rid of ghost artifacts from HDR output. The first method that is used in this research is a vintage method that uses structural similarity index measurement. The second method is using Convolutional Neural Network that is proved to be the best configuration of neural network for image recognition purpose. The first method using structural similarity is based on the vintage method of matching two images. This method works by comparing the objective image with the reference image and the algorithm estimates the degree of similarity in context of luminance, contrast and structural information. The second method is the use of convolutional neural network. Since convolutional neural network is a specialized tool for image processing, a convolutional neural network is designed and trained to estimate the index of similarity of two or more images.
Authors and Affiliations
Shahid Khan, Dr. Husnain Mansoor Ali
Keywords
Related Articles
- EP ID EP626014
- DOI 10.31645/jisrc/(2017).15.2.04
- Views 129
- Downloads 0
Analysis of SSD Utilization by Graph Processing Systems
Graph Processing Systems are highly productive when it comes to graph data. While using data parallel approach, it could not exploit common characteristics of a graph computation workload. To address all these challenges...
Online Optical Tomography System Application of Charge-Coupled Device (CCD) for Object Detection in Crystal Clear Water
This research presents an application of Charge-Coupled Device (CCD) linear sensor and laser diode in an optical tomography system. These optoelec- tronic sensors are believed to detect solid objects rather than transpar...
Implementation of Discrete Fourier Transform and Orthogonal Discrete Wavelet Transform in Python
This paper presents implementation of Discrete Fourier Transform and Orthogonal Discrete Wavelet Transform in Python computer programming language. The Fourier Transform is a fundamental signal processing tool whereas th...
Boundary Vertices Sensitive Vertex-cut Partitioning Algorithm
Graph Partitioning is one of the favorite research topics among researchers since the 70s. It attracts a diverse group of researchers from various fields such as engineering, science and mathematics. In the last decade,...
Performance Analysis of Classification Learning Methods on Large Dataset using two Data Mining Tools
Data is increasing day to day thus, processing this data and selection of right method and tool is really a big problem. Computer scientists are process- ing and analysing data on different machine learning methods using...