A Proposed Grayscale Face Image Colorization System using Particle Swarm Optimization

A Proposed Grayscale Face Image Colorization System using Particle Swarm Optimization

Abul Hasnat (Government College of Engineering and Textile Technology, Berhampore, West Bengal, India), Santanu Halder (Government College of Engineering and Leather Technology, Kolkata, India), Debotosh Bhattacharjee (Department of Computer Science and Engineering, Jadavpur University, Kolkata, India) and Mita Nasipuri (Department of Computer Science and Engineering, Jadavpur University, Kolkata, India)
Copyright: © 2017 |Pages: 18
DOI: 10.4018/IJVAR.2017010106
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

The proposed work is a novel grayscale face image colorization approach using a reference color face image. It takes a reference color image which presumably contains semantically similar color information for the query grayscale image and colorizes the grayscale face image with the help of the reference image. In this novel patch based colorization, the system searches a suitable patch on reference color image for each patch of grayscale image to colorize. Exhaustive patch search in reference color image takes much time resulting slow colorization process applicable for real time applications. So PSO is used to reduce the patch searching time for faster colorization process applicable in real time applications. The proposed method is successfully applied on 150 male and female face images of FRAV2D database. “Colorization Turing test” was conducted asking human subject to choose the image(close to the original color image) between colorized image using proposed algorithm and recent methods and in most of the cases colorized images using the proposed method got selected.
Article Preview

Introduction

Color information is a key attribute of an image which finds extensive uses in various important fields like medical image processing, facial image processing, satellite image processing, video processing etc. (Umbaugh,1998, Gonzalez, 2001, Gonzalez, 2010). Colorization is process to convert a grayscale image into a color one and it is a long sought after goal in field of image processing (Zhang, 2016). Colorization has a wide application in the area of archaeology, medical application, entertainment, law enforcement etc. In archaeology, the gray scale archive documents can be preserved by enhancing it into a colorized one. In entertainment, manual colorization of old movies and video clips (grayscale model) is normally a laborious process (Zhang, 2016). Moreover, a color face contains information like complexion, hair color, eye ball color etc. which are required for searching a face image from color face database and hence colorization of grayscale face image is important. As the gray scale face images do not contain any color information, no color based face image processing algorithms (Hadid, 2002, Bhattacharjee, 2009, Chai, 1999) can be applied on them. Our goal is not to recover the actual ground truth color but to convert the grayscale image into a visually compelling color image so that it looks natural.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 1: 2 Issues (2017)
View Complete Journal Contents Listing