A pre-processing based optimized edge weighting method for colour constancy

ABSTRACT

An improvement in the existing weighted grey-edge (GE) framework for colour constancy is proposed. The acquired images are denoised by vector filtering and then, a two-step colour correction process is performed. In the first step, the GE method is used for estimating the global illuminant and perform the initial level of colour correction. The computed illuminant as well as the initial corrected image are used in the second step, which employs the weighted GE method to iteratively compute the final illuminant for obtaining the final colour corrected image. One hundred sixty-five standard test images from a publicly available colour constancy dataset were used to study the efficacy of the proposed algorithm. The results obtained indicate a significant improvement in the colour correction process as compared to the state-of-the-art colour constancy methods. The proposed algorithm reduced the mean angular error by approximately 67.85% compared to the existing weighted GE method.

KEYWORDS:

• Colour constancy
• vector median filter
• specular edges
• machine vision

Acknowledgements

The first author acknowledges the grant of SRF-GATE fellowship from Council of Scientific and Industrial Research (CSIR), New Delhi.

Disclosure statement

No potential conflict of interest was reported by the authors.

ORCID

Shveta Mahajan http://orcid.org/0000-0002-5645-9780

Notes on contributors

Shveta Mahajan is currently a doctoral researcher at Academy of Scientific and Innovative Research, CSIR - Central Scientific Instruments Organization (CSIO), Chandigarh. She received her B.Tech degree in Computer Science and Engineering from Punjab Technical University, India. Her main research interests are in the field of image processing, computer vision and machine learning.

Anu Rani received the B.Tech degree in Computer Science and Engineering from Punjab Technical University, Jalandhar, India, in 2012 and the M.E. degree in Software Engineering from Thapar University, Patiala, India, in 2015. Currently, she is a faculty in Dronacharya College of Engineering, Gurugram, Haryana, India, as Assistant Professor in Department of Computer Science Engineering. Her research interest includes image processing and artificial intelligence. Her current research focuses on color constancy approaches.

Mamta Sharma is postgraduate with M.E degree in Computer Science and Engineering from Punjab engineering college (PEC), Chandigarh, followed by first class B.Tech in computer science from PTU. Her interests and area of work have revolved around the field of software development, designing and development of algorithms, imaging, image processing, and computer vision applications.

Sudesh Kumar Mittal is doctorate in Engineering from Kurukshetra University, India. He received his M.Tech in Computer Science and Engineering from Indian Institute of Technology, Roorki, India. Currently, he is working as Professor and Head of Computer Science and Engineering Department at Rayat Bahra University, Mohali, India. His area of interests include Sensors & Intelligent Instrumentation.

Amitava Das received B.Tech in Instrumentation Engineering from Indian Institute of Technology, Kharagpur, India and M.S. in Engineering from Akron University, Ohio, U.S.A. Presently he is a researcher in the field of imaging, image processing and machine vision applications at CSIR-CSIO, Chandigarh, India.

Additional information

Funding

This study is supported in part by CSIR under the network project ASHA, Task 1.4.