Blind image deblurring using GLCM and negans obtuse mono proximate distance

ABSTRACT

Image deblurring is a challenging problem in computer vision, which aims to recover the sharp image from a blurred observation. This paper proposes the image deblurring algorithm based on Gray-Level Co-occurrence Matrix (GLCM) and Negans obtuse mono proximate distance to extract informative regions for better deblurring process without user guidance. The high-frequency layer is extracted from blurred image using 2D Haar wavelet, sparse approximation to estimate the sharper and more detailed high-frequency layer. From the high-frequency layer, rich edge region is extracted using GLCM along sliding window concepts after the canny edge detection. Finally, the extracted regions are applied for negans obtuse mono proximate distance. The proposed method avoids over-fitting data and reduces blurring. The proposed deblurring algorithm deblurs the blurred image by restoring image textures and details. The experiments performed are compared with existing deblurring algorithms to demonstrate the effectiveness of the proposed deblurring algorithm.

KEYWORDS:

• Blur kernel estimation
• Sparse approximation
• Wavelet transforms
• Canny edge
• GLCM
• Rich edge region
• Negans obtuse mono proximate distance
• Image restoration

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

S. Jothi Lakshmi

S. Jothi Lakshmi received the Bachelor Degree in Information Technology in 2006 from Anna University, Chennai, Tamilnadu, India. She received the M.E. degree in Computer Science and Engineering in the year 2010 and Ph.D degree in Information and Communication Engineering in 2013 from Anna University, Chennai, Tamil Nadu, India. She is working as an Associate Professor, Department of Computer Science and Engineering, Akshaya College of Engineering and Technology, Coimbatore, Tamil Nadu, India. Her research area includes Machine leaning, Deep learning and Image Processing.

P. Deepa

P. Deepa received the Bachelor Degree in Electronics and Communication Engineering in 2002 from Bharathiyar University, Coimbatore, Tamil Nadu, India. She received the M.E. degree in VLSI Design in the year 2007 and Ph.D. degree in Information and Communication Engineering in 2013 from Anna University, Chennai, Tamil Nadu, India. She is working as an Assistant Professor, Department of Electronics and Communication Engineering, Government College of Technology, Coimbatore, Tamil Nadu, India. Her research area includes Low Power VLSI Design and Image Processing. Her research papers published in various journals and she presented papers in national and international conferences.