Loading

Image Restoration based on Blur Identification
Kashmeera Keshav Kale1, Sangam Borkar2

1Ms. Kashmeera Keshav Kale, Department of Electronics and telecommunication, Goa College of Engineering, Farmagudi, Goa, India.
2Sangam Borkar, Department of Electronics and Telecommunication, Goa College of Engineering, Farmagudi, Goa, India.

Manuscript received on 20 March 2017 | Revised Manuscript received on 30 March 2017 | Manuscript published on 30 March 2017 | PP: 33-38 | Volume-6 Issue-1, March 2017 | Retrieval Number: A1658036117©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: It is challenging to take satisfactory photographs in poorly-lit environment using a hand-held camera. With the long exposure time, the image is blurred due to camera shake. Whereas, with short exposure time, the image is dark and noisy. In this project paper we will present a method to improve the quality of given pictures. In particular blind deconvolution will be applied to deblur the images. Blind deconvolution is an indistinct problem and needs to be solved using regularization techniques. The steps involved are: first, an image blur identification index is calculated to evaluate the sharpness of the image. The said index is used in determining whether the following procedure needs to be performed or not. Second, a normalized sparse regularization blind deconvolution technique is used to recover the image. And lastly, we check for quality using various quality assessment algorithms to evaluate the result of recovered image. Experiment result show that the proposed blur identification algorithm and the quality assessment methods are effective in upgrading the efficiency of recovering the image while guarantying a true output.
Keyword: Blur Identification metric, Blind restoration, Image quality assessment, Sparse Regularization

Scope of the Article: Image Processing and Pattern Recognition