• ROSHINI ROMEO

Deconvolution of a true image from a degraded image from unkown blur kernel is blind image deconvolution. In real life application, assuming a known kernel for deblurring is not a suitable solution. Existing methods are not robust , in this case an algorithmic approach to combined blur identification and image rebuilding is essential.This paper mainly focus on effective method of blind motion deblurring toward image diversity. This method is a combination of two schemes, edge specific and nonedge specific scheme.Such a combination is a new approach in every aspect. Prediction and detection methods comes under edge specific scheme. It is sensitive to diversity of edges of present in natural pictures. Different images have different statistical composition, non-edge specific scheme is sensitive to these statistical variations.A novel non-edgespecific adaptive scheme (NEAS) is proposed,which work well on diversity of natural images. NEAS can highlight the features from both edge specific and non-edge specific schemes. The performance of NEAS is compared against state-of-art using a very large image set.

blind motion deblurring; kernel; deconvolution ;image restoration.

"Blind Motion Deblurring Using Non-edge Specific Adaptive Scheme", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 11, page no.637-642, November-2018, Available :http://www.jetir.org/papers/JETIR1811993.pdf

"Blind Motion Deblurring Using Non-edge Specific Adaptive Scheme", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 11, page no. pp637-642, November-2018, Available at : http://www.jetir.org/papers/JETIR1811993.pdf