Denoising of Images and Detection of Sharp Edges with Improvement in Classical Edge Detectors

  Pushpendra Ahirwar,  Prof. M. P. Parsai

This paper evaluates the performance of Laplacian of Gaussian edge detector, Prewitt edge detector, Sobel edge detector for detection of edges in a digital image corrupted with Salt & pepper noise. Different levels of noise are studied in order to evaluate the performance of these edge detectors. In this paper, we have used median filtering to mitigate the effect of salt & pepper noise. We present an image de-noising method: Sharpened Edge detection method, to detect the edges of image after the noise filtering is performed. Our method improves the output of these edge detectors and increases the quality of edges. In our method we use adaptive histogram equalization over de-noised image and we get better edge output than the classical edge detectors.

Keywords- Edge Detection, Sobel Operator, LoG operator, Prewitt operator, De-Noising, Salt and Pepper Noise, Median Filter, Adaptive histogram equalization

Unique Identification Number - IJEDR1502234
Page Number(s) - 1436-1441
Pubished in - Volume 3 | Issue 2 | May 2015
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Pushpendra Ahirwar,  Prof. M. P. Parsai,   "Denoising of Images and Detection of Sharp Edges with Improvement in Classical Edge Detectors", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.3, Issue 2, pp.1436-1441, May 2015, Available at :http://www.ijedr.org/papers/IJEDR1502234.pdf