INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
A MODIFIED IMAGE EDGE DETECTION WITH UNIQUE MIXING OF CANNY AND SOBEL (UMCS)
Authors Name:
Mohammad Irfan
, Prof. Neeta Nathani
Unique Id:
IJSDR1808030
Published In:
Volume 3 Issue 8, August-2018
Abstract:
A modified Image edge detection method is been proposed in the work where a unique mixing of Canny edge detection and Sobel edge detection is been used for finding required edges of any image. DWT cum median filter is proposed for the restoration of images that are highly corrupted by white noise or salt & pepper noise. In this filter at first the noisy pixel is identified and then it is replaced by a suitable value. Here the size of the DWT window automatically increases until it gets its suitable median value to replace the noisy pixel. This proposed algorithm shows better results than the switching mean median filter (SMMF). The proposed algorithm is tested against different images and it gives better Peak Signal-to- Noise Ratio (PSNR), Mean Square Error (MSE) and Structural Similarity Index (SSIM).The work is been done with the help of MATLAB 2013b and the results of proposed filter is found better then available work. The work is been done with the help of MATLAB 2013b and the results of proposed filter is found better then available work
Keywords:
QSP, ASL, DWT, PSNR, MSE, MATLAB, UMCS
Cite Article:
"A MODIFIED IMAGE EDGE DETECTION WITH UNIQUE MIXING OF CANNY AND SOBEL (UMCS)", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.3, Issue 8, page no.186 - 193, August-2018, Available :http://www.ijsdr.org/papers/IJSDR1808030.pdf
Downloads:
000336256
Publication Details:
Published Paper ID: IJSDR1808030
Registration ID:180597
Published In: Volume 3 Issue 8, August-2018
DOI (Digital Object Identifier):
Page No: 186 - 193
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn