Edge Detection Enhancement Based on Filtering and Threshold Estimation
Khalid Alshalfan1, Mohammed Zakariah2
1Khalid Alshalfan, Al-Imam Mohammad Bin Saud Islamic University, College of Computer Science. Riyadh, Saudi Arabia.
2Mohammed Zakariah*, King Saud University, College of Computer Science and Information, Riyadh, Saudi Arabia.
Manuscript received on June 08, 2020. | Revised Manuscript received on June 25, 2020. | Manuscript published on June 30, 2020. | PP: 1155-1163 | Volume-9 Issue-5, June 2020. | Retrieval Number: E9957069520/2020©BEIESP | DOI: 10.35940/ijeat.E9957.069520
Open Access | Ethics and Policies | Cite | Mendeley
© 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: An edge detection is a critical tool under image processing and computer vision. It is used for security and reliability purposes to provide enhanced information about an object and recognize the contents of the image for the applications of object recognition in computer vision. The most prominent application may be pedestrian detection, face detection, and video surveillance. Traditional edge detection method has many issues that are discussed in this paper. In this study, we enhanced the edge detection technique by applying filtering and detecting the threshold values to differentiate between different contrasts in the image. Differential operations are used to detect two adaptive thresholds on the histograms of the images. We have examined this technique on three databases Pascal, Corel, and Berkeley. The results obtained were then examined with qualitative and quantitative assessments test. Entropy, Mean Squares Error, and Peak Signal to Noise Ratio values were examined and it gave better results.
Keywords: Edge detection, Canny, Sobel, Prewitt, Computer vision, Image processing.