Improvement of the Traditional Canny Edge Detection Algorithm by using Combination of Arithmetic Mean Filter, Harmonic Mean Filter and Geometric Mean Filter
Ng Kok Soon1, Zuraida Abal Abas2, Asmala Ahmad3, Hidayah Rahmalan4

1Ng Kok Soon, Faculty of Information & Communication Technology, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, Durian Tunggal, Melaka, Malaysia.
2Zuraida Abal Abas, Faculty of Information & Communication Technology, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia
3Asmala Ahmad, Faculty of Information & Communication Technology, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, Durian Tunggal, Melaka, Malaysia
4Hidayah Rahmalan, Faculty of Information & Communication Technology, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, Durian Tunggal, Melaka, Malaysia

Manuscript received on November 13, 2019. | Revised Manuscript received on 22 November, 2019. | Manuscript published on December 10, 2019. | PP: 2392-2399 | Volume-9 Issue-2, December 2019. | Retrieval Number: B6448129219/2019©BEIESP | DOI: 10.35940/ijitee.B6448.129219
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: Canny Edge Detection Algorithm was very popular on the computer vision area which used to preserve the edges of the image. Due to the defect of the Canny Edge Detection Algorithm like no efficiency on noise removal, some improvement on the Canny Edge Detection Algorithm was done by the researchers. On this paper, a new enhanced Canny Edge Detection Algorithm will be propose which replaces the Gaussian Filter with combination of Arithmetic Mean Filter, Harmonic Mean Filter and Geometric Mean Filter. The replace of Gaussian Filter with combination of Arithmetic Mean Filter, Harmonic Mean Filter and Geometric Mean Filter is to improve the performance of Canny Edge Detection Algorithm on noise removal. A comparison between Canny Edge Detection Algorithm proposed by this paper, Canny Edge Detection Algorithm proposed by (Ilkin, Tafralı, &Sahin, 2017) and traditional Canny Edge Detection Algorithm will be done. The comparison will done by using eight images with different type and size which corrupted by noise. The performance of three algorithms will be determined by using the Peak Signal to Noise Ratio (henceforth, PSNR) value which uses as a quantitative measure. From the result, the Canny Edge Detection proposed by this paper will provide a better performance on noise removal and which will give a better impact on preserve the edges of the images corrupted by noise.
Keywords: Canny Edge Detection, Harmonic Mean Filter, Arithmetic Mean Filter, Geometric Mean Filter, Peak Signal to Noise Ratio
Scope of the Article: Algorithm Engineering