THE JOURNAL OF KMUTNB

Volume 32, No. 02, Month APRIL, Year 2022, Pages 261 - 272

Application of curl of the counter tangential vector field for edge detection of color images

Samruan Wiangsamut, Nawapak Eua-Anant, Wutthichai Phornphatcharaphong

Abstract Download PDF

Information regarding edges is essential for many fields of image processing. A classical edge detection method, such as the Canny algorithm, uses the gradient of an intensity image for edge description. Nevertheless, such gradient information cannot be appropriately applied to natural color images. Therefore, this paper presents the application of curl of a counter tangential vector field, directly computed from color image data, to be used as information for edge detection in place of gradient magnitude used in the traditional Canny edge detection method. Experimental edge detection results, using color images in the BSDS500 database as benchmark data, indicate that the method using curl of a counter tangential vector field can effectively detect edges in color images. When compared with the results obtained using the traditional Canny edge detection method using gradient magnitude, it is found that the proposed method using curl of a counter tangential vector field yields the better F-measures in all ODS, IDS, and AP cases, for both fixed and adaptive thresholds.

Keywords

Edge Detection of Color Images; Curl; Counter Tangential Vector Field; Normal Compressive Vector Field

---