Home > Published Issues > 2014 > Volume 2, No. 2, December 2014 >

A Hybrid Edge Detection Method for Cell Images Based on Fuzzy Entropy and the Canny Operator

Yuexiang Li 1, Siu-Yeung Cho 1, and John Crowe 2
1 Faculty of Engineering, University of Nottingham, Ningbo, China
2 Faculty of Engineering, University of Nottingham, Nottingham, United Kingdom

Abstract—Since cell biologists need to use image processing techniques, such as edge detection, to analyze cell images the precision of these techniques is pivotal to their work. Due to the often low quality of cell images, existing edge detectors fail to routinely produce highly accurate results. In this paper, a novel hybrid method based on the canny operator and fuzzy entropy theory is proposed. The method calculates the fuzzy entropy of gradients from an image to decide the threshold for the canny operator. Application of the method to cell images has demonstrated its excellent performance in edge detection and robustness in the presence of noise.

Index Terms—cell images, canny operator, fuzzy entropy theory, hybrid method, image processing

Cite: Yuexiang Li , Siu-Yeung Cho, and John Crowe, "A Hybrid Edge Detection Method for Cell Images Based on Fuzzy Entropy and the Canny Operator," Journal of Image and Graphics, Vol. 2, No. 2, pp. 135-139, December 2014. doi: 10.12720/joig.2.2.135-139