Automatic thresholding method for edge detection algorithms
Petre Anghelescu, Vlad Gabriel Iliescu, Constantin Mara, Mihai-Bogdan Gavriloaia · 2016
This paper describes an efficient edge detection algorithm that can be used as a plug-in for digital image processing systems. The proposed algorithm uses a method based on iterative clustering targeting a reduced number of operations. The algorithm splits the image into two parts, background and foreground, and calculates the mean value for each of them. Based on these results, the new threshold value will be obtained and looped until the mean values remain unchanged. The only pixels affected by the change are the pixels with values between the previous two thresholds, so only they have to be redistributed to a new class. As a result, only few operations are needed in order to obtain the desired threshold. All the algorithms and results obtained in this paper are developed and tested using the C# programming language.