Leukaemia’s Cells Pattern Tracking Via Multi-phases Edge Detection Techniques

Abstract

Edge detection involves identifying and tracing the sudden sharp discontinuities to extract meaningful information from an image. The purpose of this paper is to improve detecting the leukaemia edges in the blood cell image. Toward this end, two distinctive procedures are developed which are Ant Colony Optimization Algorithm and the gradient edge detectors (Sobel, Prewitt and Robert). The latter involves image filtering, binarization, kernel convolution filtering and image transformation. Meanwhile, ACO involves filtering, enhancement, detection and localisation of the edges. Finally, the performance of the edge detection methods ACO, Sobel, Prewitt and Robert is compared to determine the best edge detection method. The results revealed that the Prewitt edge detection method produced an optimal performance for detecting edges of leukaemia cells with a value of 107%. Meanwhile, the ACO, Sobel and Robert yielded performance results of 76%, 102% and 93% respectively. Overall findings indicated that the gradient edge detection methods are superior to the Ant Colony Optimization method.