Leukaemia is a chronic disease in human characterized by an abnormal increase in the number of white blood cells (WBC). The existence of abnormal blood can be detected when the blood sample is taken and examined by hematologist, the process require human expertize and is time consuming. Hence,a fully automated algorithm by use of image processing to aid in the detection of leukaemia by identifying and counting the infected WBC. As per the literature review, WBC detection includes segmentation, feature extraction and classification. Recent techniques used for segmentations are Watershed and Ostu which provides an accuracy of about 90-95%,the feature extraction methods involving Hausdroff dimension and Packing dimension bring only 70% accuracy. The classification performed using classifier like k-nearest neighbor, feed forward neural network provides 92% accuracy.
Keywords : Luekaemia, Whitebloodcells, Manual Examination, İmageprocessing, Microscopic İmages, Automateddetection