Acute lymphoblastic leukemia (ALL) is characterized by an abundance of lymphoid blasts in the blood and typically affects adolescents. Due to their ability to undergo rapid differentiation, these cells pose a diagnostic risk. A misdiagnosis can cause additional health problems. Only careful microscopic inspection of these cells will yield an accurate diagnosis. Image analysis for quantitative evaluation of stained blood microscopic images for leukemia detection is an efficient and low-cost method that saves time and allows treatment to begin as soon as the diagnosis is made. Using fuzzy based two stage color segmentation, we can separate leukocytes from other blood components. Support Vector Machine (SVM) classification was used to derive features from a total of 108 images. The current techniques for detecting Leukemia take too long, cost too much money, and rely too heavily on medical professionals. We suggest an automated algorithm for Leukemia detection and classification using the computational framework MATLAB to address these limitations. The microscopic pictures are used as inputs, and a variety of image processing methods including image enhancement, segmentation, feature extraction, and classification are applied to them. Diseases can be detected and recognized at an early stage by analyzing microscopic images of blood cells. Image processing techniques are increasingly being used by hematologists for analysis, detection, and identification of leukemia kinds in patients. Since there is no need for expensive laboratory tools, image-based detection is a quick and low-cost option. Microscopic pictures undergo image processing procedures like enhancement, segmentation, and feature extraction.

Image Classification, Blood cells, White blood cells Detection, Deep learning