Leukemic patients are in a rapid increase. Hence, the use of microscopic images of blood samples through visual inspection to identify blood disorders has increased, opening the door for computerized techniques for detecting leukemia. This project applies computer vision techniques to increase the accuracy and speed of detection from periph-eral blood. It also enhances visualization by providing an appropriate supplement to traditional microscopy. A micro-computer (Raspberry Pi) was well programmed in Python for analyzing images with the help of a Raspberry Pi camera and a touch screen as an alternative to the eyepiece. To achieve diversity and seek for more accuracy, image datasets for this project were obtained from various resources. These datasets were then analyzed through image processing techniques to detect leukemia cells. This detection process involves resizing cells to a standard size, noise removal by linear scaling filter, global-local contrast enhancement, segmentation of white blood cells (WBCs) using marker-controlled watershed algorithm, overlapping detection and separation using watershed and k-means clustering algorithms, and extraction with selection of the most relevant features from cells. These features were then imported into the Support Vector Machine (SVM) model which resulted in an accuracy of 93.2773%. A standalone desktop application with a suitable graphical user interface (GUI) was implemented. It was then uploaded into the Raspberry Pi, some code lines were rewritten for dealing with the camera, the hardware was designed and implemented, and then formal experiments were conducted resulting in the detection of leukemia in 5 samples out of 6. This implies that precise detection can be implemented with different data taken in various imaging conditions.