Abstract— The proposed system aims to automatically detect and recognize the leukocyte types from microscopic images. Thedeveloped system detects the leukocyte area within an input image and classifies the leukocyte type in one of the five categories (neutrophils, eosinophils, basophils, lymphocytes, and monocytes). The focused color intersection method is performed based on the color information of the blood cell images. Three main processes in the proposed system are: 1) the color histogram construction, 2) the focus region determination, and 3) the active search process. The system starts with constructing the Red Green Blue (RGB) color histogram and finding the histogram intersection. Next, the system selects the focus regions and does active searching of the focus regions which contain parts of the image which have the highest probability of the histogram intersection. The focused color intersection method enables the system to automatically detect leukocyte areas and determine the leukocyte types from microscopic images.
Index Terms— Leukocyte detection, leukocyte recognition, white blood cell, focus color intersection, active search.
Lina is with the Faculty of Information Technology, Tarumanagara University, Jakarta, Indonesia (e-mail: lina@untar.ac.id).
A. Chris is with the Faculty of Medicine, Tarumanagara University, Jakarta, Indonesia (e-mail: arlends.chris@untar.ac.id).
B. Mulyawan is with the Faculty of Information Technology, Tarumanagara University, Jakarta, Indonesia (e-mail: bagus@untar.ac.id).
[PDF]
Cite: Lina, Arlends Chris, and Bagus Mulyawan, " Focused Color Intersection for Leukocyte Detection and Recognition System," International Journal of Information and Electronics Engineering vol. 3, no. 5, pp. 498-501, 2013.