Focused Color Intersection for Leukocyte Detection and Recognition System
| Main Authors: | Lina, Lina, Chris, Arlends, Mulyawan, Bagus |
|---|---|
| Format: | Article PeerReviewed |
| Terbitan: |
Teknik Informatika
|
| Subjects: | |
| Online Access: |
http://repository.untar.ac.id/225/ |
Daftar Isi:
- The proposed system aims to automatically detectand recognize the leukocyte types from microscopic images.Thedeveloped system detects the leukocyte area within an inputimage and classifies the leukocyte type in one of the fivecategories (neutrophils, eosinophils, basophils, lymphocytes,and monocytes). The focused color intersection method isperformed based on the color information of the blood cellimages. Three main processes in the proposed system are: 1) thecolor histogram construction, 2) the focus region determination,and 3) the active search process. The system starts withconstructing the Red Green Blue (RGB) color histogram andfinding the histogram intersection. Next, the system selects thefocus regions and does active searching of the focus regionswhich contain parts of the image which have the highestprobability of the histogram intersection. The focused colorintersection method enables the system to automatically detectleukocyte areas and determine the leukocyte types frommicroscopic images.