EKSTRAKSI CITRA SEL DARAH PUTIH DARI SAMPEL CITRA SEL DARAH

• Main Authors: , DIDIK HARI PURWANTO, , Ir. Balza Achmad, M.ScE.
• Format: Theses and Dissertations NonPeerReviewed
• Published: [Yogyakarta] : Universitas Gadjah Mada 2013
• Subjects: ETD
• Online Access: https://repository.ugm.ac.id/125076/; http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=65241
• Institution: Universitas Gadjah Mada

The amount and composition of white blood cells in a blood sample are important information in diagnosis about the patients health status. Doctors require two types of blood count for diagnosis, that is Complete Blood Count (CBC) and Differential Blood Count (DBC). CBC can be done by automatic instruments called by cytometer. On the other hand, DBC uses manual procedure by hematology experts (hematologist). The automatic DBC software planning can be done by using image processing technique which include segmentation, image extraction, and classification. In this research, the automatic DBC software planning is limited on segmentation and images extraction steps. The segmentation used thresholding method at Hueness, Saturation and Value channel of image (HSV thresholding). Then, the next step is labelling process in order to give labels at each white value in binary image after thresholding. After that, image clustering between plasma and nucleus images is done in order to get plasma position in coordinates. The final step is cropping operation based on plasma image coordinate in the blood cell input image. The software planning step used 20 blood cell image samples. Those steps, optimal threshold value for plasma image are: H=0-130