Open AccessRed Blood Cells Detecting Depending on Binary Conversion at Multi Threshold Values
Author(s) -
Ali S. Lefta,
Hazim G. Daway,
Jamela Jouda
Publication year - 2022
Publication title -
maǧallaẗ ʻulūm al-mustanṣiriyyaẗ/mustansiriyah journal of science
Language(s) - English
Resource type - Journals
eISSN - 2521-3520
pISSN - 1814-635X
DOI - 10.23851/mjs.v33i1.1079
Subject(s) - blood smear , microscope , artificial intelligence , binary number , computer science , pattern recognition (psychology) , binary image , false alarm , computer vision , optical microscope , constant false alarm rate , image processing , microscopy , image (mathematics) , biomedical engineering , optics , mathematics , pathology , physics , medicine , scanning electron microscope , arithmetic , malaria
Automatic detection of Red Blood Cells (RBCs) by using image-processing techniques is important in determining blood disorders and diseases. This study proposes an algorithm for automatic detection of red blood cells in optical microscopy images of blood smears. The proposed method depends on binary conversion at multi-threshold and includes a morphological operation as erosion and image fill according to certain conditions. In this study, we used 50 images from IDB data of blood samples taken with an optical microscope. The suggested method is compared with other modern techniques based on the two accuracy coefficients, namely, detection and false alarm rates. Results show that the proposed method has a high detection accuracy compared to other methods.