Novel Image Based Blood Group Identification from Agglutinated Images
S. Jana1, N. Sivakumar Reddy2, K. Gopi3
1S. Jana, Associate Professor, Dept. of Engineering and Communication Engineering, Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology, Chennai, India.
2N. Sivakumar Reddy, Final Year, Dept of Engineering and Communication Engineering, Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology, Chennai, India.
3K. Gopi, Final Year, Dept of Engineering and Communication Engineering, Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology, Chennai, India.
Manuscript received on 02 April 2019 | Revised Manuscript received on 11 May 2019 | Manuscript published on 30 May 2019 | PP: 2210-2214 | Volume-8 Issue-1, May 2019 | Retrieval Number: A2154058119 /19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Detection of blood group before blood transfusion in situations of disaster or in remote areas where expert is unavailable is a challenge. Also, at present, technicians are performing blood group identification tests manually, which are prone to more human errors. Determination of the human blood types without any manual errors with less computation time in situations of emergency is the need of the hour. Here we propose a method based on processing of images that are obtained during the slide test where each of the reagents Antigen-A, Antigen-B and Antigen-D are added to the samples of blood in three separate slides. Image processing techniques such as morphological processing, and quantification of contour ring is used in determining the blood group. The images of the samples obtained after the slide test are processed and the occurrence of agglutination is evaluated. The proposed method is used to determine the blood group without any human error in emergency situation. Experimental results show that blood group identification using the proposed image processing technique gives accurate results thereby providing an alternative to microscope based identification in situations of emergency.
Index Terms: Blood Group, Agglutination, Morphological Processing, Contour Ring
Scope of the Article: Biomedical Computing