• Pattan Asif Ali Khan
• Prof. T. Sreenivasulu Reddy

The blood type of a person will always be an important consideration in medical studies. Blood group identification is critical while obtaining emergency blood transfusions. It was found by dilating the blood sample with a certain mix and placing the blood samples on a glass plate, so you could examine the pattern under a microscope. But, a skilled expert was also necessary to detect it correctly. It is important to correctly and quickly determine blood types without human mistakes. The technique based on current image processing technology is incredibly fast and has numerous applications in the biotechnological field. In this study, we are proposing a convolutional neural network (CNN) to accurately and fastly identify a blood type. The human eye sometimes produces inaccurate results, but when we use image processing with CNN to determine the blood group, the little mistakes are removed. On the basis of the analysis of the images taken during the slide test, we can easily and precisely classify the blood group using deep learning technology. Image processing techniques including thresholding and morphological operations are used. Hence, the developed automated technique is used to identify the blood type using CNN. When the proposed algorithm's performance is compared to existing methods approach, it performs extremely well, with 99% classification accuracy.

Antigen, Blood Samples, Image Processing, Histogram, LBP (Local Binary Pattern), Nearest Neighbour Classifier, Feature Extraction, CNN (Convolutional Neural Network) and IOT (Internet of Things).

"Identification of Human Blood Group Using Convolutional Neural Network.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.k105-k110, May-2023, Available :http://www.jetir.org/papers/JETIR2305A14.pdf

"Identification of Human Blood Group Using Convolutional Neural Network.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppk105-k110, May-2023, Available at : http://www.jetir.org/papers/JETIR2305A14.pdf