An Efficient System for Automatic Blood Type Determination Based on Image Matching Techniques

Abstract

This paper presents a fast and accurate system to determine the type of blood automatically based on image processing. Blood type determination is important in emergency situations, where there is a need for blood transfusion to save lives. The traditional blood determination techniques are performed manually by a specialist in medical labs, where the result requires a long time or may be affected by human error. This may cause serious consequences or even endanger people’s lives. The proposed approach performs blood determination in real-time with low cost using any available mobile device equipped with a camera. A total of 500 blood samples were processed in this study using different image matching techniques including oriented fast and rotated brief (ORB), scale invariant feature transform (SIFT), and speed-up robust feature (SURF). The evaluation results show that our proposed system, which adopts the ORB algorithm, is the fastest and the most accurate among the state-of-the-art systems. It can achieve an accuracy of 99.6% in an average time of 250 ms.

Recognition and Categorization of Blood Groups by Machine Learning and Image Processing Method

“…In addition, the system were superior at accuracy 98.4% wherever the accuracy in [21] was 97% in KNN method. Moreover, The system were superior at accuracy 99.7% wherever the accuracy in [20] was 95.3% in Neural Network method. Using machine learning, different methods were used to compare the results obtained and arrive at the ideal method among the methods mentioned in classifying blood types based on accuracy and time.…”

“…In the literature, many theories have been proposed to explain the identification and classification of blood groups and Rh factors using several methods such as image processing or analysis and machine learning using several algorithms such as SVM, KNN, Tree, and neural networks, summa-rized based on the program used in terms of image processing or analysis and counting of granules in blood drops, as some of the works poor some parameters such as processing time and accuracy [6][7][8][9][10][11][12][13][14][15][16]. In addition, some work classified blood groups using machine learning from the standard method, as some work lacked the time for analysis and learning and the accuracy of classification [17][18][19][20]. Moreover, some work classified blood regarding image processing and machine learning, as it was poor learning and test times [21][22][23].…”

“…Odeh et al [20] designed a system using computer vision technology to determine blood types using a machine learning method. Blood group samples, a reference image, and a computer camera are the components of this study.…”