In this project,rapid and accurate determine of blood types is very important during emergency situation before administering a blood transfusion.
At present the method based on image recognition technology to quickly determine blood type has been widely used in the automated blood analyzer.
In this project, we propose a fast, accurate and robust blood group judgement method based on the image features of ABO blood group rapid analyzer. Firstly, the image of the disk region is segmented and identified automatically. Then, the median filter is used to suppress the noise to get the best approximation of the original image.
Then, the characteristic parameters of ABO blood group are extracted according to the gray level distribution of the image. Finally, combined with the agglutination reaction between antigen and antibody, the final blood group was determined.
The experimental results show that this method can quickly and accurately classify the ABO blood group.