Klasifikasi Golongan Darah Menggunakan Artificial Neural Networks Berdasarkan Histogram Citra

Lailis Syafaah (Program Studi Teknik Elektro, Fakultas Teknik, Universitas Muhammadiyah Malang, Malang)
Yudawan Hidayat (Program Studi Teknik Elektro, Fakultas Teknik, Universitas Muhammadiyah Malang, Malang)
Novendra Setyawan (Program Studi Teknik Elektro, Fakultas Teknik, Universitas Muhammadiyah Malang, Malang)

Indonesian Journal of Electronics and Instrumentation Systems
Vol 11, No 2 (2021): Oktober

 Blood type in the medical world can be divided into 4 groups, namely A, B, AB and O. To be able to find out the blood type, a blood type test must be done. So far, human blood type detection is still done manually to observe the agglutination process. This research applies a blood type identification process using image processing. This system works by reading the blood type card image that has been filled with blood samples, then it will be processed through a histogram process to get the minimum and maximum RGB values and pixel locations which are then classified by Artificial Neural Networks (ANN) to determine the blood type from the training results and data matching. From the test results using 12 samples, it was found that the average error in blood type identification was 16.67%.