Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Green Intelligent Systems and Applications
Benitez, Ralph Andrei A.
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Transcribing Handwritten Medical Prescription using Convolutional Neural Network AlexNet Architecture and Canny Edge Detection Benitez, Ralph Andrei A.; Acula, Donata D.; Bondoc, Anton Oliver M.; Hizon, Angelo Louis L.; Santos, Aaron Joseph D.
Green Intelligent Systems and Applications Volume 4 - Issue 1 - 2024
Publisher : Tecno Scientifica Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53623/gisa.v4i1.417

Abstract

Misinterpreted medical prescriptions had led to casualties due to the illegible cursive handwriting of medical practitioners. Many studies focused on this problem. However, the accuracy was unsatisfactory and needed improvement. The study evaluated the performance of the Canny edge detection with other preprocessing methods, including RGB to Grayscale Conversion, Binarization, and Inversion, which was used to process the images of cursive handwritten medical prescriptions using Alexnet Convolutional Recurrent Neural Network (ACoRNN). The CRNN model developed by previous researchers was used as the basis for comparison, and the researchers created a faster and more accurate model. The best combination of preprocessing methods for ACoRNN was with RGB to Grayscale Conversion, Binarization, Canny edge detection, and Inversion. The researchers’ model had faster preprocessing and testing time and achieved 90.76% average accuracy through five trials.
Co-Authors Acula, Donata D. Bondoc, Anton Oliver M. Hizon, Angelo Louis L. Santos, Aaron Joseph D.