Abstract:
"This study focuses on the development of an automated system for identifying medicine names
in handwritten prescriptions that employs Optical Character Recognition (OCR) and
Convolutional Recurrent Neural Network (CRNN) technologies. The project tackles the
challenge of accurately transcribing various handwriting styles and potential distortions in
medical prescriptions, which is critical for improving patient safety and healthcare efficiency.
During the initial implementation phase, the author chose the IAM dataset, which consists of
handwritten text images created specifically for handwritten text recognition (HTR) tasks. This
dataset includes a wide variety of handwriting styles and formats commonly found in medical
prescriptions, making it ideal for training and benchmarking OCR and CRNN models.
This study focuses on the development of an automated system for identifying medicine names
in handwritten prescriptions that employs Optical Character Recognition (OCR) and
Convolutional Recurrent Neural Network (CRNN) technologies. The project tackles the
challenge of accurately transcribing various handwriting styles and potential distortions in
medical prescriptions, which is critical for improving patient safety and healthcare efficiency.
During the initial implementation phase, the author chose the IAM dataset, which consists of
handwritten text images created specifically for handwritten text recognition (HTR) tasks. This
dataset includes a wide variety of handwriting styles and formats commonly found in medical
prescriptions, making it ideal for training and benchmarking OCR and CRNN models. "
