Text Detection and Recognition of Characters in Medical Prescription

Among millions of individuals throughout the world are blind or visually handicapped. Visually in able people's lives are significantly impacted by their inability to read. The proposed technology is cost-effective and assists visually challenged individuals in hearing text. This project's core aim is to employ optical character recognition to turn text characters into audio signals. The text is first preprocessed, and then each character is segmented for recognition. Following segmentation, the letter is extracted and the file containing the text is resized. The audio signal is then created from the text file. All of the preceding processes will be carried out in Python.