Development of a Text Detection and Recognition System to Assist Individuals with Visual Impairments

This research focuses on developing a text detection and recognition system tailored to aid visually impaired individuals in accessing cricical information. Utilizing a camera-based system, detects and interprets text from various sources such as signage, labels, and announcements. The core technology leverages the YOLOv8 object/text-image detection algorithm, which achieved an accuracy of 0.74, precision of 0,984, recall of 0,642, and an F1-score of 0,777, for text detection coupled with Optical Character Recognition (OCR) for converting text to machine-readableformat. Subsequently, the text is transformed into speech using eSpeak software, providing an auditory output for users, with an average processing time of 7.271 ms.. The primary goal of this project is to enable visually impaired individuals to interact more effectively with their environment by accessing textual information independently. Additionally, this study incorporates a user acceptance test with five visually impaired participants to assess the system’s usability. Feedback from participants has been overwhelmingly positive, highlighting the system’s effectiveness in facilitating access to text-based content.