OBJECT DETECTION AND SOUND RECOGNITION YOLOv5 AND GTTS

COMPUTER ENGINEERING

This research presents an innovative solution aimed at enhancing accessibility for individuals with visual impairments by integrating YOLOv5 (You Only Look One) object detection and Google Text-to-Speech (GTTS) technology. The proposed system empowers blind users by providing real-time information about their surroundings through object detection and sound recognition. The YOLOv5 model is employed to accurately detect and classify objects within the user's environment, leveraging its efficiency and speed. Simultaneously, sound recognition algorithms are incorporated to identify and interpret auditory cues, such as alarms, sirens, or other important sounds, enhancing situational awareness. To bridge the visual information gap, detected objects are converted into meaningful spoken descriptions using GTTS, facilitating an auditory understanding of the surroundings. The system operates in real-time, ensuring timely and relevant information delivery. The effectiveness of the proposed solution is evaluated through extensive testing with visually impaired participants, emphasizing user feedback and system responsiveness. The results showcase the system's potential to significantly improve the daily lives of individuals with visual impairments by providing them with a comprehensive and intuitive understanding of their environment.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.