Anuksha Chikte, Afiya Mohammad , Dipti Bangde, Aditi Charlawar, Dr. Rahila Sheikh
Yolo V3, Voice Feedback, pyttsx3, Object Detection, COCO dataset.
Object recognition technology has transformed a number of industries, including industrial facilities and driverless cars. The people who need this technology the most—those who are visually impaired—haven't been able to use it well, though. Consequently, a machine learning-based object identification system created especially for the blind community is presented in this work. The system combines text-to-speech (TTS) technology to deliver a voice-guidance technique that transmits information about the objects around users, and it incorporates the Yolo V3 (You Only Look Once) algorithm for object detection. The suggested system's primary goal is to enable visually impaired people to recognize items in a given location on their own, without the need for outside assistance. Experiments are used to carefully examine the system's effectiveness and performance to verify its precision and efficiency. The suggested method uses technical jargon like object recognition, machine learning, the Yolo V3 algorithm, and image classification techniques to identify and extract features from video frames and classify them into the appropriate groups. The COCO dataset is used. In summary, the proposed object detection system combines voice assistance and state-of-the-art deep learning techniques to let visually impaired people identify objects on their own. Experiments are used to assess the system's performance and show off its usefulness and potential in practical settings.
Article Details
Unique Paper ID: 164616

Publication Volume & Issue: Volume 10, Issue 12

Page(s): 1513 - 1517
Article Preview & Download

Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews