[email protected] +91 9840521421 Scholarly Open Access, Peer-reviewed, Refereed Journal e-ISSN 2583-5300 Since 2022
  1. Home
  2. Archives
  3. 2026
  4. Vol. 5 Issue 2
  5. Article
Original Article

Voice Based Assistant for Visually Impaired Using Machine Learning Techniques

Open Access Peer Reviewed Crossref DOI

Authors

  • Mangala S Biradar1
  • Shilpa Rawale2
  • Manjiri Dongare3
  • Bhovati Rathod4
  • Akanksha Choure5
  • Sakshi Raut6

1 Professor, SRCOE, Department of Computer Engineering, Pune, Maharashtra, India. 2 3 4 5 6 Student, SRCOE, Department of Computer Engineering, Pune, Maharashtra, India.

Article Information

Published Online
May-August 2026
Pages
400-409
Article Type
Original Article
Check for updates
check update

Abstract

View PDF

In the field of artificial intelligence and computer vision, object detection has become a fundamental technology for enabling machines to understand and interpret visual data. Object detection involves identifying and locating objects within images or video streams by assigning labels and bounding boxes. It plays a critical role in applications such as autonomous driving, surveillance, healthcare, and assistive technologies for visually impaired individuals. Various algorithms have been developed to improve the accuracy, speed, and efficiency of object detection systems. Among the most prominent are Region-Based Convolutional Neural Networks (R-CNN), Faster R-CNN, and You Only Look Once (YOLO), each offering unique approaches to object localization and classification. This paper explores and compares these algorithms in terms of architecture, working principles, and real-world performance. The study highlights how modern deep learning techniques, especially YOLO, enable real-time object detection with high efficiency and scalability.

APC from ₹1200 + 18% GST

Peer-reviewed open access₹1200 Indian (₹1400 with DOI)$80 USD internationalpaid after acceptance Peer-reviewed open access₹1200 Indian$80 USD international ₹1200 Indian · $80 intl

  • CrossRef DOI
  • ISSN 2583-5300
  • Open Access
  • Peer Reviewed
  • Plagiarism Checked
  • Google Scholar
Contact Us Submit Paper