Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{187742,
        author = {PEEKA JAHNAVI},
        title = {REAL-TIME OBJECT RECOGNITION WITH VOICE-GUIDED NAVIGATION FOR THE VISUALLY IMPAIRED},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {6698-6700},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187742},
        abstract = {This research introduces a voice-guided navigation system designed to assist visually impaired individuals by providing real-time obstacle detection, spatial orientation, and auditory feedback. Leveraging models like SSD MobileNet V3 for object detection and Faster R-CNN for person counting, the system delivers precise information such as, "A person is 2.8 meters ahead," detailing obstacle type, position (left, right, forward), and distance. Multilingual text-to-speech (TTS) capabilities, powered by pyttsx3 and gTTS, ensure accessibility across diverse languages, while Qwen/Qwen2-1.5B- Instruct enhances natural language interaction for intuitive user experiences. Integrated with OpenCV, TensorFlow, and PyTorch, this robust platform offers real-time guidance, improving mobility, safety, and independence for visually impaired users in various environments.},
        keywords = {SSD MobileNet V3, Faster R-CNN (ResNet-50), Computer Vision (OpenCV, TensorFlow & PyTorch), Text-to-Speech (TTS) Technology, Multilingual Support},
        month = {November},
        }