Vision Aid: AI-Powered Assistive Technology for the Visually Impaired

Authors

  • Donna K Jomy Dept. of Computer Science and Engineering, Sahrdaya College of Engineering and Technology Author
  • Emy Joseph Dept. of Computer Science and Engineering, Sahrdaya College of Engineering and Technology Author
  • Nayana M Dept. of Computer Science and Engineering, Sahrdaya College of Engineering and Technology Author
  • P Lakshmi Parvathi Dept. of Computer Science and Engineering, Sahrdaya College of Engineering and Technology Author
  • Anil Antony Dept. of Computer Science and Engineering, Sahrdaya College of Engineering and Technology Author
  • Sreejith P S Dept. of Computer Science and Engineering, Sahrdaya College of Engineering and Technology Author

DOI:

https://doi.org/10.21467/proceedings.7.5.3

Keywords:

Assistive Technology, Artificial Intelligence, Deep Learning

Abstract

Vision Aid is a tech tool powered by AI that intends to increase the self-reliance and well-being of people who have impaired sight. This mobile application offers features such as medicine identification, emotion detection, and real-time facial recognition, providing intelligent support through advanced deep learning algorithms. The system, with convolutional neural network as well as via transfer learning, rapidly recognizes a number of known faces, understands multiple emotional signals, along with reads prescription labels, in addition to translating this entire store of information into real-time spoken feedback. By fostering user autonomy, the software also addresses critical issues like social isolation, medication management, and safety, creating a comprehensive and inclusive experience. The potential for scalability exists, as the data and training models can be repurposed for different datasets. For instance, an eye model could serve as a sensor for an autonomous mobile robot for tasks such as object recognition or environmental awareness. Vision Aid, along with assistive technology continuing improvement, is certainly a breakthrough for many people with visual impairments so they can improve capability in closing the divide across the environment surrounding them.

References

[1] T. Pun, P. Roth, G. Bologna, K. Moustakas, and D. Tzovaras, "Image and video processing for visually handicapped people," EURASIP J. Image Video Process. 2007, 1–15 (2007) at https://jivp-eurasipjournals.springeropen.com/articles/10.1155/2007/25214

[2] C. Shi, C. Tan, and L. Wang, "A facial expression recognition method based on a multibranch cross-connection convolutional neural network," IEEE Access 9, 1–10 (2021) at https://ieeexplore.ieee.org/iel7/6287639/9312710/09367192.pdf

[3] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv:1409.1556, (2014) at https://arxiv.org/abs/1409.1556

[4] L. Li, X. Mu, S. Li, and H. Peng, "A review of face recognition technology," IEEE Access 8, 123456–123467 (2020)

[5] G. Zhao, H. Yang, and M. Yu, "Expression recognition method based on a lightweight convolutional neural network," IEEE Access 8, 1–10 (2020) at https://ieeexplore.ieee.org/iel7/6287639/8948470/08952725.pdf

[6] S. D. M. Iqbal and B. Y. Suprapto, "Real-time implementation of face recognition and emotion recognition in a humanoid robot using a convolutional neural network," IEEE Access 10, 1–10 (2022) at https://ieeexplore.ieee.org/document/9864185

[7] Y. Lecun, Y. Bengio, and G. Hinton, "Deep learning," Nature 521, 436–444 (2015) at https://www.nature.com/articles/nature14539

[8] B. Mocanu, R. Tapu, and T. Zaharia, "Deep-see face: A mobile face recognition system dedicated to visually impaired people," IEEE Access 6, 1–10 (2018) at https://ieeexplore.ieee.org/iel7/6287639/8274985/08466782.pdf

[9] L. B. Neto, F. Grijalva, V. R. M. L. Maike, L. C. Martini, D. Florencio, M. C. C. Baranauskas, A. Rocha, and S. Goldenstein, "A kinect-based wearable face recognition system to aid visually impaired users," IEEE Trans. Hum.-Mach. Syst. 47(2), 1–10 (2017) at https://ieeexplore.ieee.org/document/7571103

[10] S. Zhang, F. Jiang, and M. Li, "Facial expression recognition based on improved VGG16 convolutional neural network," in Proc. 2nd Int. Conf. Signal Process. Comput. Netw. Commun., 162–168 (ACM, 2024) at https://dl.acm.org/doi/abs/10.1016/j.patcog.2016.07.026

[11] Y. Huang, F. Chen, S. Lv, and X. Wang, "Facial expression recognition: A survey," Symmetry, vol. 11, no. 10, pp. 1189, 2019) at https://www.mdpi.com/2073-8994/11/10/1189

[12] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the inception architecture for computer vision," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2818–2826 (2016) at https://ieeexplore.ieee.org/document/7780677

[13] R. Girshick, "Fast R-CNN," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 1440–1448 (2015) at https://ieeexplore.ieee.org/document/7410526

[14] S. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial networks," Commun. ACM 63(11), 139–144 (2020) at https://dl.acm.org/doi/10.1145/3422622

[15] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 779–788 (2016) at https://ieeexplore.ieee.org/document/7780460

Downloads

Published

2025-09-23

Issue

Vol. 7 No. 5 (2025): Proceedings of the International Conference on Innovations in Mechanical Robotics Computing and Biomedical Engineering: ICIMRBE 2025

Section

Articles

License

Creative Commons License

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

How to Cite

[1]
D. K. Jomy, E. Joseph, M. Nayana, P. L. Parvathi, A. Antony, and S. P. S, “Vision Aid: AI-Powered Assistive Technology for the Visually Impaired”, AIJR Proc., vol. 7, no. 5, pp. 15–22, Sep. 2025, doi: 10.21467/proceedings.7.5.3.