Author : Preethi Harris 1
Date of Publication :21st January 2020
Abstract: Vision impairment is one of the top disabilities among mankind. Indians with this disability roughly account to one-third of the world’s blind population. Hence accessible visual information improves independence and safety of visually impaired people. With the explosion of data and multimedia, researchers are exploring new avenues to train devices that detect and classify multiple objects within an image. At the outset, the advancements in the field of deep learning can be extended to enhance the life of the visually challenged through smart devices also. Inspired by these findings in literature, a virtual assistant for the visually challenged has been proposed. The assistant detects and classifies objects with an image to provide a voice output for the detected objects. This system has been designed using Mobilenet and Single Shot Detector (SSD) algorithm pertaining to Deep Learning, to incorporate deep learning network for PC and mobile devices and also finds its application for illiterates.
Reference :
-
- India has largest blind population https://timesofindia.indiatimes.com/india/India-haslargest-blind population/articleshow/2447603.cms
- Rodrigo Verschae1 and Javier Ruiz-del-Solar, "Object Detection: Current and Future Directions", Frontiers in Robotics and AI, pp.1-7,Vol 2, 2015.
- Object detection: one-stage methods.https://www.jeremyjordan.me/objectdetection-one-stage/
- Object Localization and Detection https://leonardoaraujosantos.gitbooks.io/arti ficialinteligence/content/object_localization_and_det ection.html
- Skilton Mark and Hovsepian Felix, “The 4th Industrial Revolution Responding to the Impact of Artificial Intelligence on Business”, First Edition, Palgrave Macmillan, 2018.
- Frontier of visual recognition technology https://ai.googleblog.com/2016/08/improv ing-inception-and-image.html
- CloudvisionAPI https://cloud.google.com/vision/
- Esraa Elhariria, Nashwa El-Bendaryb, Aboul Ella Hassanienc and Vaclav Snaself ,"An Assistive Object Recognition System for enhancing seniors quality of life", in the proceedings of the International Conference on Communication, Management and Information Technology , pp. 691- 700,Vol.65,2018.
- Rohini Chavan and Sachin R. Gengaje ,"Multi object detection techniques in video surveillance application",in the proceddings of IEEE International Conference on Power, Control, Signals and Instrumentation Engineering, pp. 11-23,2017.
- Ajeet Ram Pathaka, Manjusha Pandeya and Siddharth Rautaraya , "Application of Deep Learning For Object Detection", in the proceedings of International Conference on Computational Intelligence and Data Science, pp. 1706-1717,Vol.132,2018.
- Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto and Hartwig Adam, “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”, arXiv:1704.04861v1, 2017.
- Wei Liu, Dragomir Anguelov, DumitruErhan, Christian Szegedy,Scott Reed, Cheng-Yang Fu, and Alexander C. Berg, "SSD: Single Shot MultiBox Detector", in the proceedings of the European Conference on Computer Vision, Pg.21-37,2016.
- Mark Everingham ,S. M. Ali Eslami,Luc Van Gool,Christopher K. I.Williams,John Winn and Andrew Zisserman,"ThePASCAL VisualObject Classes Challenge:A Retrospective",International Journal of Computer Vision, pp.98-136,Vol.111, No.1,2015