In this paper, we have proposed a real time android application for object detection using android Smartphone for visually impaired person. The proposed object detection system, the main module is to scan objects and match to a database of objects for object detection. Feature detector methods such as SIFT, SURF, FAST are good which yields high quality features but they are computationally complex to use in real time system. It also has limited resources for computer and Smartphone platform. In this paper, we have used Sobel edge detection method for faster feature computation by extracting object edge information. Normalization is applied to extracted object features. Further, back propagation neural network training is performed for efficient detection of objects. Compared to conventional SIFT, SURF and FAST algorithm. The proposed object detection system based on Sobel edge detection yields in increased speed of detection and low performance degradation on Smartphone.

Object Detection; Sobel Edge Detection, BPNN, Smartphone;

[1] Strumillo P. Electronic navigation systems for the blind and the visually impaired, Lodz University of Technology Publishing House ( in polish).
[2] Hersh M, Johnson M. (Eds) Assistive technology for visually impaired and blind people, Springer, London (2008)
[3] Ms. Sonali. B. Maind and Ms. Priyanka Wankar “Research Paper on Basic of Artificial Neural Network” International Journal on Recent and Innovation Trends in Computing and Communication, Vol. 2, Issue-1, January 2014, pp.96 – 100.
[4] Gartner Says Worldwide Sales of Mobile Phone
http:/www.gartner.com/newsroom/id/2237315.
Accessed 25th February 2013.
[5] Kanghun Jeong and Hyeonjoon Moon “Object Detection using FAST Corner Detector based on Smartphone platforms” 2011 First ACIS/JNU International Conference on Computers, Networks, Systems, and Industrial Engineering, pp.111 – 115.
[6] K. Matusiak, P.Skulimowski and P. Strumillo “Object Recognition in a mobile phone application for visually impaired users” 6th International Conference on Human System Interaction (HSI), 2013 , IEEE, pp. 479 – 484.
[7] Savitha G, Venugopal P S, Dr. Sarojdevi and Dr. Niranjan Chiplunkar “An Approach for Object Detection in Andriod Device” Fifth International Conference on Signal and Image Processing , 2014, pp. 9 – 14.
[8] Ruxandra tapu, Bogdan Mocanu, Andrei Bursuc and Titus Zaharia “A Smartphone-based obstacle detection and classfication system for assisting visually impaired people” Proceedings of the 2013 IEEE International Conference on Computer Vision Workshops, pp. 444-451.
[9] Rashmi, Mukesh Kumar and Rohini Saxena “ Algorithm And Technique On Various Edge Detection : A Survey” An International Journal Signal & Image Processing, June 2013, Vol.4, Issue-3, pp.65-75.
[10] Saduf and Mohd Arif Wani “Comparative Study of Back Propagation Learning Algorithms for Neural Networks” International Journal of Advanced Research in Computer Science and Software Engineering, December 2013 Vol.3, Issue-12, pp 1151-1157.
[11] Wenshuo Gao, LeiYang Xiaoguang Zhang and Huizhong Liu , “An Improved Sobel Edge Detection” 2010 3rd IEEE International Conference on Computer Science and Information Technology (ICCSIT), pp. 67 – 71.
[12] Dr. Rama kishore and Taranjit Kaur “Backpropagation Algorithm: An Artificial Neural Network Approach for Pattern Recognition” International Journal of Scientific & Engineering Research, June 2012 , Vol.3, Issue-6, pp.1-