Smart Embedded Device for Object and Text Recognition through Real Time Video Using Raspberry PI
-
2018-11-27 https://doi.org/10.14419/ijet.v7i4.19.27959
-
Object Detection, Raspberry Pi, SSD, Text extraction, Video frame extraction. -
Abstract
Object recognition, text recognition, face recognition, navigation is a challenging problem in real world scenario particularly in developing advanced technology to assist for people. The complexity of recognition for a system is difficult because of having the objects and texts are having variations in sizes, shapes, mixed with complex backgrounds and having different lighting condition.We proposed a smart embedded device that consists of five switches to recognize objects and text information from videos, images, documents and pdf files. For recognizing the object, the image data is captured by using pi camera and is processed on Raspberry pi by using SSD method for detecting objects in captured data by a single deep neural network to provide a fixed size bunch of bounding boxes and scores for the presence of object class instances in those boxes.By combining MobileNets architecture with the single shot detector framework the prediction of accuracy in detecting object is more and fast. The text information from videos are recognized by extracting a best frame using Laplacian method and performs pre-processing on the frame by applying noise removal methods. Thresholding methods are applied to improve the lucidity of the text area and Grab-cut approach is used to eliminate the unwanted backgrounds. The frame is then given to the OCR to extract the text information and was given to TTS converter to convert the text output into speech from to assist users easily.
Â
ÂÂ
-
References
[1] S. Ren, K. He, R. Girshick, J. Sun. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39, pp. 1137-1149.
[2] Nidhin Raju, Dr. Anita H.B, “Text Extraction from Video Imagesâ€, International Journal of Applied Engineering Research,2017, 12, pp.14750-14754.
[3] Santosh, L.M. Jenila Livingston. Text Detection from Documented Image Using Image Segmentation. International Journal of Technology Enhancements and Emerging Engineering Research, 2013, 1,ISSN 2347-4289.
[4] Q. Ye, D. Doermann. Text Detection and Recognition in Imagery: A Survey. IEEE Transactions on Pattern Analysis& Machine Intelligence, 2015, 37, pp. 1480-1500.
[5] Yi-Feng Pan, Xinwen Hou, Cheng-Lin Liu. A Hybrid Approach to Detect and Localize Texts in Natural Scene Images. IEEE Transactions on Image Processing, 2011, 20,pp. 800-813.
[6] S. Goyal, P. Desai, V. Swaminathan. Multi-Level Security Embedded With Surveillance System. IEEE Sensors Journal,2017, 17, pp. 7497-7501.
[7] J. Ohya,A. Shio, S. Akamatsu.Recognizing characters in scene images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16,pp. 214–220.
[8] Keechul Junga, Kwang In Kimb, K. Anil Jainc.Text information extraction in images and video: a survey. Pattern Recognition Society, 2004, 37, pp. 977-997.
[9] Divya patel. A Review Paper on Object Detection for Improve the Classification Accuracy and Robustness using different Techniques. International Journal of Computer Applications, 2015, 112, pp. 0975-8887.
[10] Adrian Rosebrock. Raspberry Pi: Deep learning object detection with OpenCV, 2017. https://www.pyimagesearch.com/2017/10/16/raspberry-pi-deep-learning-object-detection-with-opencv.
[11] Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, Trevor Darrell. Caffe: Convolutional Architecture for Fast Feature Embedding. IEEE Conference on Computer Vision and Pattern Recognition, Jun 2014.
[12] Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg. SSD: Single Shot Multi Box Detector. IEEE Conference onComputer Vision and Pattern Recognition,Dec 2015.
[13] Andrew G. Howard, Menglong Zhu, BoChen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. IEEE Conference on Computer Vision and Pattern Recognition,Apr 2017.
[14] B. Anilkumar, KRJ Srikanth. Design and Development of Real Time paper Currency Recognition System of Demonetization New Indian Notes by Using Raspberry Pi for visually challenged. International Journal of Mechanical Engineering and Technology, 2018, 9, pp. 884–891.
[15] Virginia Menezes, Vamsikrishna Patchava, M. Surya Deekshith Gupta.Human detector and counter using raspberry Pi microcontroller. Innovations in Power and Advanced Computing Technologies, Jan 2018.
[16] Takasshi hirano, Yuichi Okano, Yasuhiro okada, Fumio yoda. Text and Layout Information Extraction from Document Files of Various Formats Based on the Analysis of Page Description Language. Ninth International Conference on Document Analysis and Recognition,Sep2007.
[17] B. Anil kumar. Hardware Implementation of Image Processing Concepts for Mechatronics: A Survey. International Journal of Mechanical Engineering and Technology, 2018, 9, pp.876-883.
[18] S. Syed Ameer Abbas, M. Anitha, X. Vinitha Jaini. Realization of multiple human head detection and direction movement using Raspberry Pi. International Conference on Wireless Communications, Signal Processing and Networking, Mar 2017.
[19] Samruddhi Deshpande, RevatiShriram. Real Time Text Detection and Recognition on Hand Held Objects to Assist Blind People. International Conference on Automatic Control and Dynamic Optimization Techniques, Sep 2016.
-
Downloads
-
How to Cite
Anil Kumar, B., Praneeth Chowdary, T., & Govinda Rao, T. (2018). Smart Embedded Device for Object and Text Recognition through Real Time Video Using Raspberry PI. International Journal of Engineering & Technology, 7(4.19), 556-562. https://doi.org/10.14419/ijet.v7i4.19.27959Received date: 2019-02-26
Accepted date: 2019-02-26
Published date: 2018-11-27