Comparison of Neural Networks with Feature Extraction Methods for Depth Map Classification
Keywords:Convolutional Neural Network, deep learning, depth map, Fourier transform, Radon transform
In this paper a comparison between feature extraction methods (Radon Cosine Method, Canny Contour Method, Fourier Transform, SIFT descriptor and Hough Lines Method) and Convolutional Neural Networks (proposed CNN and pre-trained AlexNet) is presented. For evaluation of these methods depth maps were used. The tested data were obtained by Microsoft Kinect camera (IR depth sensor). The feature vectors were classified by the Support Vector Machine (SVM). The confusion matrix for evaluation of experimental results was used. The row of confusion matrix represents target class of tested data and the column represents predicted class. From the experimental results is evident that, the best results were achieved by proposed CNN (97.4%). The feature extraction methods reached up to 91.9% (Radon Cosine Method). The pre-trained AlexNet scored 93.7%.
SYKORA, P., KMAENCAY, P., HUDEC, R., BENCO, M. and SINKO, M. Comparison of Feature Extraction Methods and Deep Learning Framework for Depth Map Recognition. In Proceedings of the New Trends in Signal Processing (NTSP 2018). Demanovska Dolina: IEEE, 2018, p. 1-7. https://doi.org/10.23919/NTSP. 2018.8524109.
MURUGESWARI, M. and VELUCHAMY, S. Hand Gesture Recognition System for Real-Time Application. In Proceedings of the International Conference on Advanced Communication Control and Computing Technologies (ICACCCT), Ramanathapuram: IEEE, 2014, p. 1220-1225. https://doi.org/10.1109/ICACCCT.2014.7019293.
CERRUELA GARCIA, G., GARCIA PEDRAJAS, N., BELLIDO OUTEIRINO, F.J., LUQUE RUIZ, I. and GOMEZ-NIETO, M.A. An Ubiquitous System for Advertising Using Mobile Sensors and Hand Gestures. In Proceedings of the IEEE Fourth International Conference on Consumer Electronics Berlin (ICCEBerlin). Berlin: IEEE, 2014, p. 205-209. https://doi.org/10.1109/ICCEBerlin.2014.7034304.
CHUDGAR, H.S., MUKHERJEE, S. and SHARMA, K. S Control: Accelerometer-based Gesture Recognition for Media Control. In Proceedings of the International Conference on Advances in Electronics Computers and Communications. Bangalore: IEEE, 2014, p. 1-6. https://doi.org/10.1109/ICAECC.2014.7002459.
YAO, Y. and FU, Y. Contour Model-Based Hand-Gesture Recognition Using the Kinect Sensor. Transactions on Circuits and Systems for Video Technology, 2014, vol. 24, no. 11, p. 1935-1944. https://doi.org/10.1109/TCSVT.2014.2302538.
AZAD, R., ASADI-AGHBOLAGHI, M., KASAEI, S. and ESCALERA, S. Dynamic 3D Hand Gesture Recognition by Learning Weighted Depth Motion Maps. Transactions on Circuits and Systems for Video Technology, 2018, vol. 29, no. 6, p. 1729-1740. https://doi.org/10.1109/TCSVT.2018.2855416.
KASTHURI ARACHCHI, S.P., HAKIM, N.O., HSU, H-H., KLIMENKO, S.V. and SHIH, T.K. Real-Time Static and Dynamic Gesture Recognition Using Mixed Space Features for 3D Virtual World’s Interactions. In Proceedings of the 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA). Krakow: IEEE, 2018, p. 627-632. https://doi.org/10.1109/WAINA.2018.00157.
KHORSANDI, M.A., KARIMI, N., SOROUSHMEHR, S.M.R., HAJABDOLLAHI, M., SAMAVI, S., WARD, K. and NAJARIAN, K. Radon Transform
Inspired Method for Hand Gesture Recognition. In Proceedings of the 23rd International Conference on Pattern Recognition (ICPR). Cancun: IEEE, 2016, p. 1053-1058. https://doi.org/10.1109/ICPR.2016.7899775.
CANNY, J. A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, vol. PAMI-8, no. 6, p. 679-698. ISSN 0162-8828.
DONG, Y., LI, M. and LI, J. Image Retrieval Based on Improved Canny Edge Detection Algorithm. In Proceedings of the International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC). Shengyang: IEEE, 2013, p. 1453-1457. ISBN 978-1-4799-2565-0.
BEAUDOIN, N. and BEAUCHEMIN, S. An Accurate Discrete Fourier Transform for Image In Proceedings of the 16th International Conference on Pattern Recognition. Quebec City: IEEE, 2002, p. 935-939. https://doi.org/10.1109/ICPR.2002.1048189.
MA, J. Based on the Fourier Transform and the Wavelet Transformation of the Digital Image Processing. In Proceedings of the International Conference on Computer Science and Information Processing (CSIP). Xi'an: IEEE, 2012, p. 1232-1234. https://doi.org/10.1109/CSIP.2012.6309081.
LOWE, D.G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004, vol. 60, no. 2, p. 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94.
MIKHALEV, A. and ORMONDROYD, R.F. Comparison of Hough Transform and Particle Filter Methods of Emitter Geolocation using Fusion of TDOA Data. In Proceedings of the 4th Workshop on Positioning, Navigation and Communication. Hannover: IEEE, 2007, p. 121-127. https://doi.org/10.1109/WPNC.2007.353622.
KRIZHEVSKY, A, SUTSKEVER, I. and HINTON, G.E. Imagenet Classification with Deep Convolutional Neural Networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe: Curran Associates Inc., 2012, p. 1097-1105. https://doi.org/10.1145/3065386.
WU, J.L. and MA, W.Y. A Deep Learning Framework for Coreference Resolution Based on Convolutional Neural Network. In Proceedings of the IEEE 11th International Conference on Semantic Computing (ICSC). San Diego: IEEE, 2017, p. 61-64. https://doi.org/10.1109/ICSC.2017.57.
Convolutional Neural Networks for Visual Recognition [on-line]. [viewed 2008-02-12]. Available from: http://cs231n.github.io/convolutional-networks/
BRITZ, D. Understanding Convolutional Neural Networks for NLP. WILDML [on-line]. November 2015. [viewed 2008-02-12]. Available from: http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/
How to Cite
Copyright (c) 2020 Advances in Military Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
Users can use, reuse and build upon the material published in the journal for any purpose, even commercially.