Abstract
The proposed work summarizes approach of using histogram of gradients as descriptor which are taken as training features for the neural network. This paper describes object classification using artificial neural network with back-propagation as a Feed-Forward network. HOG features were extracted from the images to pass on to this feed-forward network and this neural network has been used to classify different categories of objects based on the features extracted and trained. The converging condition is determined and analyzed for the designed approach. The experimental neural network comprises of 64 neurons in the input layer and 16 neurons in the hidden layer and the output layer has 4 neurons, which is the number of classes. The accuracy for training as well as testing will be discussed and provided in a tabular form up to 3500 epochs. All experimental results are shown in form of graphs and tables.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jeyanthi Suresh, A., Asha, P.: Human action recognition in video using histogram of oriented gradient (HOG) features and probabilistic neural network (PNN). Int. J. Innov. Res. Comput. Commun. Eng. 4(7) (2016)
Bishop, C.: Neural Networks and Pattern Recognition. Wiley
Dalal, N., Briggs, B.: Histogram of Gradients
Fard, H.M., Khanmohammadi, S., Ghaemi, S., Samadi, F.: Human age-group estimation based on ANFIS using the HOG and LBP features. Electr. Electron. Eng.: Int. J. (ELELIJ) 2(1) (2013)
Badami, I.: Material recognition: Bayesian inference or SVMs?. In: Proceedings of CESCG 2012: The 16th Central European Seminar on Computer Graphics, Apr 2012
Vardhan, J.V., Kumar, U.: Plant recognition using hog and artificial neural network. Int. J. Recent Innov. Trends Comput. Commun. 5(5), 746–750 (2017). ISSN: 2321-8169
Neural Networks for Classification: A Survey, Peter Zhang
Devijver, P.A., Kittler, J.: Pattern Recognition: A Statistical Approach. Prentice-Hall, Englewood Cliffs, NJ (1982)
Duda, P.O., Hart, P.E.: Pattern Classification and Scene Analysis. Wiley, New York (1973)
Pradeebha, R., Karpagavalli, S.: Prediction of lung disease using HOG features and machine learning algorithms. Int. J. Innov. Res. Comput. 4(1) (2016)
Kaur, R., Singh, S., Sohanpal, H.: Human activity recognition based on Ann using Hog features. In: Proceedings of the International Conference on Advances in Engineering and Technology—ICAET-2014 Copyright© Institute of Research Engineers and Doctors. All rights reserved. ISBN: 978-1-63248-028-6. https://doi.org/10.15224/978-1-63248-028-6-02-35
Tsai, W.-Y., Choi, J., Parija, T., Gomatam, P., Das, C., Sampson, J., Narayanan, V.: Co-training of feature extraction and classification using partitioned convolutional neural networks. In: DAC’ 17 Proceedings of the 54th Annual Design Automation Conference 2017, Article No. 58, Austin, TX, USA, 18–22 June 2017. ISBN: 978-1-4503-4927-7
Zheng, Y., Meng, Y., Jin, Y.: Object recognition using neural networks with bottom-up and top-down pathways. Neurocomputing 74, 3158–3169 (2011)
Zheng, Y., Meng, Y., Jin, Y.: Fusing bottom-up and top-down pathways in neural networks for visual object recognition. In: Proceedings of the International Joint Conference on Neural Networks, pp. 1–8 (2010). https://doi.org/10.1109/ijcnn.2010.5596497
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Gupta, V., Sunita, Singh, J.P. (2019). Study and Analysis of Back-Propagation Approach in Artificial Neural Network Using HOG Descriptor for Real-Time Object Classification. In: Ray, K., Sharma, T., Rawat, S., Saini, R., Bandyopadhyay, A. (eds) Soft Computing: Theories and Applications. Advances in Intelligent Systems and Computing, vol 742. Springer, Singapore. https://doi.org/10.1007/978-981-13-0589-4_5
Download citation
DOI: https://doi.org/10.1007/978-981-13-0589-4_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-0588-7
Online ISBN: 978-981-13-0589-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)