Open Access Open Access  Restricted Access Subscription or Fee Access

Classification of Objects with Occlusions by Means of a DAG-CNN


(*) Corresponding author


Authors' affiliations


DOI: https://doi.org/10.15866/ireaco.v11i6.15737

Abstract


In the following paper, the training of a Convolutional Neural Network (CNN) type DAG (Directed Acyclic Graph) that classifies 5 tools: scalpel, pliers, scissor, screwdriver and spanner, with a 99.8% accuracy is presented, in order to perform a classification process under unexpected conditions, such as the presence of occlusions, where the visualization of activations of the convolution layers of the network allows to analyze the reasons why the network correctly or incorrectly classifies each image, for cases with different percentages of occlusion on each one of the trained categories. Subsequently, a solution for the classification of occluded objects is proposed, and a new DAG-CNN is trained, with a 99% accuracy, in order to evaluate the feasibility of the said proposal, and to observe the change of the activations against occluding percentages between 0% and 80%. Finally, the results of both networks are compared and the proposal viability and its right conditions are determined.
Copyright © 2018 Praise Worthy Prize - All rights reserved.

Keywords


DAG-CNN; Occluded Objects; Occlusion Percentages; Activations; Object Classification

Full Text:

PDF


References


A. Krizhevsky, I. Sutskever and G. E. Hinton, Imagenet classification with deep convolutional neural networks, In Advances in neural information processing systems, 2012, pp. 1097-1105.
https://doi.org/10.1145/3065386

O. Bichler, Convolutional neural network, U.S. Patent Application No 15/505,231, 13 July 2017.

P. C. U. Murillo, J. O. P. Arenas and R. J. Moreno, Face Recognition Access Control System using Convolutional Neural Networks, Research Journal of Applied Sciences , 2017, vol. 13, no. 1, pp. 47-53.

K. J. Piczak, Environmental sound classification with convolutional neural networks, 2015 IEEE 25th International Workshop on In Machine Learning for Signal Processing (MLSP). IEEE, 2015, pp. 1-6.
https://doi.org/10.1109/mlsp.2015.7324337

M. Szarvas, A. Yoshizawa, M. Yamamoto andJ. Ogata, Pedestrian detection with convolutional neural networks, In Intelligent vehicles symposium, 2005. Proceedings. IEEE. IEEE, 2005, pp. 224-229.
https://doi.org/10.1109/ivs.2005.1505106

D. C. Ciresan, U. Meier, L. M. Gambardella and J. Schmidhuber, Convolutional neural network committees for handwritten character classification, 2011 International Conference on In Document Analysis and Recognition (ICDAR). IEEE, 2011, pp. 1135-1139.
https://doi.org/10.1109/icdar.2011.229

S. Chaichulee, et al.,Multi-task Convolutional Neural Network for Patient Detection and Skin Segmentation in Continuous Non-contact Vital Sign Monitoring In, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017). IEEE, 2017. pp. 266-272.
https://doi.org/10.1109/fg.2017.41

S. Yang and D. Ramanan, Multi-scale recognition with DAG-CNNs. In 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, 2015, pp. 1215-1223.
https://doi.org/10.1109/iccv.2015.144

J. O. P. Arenas, R. J. Moreno and R. D. H. Beleño, Convolutional Neural Network with a DAG Architecture for Control of a Robotic Arm by Means of Hand Gestures, Contemporary Engineering Sciences, 2018, vol. 11, no. 10, pp. 547-557.
https://doi.org/10.12988/ces.2018.8241

H. Liu, P. Ai and J. Chen, A Systematic Practice of Judging the Success of a Robotic Grasp Using Convolutional Neural Network, In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), 2017, pp. 4959-4960.

J. Mahler, et al., Dex-net 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics, arXiv preprint arXiv:1703.09312, 2017.
https://doi.org/10.15607/rss.2017.xiii.058

J. Redmon and A. Angelova, Real-time grasp detection using convolutional neural networks, In, 2015 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2015,pp. 1316-1322.
https://doi.org/10.1109/icra.2015.7139361

F. J. Chu and P. A. Vela, Deep Grasp: Detection and Localization of Grasps with Deep Neural Networks, arXiv preprint arXiv:1802.00520, 2018.

Benyettou, A., Bennani, Y., Benyettou, A., Bendahmane, A., Cabanes, G., Semi-Supervised Multi-Label Classification Through Topological Active Learning, (2017) International Journal on Communications Antenna and Propagation (IRECAP), 7 (3), pp. 222-232.
https://doi.org/10.15866/irecap.v7i3.12742

Hannane, A., Fizazi, H., Metaheuristics and Neural Network for Satellite Images Classification, (2016) International Review of Aerospace Engineering (IREASE), 9 (4), pp. 107-113.
https://doi.org/10.15866/irease.v9i4.10220

Gupta, K., Gupta, R., Wavelet Based Speckle Filtering of the SAR Images, (2015) International Journal on Information Technology (IREIT), 3 (5), pp. 151-159.

Gherdaoui, S., Fizazi, H., Hybrid Approach for the Detection of Regions of a Satellite Image, (2017) International Review of Aerospace Engineering (IREASE), 10 (3), pp. 114-121.
https://doi.org/10.15866/irease.v10i3.11980

Sayed, S., Shaikh, N., Feature Extracting from Video Encoded for Searching Using Improved Methods, (2017) International Journal on Communications Antenna and Propagation (IRECAP), 7 (6), pp. 545-551.
https://doi.org/10.15866/irecap.v7i6.13612

Z. Xu, Y. Yang, A. G. Hauptmann, A discriminative CNN video representation for event detection, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1798-1807, (2015).
https://doi.org/10.1109/cvpr.2015.7298789

P. C. U. Murillo, J. O. P. Arenas and R. J. Moreno, Implementation of a Data Augmentation Algorithm Validated by Means of the Accuracy of a Convolutional Neural Network, Journal of Engineering and Applied Sciences, 2017, vol. 12, no. 20, pp. 5323-5331.


Refbacks

  • There are currently no refbacks.



Please send any question about this web site to info@praiseworthyprize.com
Copyright © 2005-2024 Praise Worthy Prize