Abstract
Multi-view images represent the target object from multiple perspectives. Learning the target object information from different viewpoints helps to improve the accuracy of multi-view images classification. We propose a multi-view recognition method (SCNN-a) based on shallow convolutional neural network. In order to improve the generalization capability and classification performance of model, we develop a new multi-view images classification method (SCNN), which adds Dropout (after each max-pooling layer) technology to SCNN-a. SCNN-a and SCNN regard the images from predefined views as latent variables, and extract the high-order features of multi-view images with two convolutional layers. Experimental results show that SCNN achieves similar accuracy to the state-of-the-art result of [7] with less layers and time complexity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arsalan Soltani, A., Huang, H., Wu, J., Kulkarni, T.D., Tenenbaum, J.B.: Synthesizing 3D shapes via modeling multi-view depth maps and silhouettes with deep generative networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1511–1519 (2017)
Arvind, V., Costa, A., Badgeley, M., Cho, S., Oermann, E.: Wide and deep volumetric residual networks for volumetric image classification. arXiv preprint arXiv:1710.01217 (2017)
Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291–7299 (2017)
Dominguez, M., Dhamdhere, R., Petkar, A., Jain, S., Sah, S., Ptucha, R.: General-purpose deep point cloud feature extractor. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1972–1981. IEEE (2018)
Dominguez, M., Such, F.P., Sah, S., Ptucha, R.: Towards 3D convolutional neural networks with meshes. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3929–3933. IEEE (2017)
Garcia-Garcia, A., Gomez-Donoso, F., Garcia-Rodriguez, J., Orts-Escolano, S., Cazorla, M., Azorin-Lopez, J.: Pointnet: a 3D convolutional neural network for real-time object class recognition. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp. 1578–1584. IEEE (2016)
Han, Z., Shang, M., Liu, Y.S., Zwicker, M.: View inter-prediction GAN: unsupervised representation learning for 3D shapes by learning global shape memories to support local view predictions. arXiv preprint arXiv:1811.02744 (2018)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)
Kanezaki, A., Matsushita, Y., Nishida, Y.: RotationNet: joint object categorization and pose estimation using multiviews from unsupervised viewpoints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5010–5019 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Lei, F.Y., Cai, J.: EIWCS: characterizing edges importance to weaken community structure. In: Applied Mechanics and Materials, vol. 556, pp. 6054–6057. Trans Tech Publ (2014)
Lei, F., Cai, J., Dai, Q., Zhao, H.: Deep learning based proactive caching for effective WSN-enabled vision applications. Complexity 2019, 12 p. (2019)
Lei, F.Y., Dai, Q.Y., Cai, J., Zhao, H.M., Liu, X., Liu, Y.: A Proactive Caching Strategy Based on Deep Learning in EPC of 5G. In: Ren, J., Hussain, A., Zheng, J., Liu, C.-L., Luo, B., Zhao, H., Zhao, X. (eds.) BICS 2018. LNCS (LNAI), vol. 10989, pp. 738–747. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00563-4_72
Liu, S., Giles, L., Ororbia, A.: Learning a hierarchical latent-variable model of 3D shapes. In: 2018 International Conference on 3D Vision (3DV), pp. 542–551. IEEE (2018)
Ma, C., Guo, Y., Lei, Y., An, W.: Binary volumetric convolutional neural networks for 3-D object recognition. IEEE Trans. Instrum. Meas. 99, 1–11 (2018)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)
Ren, J., Wang, D., Jiang, J.: Effective recognition of MCCS in mammograms using an improved neural classifier. Eng. Appl. Artif. Intell. 24(4), 638–645 (2011)
Ren, J., Xu, M., Orwell, J., Jones, G.A.: Multi-camera video surveillance for real-time analysis and reconstruction of soccer games. Mach. Vis. Appl. 21(6), 855–863 (2010)
Simonovsky, M., Komodakis, N.: Dynamic edge-conditioned filters in convolutional neural networks on graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3693–3702 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Solli, M., Bergstrom, S.: Image retrieval and processing systems and methods, US Patent App. 10/180,950, 15 Jan 2019
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE international conference on computer vision. pp. 945–953 (2015)
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 945–953 (2015)
Wang, Z., Ren, J., Zhang, D., Sun, M., Jiang, J.: A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos. Neurocomputing 287, 68–83 (2018)
Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: Advances In Neural Information Processing Systems, pp. 82–90 (2016)
Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3D ShapeNets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912–1920 (2015)
Xu, X., Todorovic, S.: Beam search for learning a deep convolutional neural network of 3D shapes. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 3506–3511. IEEE (2016)
Yan, Y., et al.: Unsupervised image saliency detection with gestalt-laws guided optimization and visual attention based refinement. Pattern Recogn. 79, 65–78 (2018)
Zanuttigh, P., Minto, L.: Deep learning for 3D shape classification from multiple depth maps. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3615–3619. IEEE (2017)
Zhang, A., Sun, G., Ren, J., Li, X., Wang, Z., Jia, X.: A dynamic neighborhood learning-based gravitational search algorithm. IEEE Trans. Cybern. 48(1), 436–447 (2016)
Zheng, J., Liu, Y., Ren, J., Zhu, T., Yan, Y., Yang, H.: Fusion of block and keypoints based approaches for effective copy-move image forgery detection. Multidimension. Syst. Sig. Process. 27(4), 989–1005 (2016)
Acknowledgment
This research was funded by the Scientific and Technological Projects of Guangdong Province grant number (2017A050501039), the Guangdong Province General Colleges and Universities Featured Innovation grant number (2015GXJK080), the Qingyuan Science and Technology Plan Project grant number (170809111721-249, 170802171710591), and the Scientific and Technological Projects of Guangdong Province (2019A070701013).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Lei, F., Liu, X., Dai, Q., Zhao, H., Wang, L., Zhou, R. (2020). A Multi-view Images Classification Based on Shallow Convolutional Neural Network. In: Ren, J., et al. Advances in Brain Inspired Cognitive Systems. BICS 2019. Lecture Notes in Computer Science(), vol 11691. Springer, Cham. https://doi.org/10.1007/978-3-030-39431-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-39431-8_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-39430-1
Online ISBN: 978-3-030-39431-8
eBook Packages: Computer ScienceComputer Science (R0)