Abstract
The Convolutional Neural Networks (CNNs) have been employed successfully for object identification, behavior analysis, letters and digits recognition, etc. The researchers in computer vision committee have studied the capacity of this model in two directions. The first one is improving its performance by increasing layers of the network, using learned features, more data, or more computing (GPUs). The second one is theoretical understanding in architecture design, in optimization and in a generalization of deep networks. One of the first researches in limitation of CNNs in understudying the semantics of images has done by Hosseini et al. in 2017. This result puts the researchers in CNNs community to do more researches to keep up with proper understanding and continued advances in the fields. This paper also forces on analysis the CNNs capability in understanding semantics information in images by recognizing images of the same shape and semantics but opposite the intensity. Experimental results were done on MNIST and GTSRB dataset indicates the limitation of CNNs in understanding the image semantic.
This research is funded by the Vietnam National University, Hanoi (VNU) under project number QG.18.04.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arnold, R., Miklos, P.: Character recognition using neural networks. In: 11th International Symposium on Computational Intelligence and Informatics (CINTI) (2010)
Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. CoRR, abs/1405.3531 (2014)
Dede, G., Sazli, M.H.: Speech recognition with artificial neural networks 20(3), 763–768 (2010)
Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. CoRR, abs/1311.2524 (2013)
Hauberg, S., Freifeld, O., Larsen, A.B.L., Fisher III, J.W., Hansen, L.K.: Dreaming more data: class-dependent distributions over diffeomorphisms for learned data augmentation. CoRR, abs/1510.02795 (2015)
Hosseini, H., Xiao, B., Jaiswal, M., Poovendran, R.: On the limitation of convolutional neural networks in recognizing negative images. In: Computer Vision and Pattern Recognition (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, NIPS 2012, vol. 1, pp. 1097–1105. Curran Associates Inc., USA (2012)
Li, X., Jie, Z., Feng, J., Liu, C., Yan, S.: Learning with rethinking: recurrently improving convolutional neural networks through feedback. CoRR, abs/1708.04483 (2017)
Lim, C.P., Woo, S.C., Loh, A.S., Osman, R.: Speech recognition using artificial neural networks. In: Proceedings of the First International Conference on Web Information Systems Engineering. IEEE (2000)
Nguyen, K., Fookes, C., Sridharan, S.: Improving deep convolutional neural networks with unsupervised feature learning, pp. 3646–3653 (2015)
Perwej, Y., Chaturvedi, A.: Neural networks for handwritten english alphabet recognition. CoRR, abs/1205.3966 (2012)
Pinheiro, P., Collobert, R., Dollar, P.: Learning to segment object candidates. In: Advances in Neural Information Processing System 28 (2018)
Pradeep, J., Srinivasan, E., Himavathi, S.: Diagonal based feature extraction for handwritten alphabets recognition system using neural network. CoRR, abs/1103.0365 (2011)
Pradeep, J., Srinivasan, E., Himavathi, S.: Neural network based handwritten character recognition system without feature extraction. In: International Conference on Computer, Communication and Electrical Technology (ICCCET) (2011)
Santosh, K.C., Antani, S.: Automated chest x-ray screening: can lung region symmetry help detect pulmonary abnormalities? IEEE Trans. Med. Imaging 37(5), 1168–1177 (2018)
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: integrated recognition, location and detection using convolutional networks. In: The International Conference on Learning Representations (2014)
Shang, W., Sohn, K., Almeida, D., Lee, H.: Understanding and improving convolutional neural networks via concatenated rectified linear units. CoRR, abs/1603.05201 (2016)
Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw. 32, 323–332 (2012)
Suryani, D., Doetsch, P., Ney, H.: On the benefits of convolutional neural network combinations in offline handwriting recognition. In: The 15th International Conference on Frontiers in Handwriting Recognition (2016)
Ukil, S., Ghosh, S., Obaidullah, Sk.Md., Santosh, K.C., Roy, K., Das, N.: Deep learning for word-level handwritten indic script identification. CoRR, abs/1801.01627 (2018)
Wang, N., Li, S., Gupta, A., Yeung, D.: Transformation pursuit for image classification. CoRR, abs/1501.04587 (2015)
Acknowledgements
This research is funded by the Vietnam National University, Hanoi (VNU) under project number QG.18.04.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Do, TH., Anh, N.T.V., Dat, N.T., Santosh, K.C. (2019). Can We Understand Image Semantics from Conventional Neural Networks?. In: Santosh, K., Hegadi, R. (eds) Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2018. Communications in Computer and Information Science, vol 1035. Springer, Singapore. https://doi.org/10.1007/978-981-13-9181-1_45
Download citation
DOI: https://doi.org/10.1007/978-981-13-9181-1_45
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9180-4
Online ISBN: 978-981-13-9181-1
eBook Packages: Computer ScienceComputer Science (R0)