Abstract
For the customary classification algorithms, performance depends on feature extraction methods. However, it is challenging to extract such unique features. With the advancement of Convolutional Neural Networks (CNN), which is the widely used Deep Learning Framework, there seems to be a substantial improvement in classification performance combined with implicit feature extraction process. But, training a CNN is an intensive process that often needs high computing machines (GPU) and may take hours or even days. This may confine its application in a few situations. Considering these factors, an ensemble architecture is modelled, that is trained on a subset of mutually exclusive classes, grouped by Hierarchical Agglomerative Clustering based on similarity. A new Probabilistic Ensemble-Based Classifier is designed for classifying an image. This new model is trained in comparatively lesser time with classification accuracy comparable to the traditional ensemble model. Also, GPUs are not necessary for training this model, even for large datasets.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Hubel, D.H., Wiesel, T.N.: Receptive elds and functional architecture of monkey striate cortex. J. Physiol. 195(1), 215 (1968)
Nithin, D.K., Sivakumar, P.B.: Generic feature learning in computer vision. Procedia Comput. Sci. 58, 202–209 (2015)
Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)
John, S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.C., Boser enker, B., Lawrence, D.: Handwritten digit recognition with a back-propagation network. In: Advances in Neural Information Processing Systems. Citeseer (1990)
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)
Fei-Fei, L., Berg, A., Deng, J.: Large Scale Visual Recognition Challenge (2010)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: ECCV, pp. 818–833. Springer (2014)
Matthew D Zeiler, Graham W Taylor, and Rob Fergus. Adaptive deconvolutional networks for mid and high level feature learning. In: 2011 ICCV, pp. 2018–2025. IEEE (2011)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv:1409.1556
Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning (2016). arXiv:1602.07261
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). arXiv:1512.03385
Kumar, K., Sachin, S., Anil, R.M., Soman, K.P.: Convolutional neural networks for the recognition of malayalam characters. In: FICTA 2014, pp. 493–500. Springer (2015)
Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: Advances in Neural Information Processing Systems, pp. 545–552 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Neena, A., Geetha, M. (2018). Image Classification Using an Ensemble-Based Deep CNN. In: Sa, P., Bakshi, S., Hatzilygeroudis, I., Sahoo, M. (eds) Recent Findings in Intelligent Computing Techniques . Advances in Intelligent Systems and Computing, vol 709. Springer, Singapore. https://doi.org/10.1007/978-981-10-8633-5_44
Download citation
DOI: https://doi.org/10.1007/978-981-10-8633-5_44
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-8632-8
Online ISBN: 978-981-10-8633-5
eBook Packages: EngineeringEngineering (R0)