Abstract
Convolutional neural networks (CNN) with deep architectures have paved way for immense opportunities where any complex mechanism can be undertaken and analyzed. The main drawback of all such architectures is their high number of trainable parameters. This increases its complexity and makes it difficult for real-time processing. We suggest in this paper a multi-channel-based design with shallow layers that can efficiently be trained and tested with less complexity as compared to the existing deep architectures. The performance is achieved by using the concept of a side channel with a main channel. The main concentration is to reduce the parameters to be trained as much as possible with slight compromise in the accuracy. Different values of filter sizes are given, and the output accuracy was observed for different cases. The proposed network was tested on a brain tumor-type database, and it successfully classified the images comprising of meningioma and pituitary tumor. The entire network performance is evaluated by comparing it with two deep architectures known as AlexNet and VGG16. The results show a huge drop in the number of parameters to be trained with much less execution time and comparable accuracy.
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
Similar content being viewed by others
References
Y. Lecun, Y. Bengio, G. Hinton, Deep learning. Nature 521(7553), 436–444 (2015)
S. Deepak, P.M. Ameer, Brain tumor classification using deep CNN features via transfer learning. Comput. Biol. Med. 111, 103345 (2019)
Z.N.K. Swati et al., Brain tumor classification for MR images using transfer learning and fine-tuning. Comput. Med. Imaging Graph. 75, 34–46 (2019)
H. Wang, P. Chen, S. Kwong, Building correlations between filters in convolutional neural networks. IEEE Trans. Cybern. 47(10), 3218–3229 (2017)
H. Li, A. Kadav, I. Durdanovic, H. Samet, H.P. Graf, Pruning Filters for Efficient ConvNets (2016), no. 2016, pp. 1–13
C.T. Liu et al., Computation-performance optimization of convolutional neural networks with redundant filter removal. IEEE Trans. Circ. Syst. I Regul. Pap. 66(5), 1908–1921 (2019)
C.F. Chen, G.G. Lee, V.Sritapan, C.Y. Lin, Deep convolutional neural network on iOS mobile devices (Invited Paper), in International Workshop on Signal Processing Systems SiPS Design Implement. (2016), pp. 130–135
M. R. Islam and N. Rishad, “Effects of filter on the classification of brain MRI image using convolutional neural network, in 4th International Conference on Electrical Engineering and Information & Communication Technology (iCEEiCT) 2018, pp. 489–494 (2019)
T. Sinha, B. Verma, A. Haidar, Optimization of convolutional neural network parameters for image classification, in IEEE Symposium Series on Computational Intelligence SSCI 2017—Proc., vol. 2018 (2018), pp. 1–7
J. Jiang, X. Feng, F. Liu, Y. Xu, H. Huang, Multi-spectral RGB-NIR image classification using double-channel CNN. IEEE Access 7, 20607–20613 (2019)
P. Barros, S. Magg, C. Weber, S. Wermter, A multichannel convolutional neural network for hand posture recognition, in Lecture Notes Computer Science (including Subseries Lecture Notes Artificial Intelligence Lecture Notes Bioinformatics), vol. 8681 LNCS, no. Icann, pp. 403–410 (2014)
D. Hamester, P. Barros, S. Wermter, Face expression recognition with a 2-channel convolutional neural network, in Proceedings of International Joint Conference Neural Networks (2015)
A. Krizhvesky, I. Sutsekever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, in Handbook Approximation Algorithms Metaheuristics (2007), pp. 45-1–45-16
S. Tammina, Transfer learning using VGG-16 with deep convolutional neural network for classifying images. Int. J. Sci. Res. Publ. 9(10), 143–150 (2019)
Brain tumor dataset. Accessed date July 2019. https://figshare.com/articles/brain_tumor_dataset/1512427
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kesav, N., Jibukumar, M.G. (2021). Complexity Reduced Bi-channel CNN for Image Classification. In: Joshi, A., Khosravy, M., Gupta, N. (eds) Machine Learning for Predictive Analysis. Lecture Notes in Networks and Systems, vol 141. Springer, Singapore. https://doi.org/10.1007/978-981-15-7106-0_12
Download citation
DOI: https://doi.org/10.1007/978-981-15-7106-0_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-7105-3
Online ISBN: 978-981-15-7106-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)