Abstract
In comparison to human vision, it’s hard for systems to understand images and figure them out on their own. In the modern world, image processing is mostly done by convolutional neural networks that have been learned over time. As a result, our system categorizes real-time natural colour photographs using deep learning. In the majority of convolutional networks, the activation function is often a form of the rectified linear unit, which is prone to vanishing and exploding gradient problems. Though numerous studies have proposed solutions for resolving this issue, there has yet to be an efficient and feasible approach. To overcome this issue in our method, we combined Rectified Linear Unit (ReLU) variations without altering the activation functions or adding more layers. There are 12 hidden layers in the proposed network, and ten separate image categories were made from the CIFAR10 data set. In the experiment, we got 89.13 percent accuracy which is best when we compared our model to Alex net, Google net, and Resnet18. This shows that our model is better than convolutional neural networks with rectified linear units at categorizing natural pictures.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig7_HTML.png)
(Source: Google Images)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig13_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig14_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig15_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15631-3/MediaObjects/11042_2023_15631_Fig16_HTML.png)
Similar content being viewed by others
Data availability
CIFAR-10 Matlab version dataset is used in this work and accessed from the link https://www.cs.toronto.edu/~kriz/cifar.html for comparison of the proposed work Imagenet dataset is also used.
Code availability
Use our own code with Matlab 2022a software in Windows 10 OS and compared with state of art networks like Alex net, Google net and Resnet18.
References
Ba JL, Kiros JR, Hinton GE (2016) Layer Normalization, Machine Learning. https://doi.org/10.48550/ar**v.1607.06450
Bharadi V, Panchbhai MN, Mukadam AI, Rode NN (2017) Image classification using deep learning. Int J Eng Res Technol 6(11):17–19
Bryson AE, Ho YC, Siouris GM (1979) Applied optimal control: optimization, estimation and control. IEEE Trans Syst Man Cybern 9(6):366–368. https://doi.org/10.1109/TSMC.1979.4310229
Cireşan D, Meier U, Masci J, Gambardella LM, Schmidhuber J (2011) Flexible, High performance convolutional neural networks for image classification, in Proc. 22nd international joint conference on Artificial Intelligence, Barcelona, Catalonia, Spain, 1237–1242. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-210
Diwakar M, Kumar P (2019) Wavelet Packet Based CT Image Denoising Using Bilateral Method and Bayes Shrinkage Rule, in Handbook of Multimedia Information Security: Techniques and Applications, A. K. Singh and A. Mohan, Eds. Cham: Springer International Publishing. 501–511. https://doi.org/10.1007/978-3-030-15887-3_24
Diwakar M, Kumar M (2018) A review on CT image noise and its denoising. Biomed Signal Process Control 42:73–88. https://doi.org/10.1016/j.bspc.2018.01.010
Diwakar M, Kumar P, Singh AK (2020) CT image denoising using NLM and its method noise thresholding. Multimed Tools Appl 79(21):14449–14464. https://doi.org/10.1007/s11042-018-6897-1
Diwakar M, Singh P (2020) CT image denoising using multivariate model and its method noise thresholding in non-subsampled shearlet domain. Biomed Signal Process Control 57:101754. https://doi.org/10.1016/j.bspc.2019.101754
Diwakar M, Sonam, and Kumar M (2015) CT image denoising based on complex wavelet transform using local adaptive thresholding and Bilateral filtering, in Proceedings of the Third International Symposium on Women in Computing and Informatics, New York, NY, USA. 297–302. https://doi.org/10.1145/2791405.2791430
Diwakar M, Verma A, Lamba S, Gupta H (2019) Inter- and Intra-scale Dependencies-Based CT Image Denoising in Curvelet Domain: Proceedings of SoCTA 2017. 343–350. https://doi.org/10.1007/978-981-13-0589-4_32
Elangovan P, Nath MK (2020) Glaucoma Assessment from Color Fundus Images using Convolutional Neural Network. International Journal of Imaging Systems and Technology 31(02):955–971. https://doi.org/10.1002/ima.22494
Hao W, Yizhou W, Yaqin L, Zhili S (2020) The Role of Activation Function in CNN, in Proc. 2nd IEEE International Conference on Information Technology and Computer Application. https://doi.org/10.1109/ITCA52113.2020.00096
He K, Zhang X, Ren S, Sun J (2015) Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, in Proc. 2015 IEEE International Conference on Computer Vision. https://doi.org/10.1109/ICCV.2015.123
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto A, Adam H, (2017) MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, in Proc. IEEE International Conference on Computer Vision and Pattern Recognition. https://doi.org/10.48550/ar**v.1704.04861
Ioffe S, Szegedy C (2015) Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, in Proc. 32nd International Conference on International Conference on Machine Learning, 37:448–456. http://proceedings.mlr.press/v37/ioffe15.pdf. Accessed 26 April 2022
Juneja M, Vedaldi A, Jawahar CV, Zisserman A (2013) Blocks that shout: Distinctive parts for scene classification, in Proc. IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA. 923–930. https://doi.org/10.1109/CVPR.2013.124
Kar MK, Nath MK, Neog DR (2021) A Review on Progress in Semantic Image Segmentation and Its Application to Medical Images, SN Computer Science, Springer Nature 2:397. https://doi.org/10.1007/s42979-021-00784-5
Kohonen T (1988) An introduction to neural computing. Neural Netw-Elsevier 1(1):3–16. https://doi.org/10.1016/0893-6080(88)90020-2
Krishna MM, Neelima M, Harshali M, Rao MVG (2018) Image classification using deep learning. Int J Eng Technol 7(2): 614–617. https://www.sciencepubco.com/index.php/ijet/article/view/10892. Accessed 10 May 2023
Krizhevsky A (2010) Convolutional deep belief networks on CIFAR-10, Department of Computer Science, University of Toronto. https://www.cs.toronto.edu/~kriz/conv-cifar10-aug2010.pdf. Accessed 10 May 2023
Laavanya M, Vijayaraghavan V (2020) Residual Learning of Transfer Learned Alex Net for Image Denoising. IEIE Trans Smart Process Comput 9(2):135–141. https://doi.org/10.5573/IEIESPC.2020.9.2.135
Laavanya M, Vijayaraghavan V (2021) Image Denoising with Convolution Neural Network using Gaussian Filtered Residuals. IEIE Trans Smart Process Comput 10(2):96–100. https://doi.org/10.5573/IEIESPC.2021.10.2.096
LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Back propagation applied to handwritten zip code recognition. IEEE J Neural Comput 1(4):541–551. https://doi.org/10.1162/neco.1989.1.4.541
Lee H, Grosse R, Ranganath R, Ng AY (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations, in Proc. 26th ACM Annual International Conference on Machine Learning, Montreal, Quebec, Canada, 609–616. https://doi.org/10.1145/1553374.1553453
Li W, Wu G, Zhang F, Du Q (2017) Hyper spectral image classification using deep pixel-pair features. IEEE Trans Geosci Remote Sens 55(2):844–853. https://doi.org/10.1109/TGRS.2016.2616355
Lin G, Shen W (2018) Research on convolutional neural network based on improved Relu piecewise activation function. Procedia Comput Sci 131:977–984. https://doi.org/10.1016/j.procs.2018.04.239
Lu C-T, Chen R-H, Wang L-L, Lin J-A (2020) Image enhancement using convolutional neural network to identify similar patterns. IET Image Processing 14(15):3880–3889. https://doi.org/10.1049/iet-ipr.2020.0560
Maas AL, Awni HY, Andrew NY (2013) Rectifier nonlinearities improve neural network acoustic models, in Proc. ICML Workshop on Deep Learning for Audio, Speech, and Language Processing, 1–9. https://awnihannun.com/papers/relu_hybrid_icml2013_final.pdf. Accessed 10 May 2023
Mitchell TM (1997) Machine Learning, 1st edn. McGraw-Hill Inc, New York
Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines, in Proc. 27th International Conference on International Conference on Machine Learning, Haifa, Israel, 807–814. https://www.cs.toronto.edu/~fritz/absps/reluICML.pdf. Accessed 10 May 2023
Ramprasath M, Anand MV, Hariharan S (2018) Image classification using convolutional neural networks, Int. J Pure Appl Math 119(17):1307–1319. https://www.acadpubl.eu/hub/2018-119-17/4/419.pdf. Accessed 10 May 2023
Rawat W, Wang Z (2017) Deep convolutional neural networks for image classification: A comprehensive review. Neural Comput 29:2352–2449. https://doi.org/10.1162/NECO_a_00990
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Int J Sci Nature 323:533–536
Sharif M, Kausar A, Park J, Shin DR (2019) Tiny image classification using four-block convolutional neural network, in Proc. 2019 International Conference on Information and Communication Technology Convergence. https://doi.org/10.1109/ictc46691.2019.8940002
Simard PY, Steinkraus D, Platt JC (2003) Best practices for convolutional neural networks applied to visual document analysis, in Proc. 7th IEEE International Conference on Document Analysis and Recognition, Edinburgh, UK 2: 958–963. https://doi.org/10.1109/ICDAR.2003.1227801
Uk I (2017) A Review on Image Enhancement Techniques. Int J Eng Appl Comput Sci IJEACS 02:232–235. https://doi.org/10.24032/ijeacs/0207/05
Vijayaraghavan V, Laavanya M (2019) Vehicle classification and detection using deep learning. Int J Eng Adv Technol 9(1S5):24–28. https://doi.org/10.35940/ijeat.A1006.1291S52019
Werbos PJ (1974) Beyond regression: New tools for prediction and analysis in the behavioral sciences, Ph. D. Dissertation, University of Harvard, Washington, USA
Wu Y, He K (2018) Group Normalization, Facebook AI Research, in proc. European Conference on Computer Vision. https://openaccess.thecvf.com/content_ECCV_2018/papers/Yuxin_Wu_Group_Normalization_ECCV_2018_paper.pdf. Accessed 26 April 2022
Zheng H, Jiaojiao Z, Yun G (2021) Handling Vanishing Gradient Problem Using Artificial Derivative. IEEE J Mag 9:22371–22377. https://doi.org/10.1109/ACCESS.2021.3054915
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
There is no conflict of interest with any person or body regarding this work.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Veeramani, V., Mohan, L. Image category classification using 12-Layer deep convolutional neural network. Multimed Tools Appl 83, 4017–4036 (2024). https://doi.org/10.1007/s11042-023-15631-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15631-3