Fine-grained Image Classification using Convolutional Neural Network and Support Vector Machine

Tao Lin

¹ School of Computer Science & Infomation Enineering, Shanghai Institute of Technology, Shanghai, China

*Corresponding author

Although vast neural network models can classify images, sub-classification for each image class requires retraining the exisiting model with new fine-grained data, subject to high training cost and uncertain classification accuracy. To solve the aforementioned problems, a method using Convolution Neural Network and Support Vector Machine is proposed, where the former extracts general features from images for sub-classification while the latter categorizes these features. The method can be rapidly deployed in most Internet of Things systems to identify various targets; its effectiveness in reducing training cost and improving classification accuracy is verified through experiments.

Fine-grained image classification, feature extraction, convolutional neural network, support vector machine, face classification, IoT

Yu Shi, Tao Lin, Wei He, Biao Chen, Ruixia Wang, Nan Jiang, Yabo Zhang (2022). Fine-grained Image Classification using Convolutional Neural Network and Support Vector Machine. Journal of Networking and Network Applications, Volume 2, Issue 2, pp. 86–94. https://doi.org/10.33969/J-NaNA.2022.020204.

[1] D. Anguita and A. Boni, “Improved neural network for svm learning,” IEEE Trans Neural Netw, vol. 13, no. 5, pp. 1243–1244, 2002.

[2] J. Tsiligaridis, “Classification with neural network and svm via decision tree algorithm,” in MATHEMATICAL METHODS AND COMPUTATIONAL TECHNIQUES IN SCIENCE AND EN-GINEERING II, 2018.

[3] T. M. Hamdani, A. M. Alimi, and M. A. Khabou, “An iterative method for deciding svm and single layer neural network struc-tures,” Neural Processing Letters, vol. 33, no. 2, pp. 171–186, 2011. 

[4] G. Gao and M. W ¨uthrich, “Convolutional neural network classi-fication of telematics car driving data,” Risks, vol. 7, no. 1, 2019.

[5] F. Lei, X. Liu, Q. Dai, and W. K. Ling, “Shallow convolutional neural network for image classification,” SN Applied Sciences, vol. 2, no. 1, 2020.

[6] A. Mahmood, M. Bennamoun, S. An, F. A. Sohel, F. Boussaid,

R. Hovey, G. A. Kendrick, and R. B. Fisher, “Deep image repre-sentations for coral image classification,” IEEE Journal of Oceanic Engineering, vol. 44, no. 1, pp. 121–131, 2019.

[7] Z. Ge, C. McCool, C. Sanderson, and P. Corke, “Modelling local deep convolutional neural network features to improve fine-grained image classification,” in 2015 IEEE International Conference on Image Processing (ICIP), pp. 4112–4116, IEEE, 2015.

[8] E. Deniz, A. S¸eng ¨ur, Z. Kadiro˘glu, Y. Guo, V. Bajaj, and ¨U. Budak, “Transfer learning based histopathologic image classification for breast cancer detection,” Health information science and systems, vol. 6, no. 1, pp. 1–7, 2018.

[9] F. Demir, A. Sengur, and V. Bajaj, “Convolutional neural networks based efficient approach for classification of lung diseases,” Health information science and systems, vol. 8, no. 1, pp. 1–8, 2020.

[10] D. Yu and Y. Gu, “A machine learning method for the fine-grained classification of green tea with geographical indication using a mos-based electronic nose,” Foods, vol. 10, no. 4, p. 795, 2021. 

[11] M. A. Ebrahimi, M. H. Khoshtaghaza, S. Minaei, and B. Jamshidi, “Vision-based pest detection based on svm classification method,” Computers and Electronics in Agriculture, vol. 137, p. 52–58, 2017.

[12] Y. Xu, Z. Chen, X. Xiang, and J. Meng, “An energy-efficient parallel vlsi architecture for svm classification,” Ieice Electronics Express, vol. 15, no. 7, pp. 20180099–20180099, 2018.

[13] K. Raju, N. Sandhya, and R. Mehra, “Supervised svm classifi-cation of rainfall datasets,” Indian Journal of ence and Technology, vol. 10, no. 15, pp. 1–6, 2017.

[14] Hinton, E. G., Salakhutdinov, and R. R., “Reducing the dimen-sionality of data with neural networks.,” Science, 2006.

[15] M. J. Cannon, A. M. Keller, C. A. Thurlow, A. Perez-Celis, and M. J. Wirthlin, “Improving the reliability of tmr with non-triplicated i/o on sram fpgas,” IEEE Transactions on Nuclear Sci-ence, vol. PP, no. 99, pp. 1–1, 2019.

[16] K. T. Ahmed, Shahida, and M. A. Iqbal, “Content based image retrieval using image features information fusion,” Information Fusion, 2018.

[17] A. Sengupta, Y. Ye, R. Wang, C. Liu, and K. Roy, “Going deeper in spiking neural networks: Vgg and residual architectures,” arXiv

e- prints, 2018.

[18] D. Laptev, N. Savinov, J. M. Buhmann, and M. Pollefeys, “Ti-pooling: transformation-invariant pooling for feature learning in convolutional neural networks,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

[19] P. Oza and V. M. Patel, “One-class convolutional neural network,” IEEE Signal Processing Letters, vol. 26, no. 2, pp. 277–281, 2019.

[20] E. Chen, X. Wu, C. Wang, and Y. Du, “Application of improved convolutional neural network in image classification,” in 2019 International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), 2019.

[21] L. Windrim, A. Melkumyan, R. J. Murphy, A. Chlingaryan, and

R. Ramakrishnan, “Pretraining for hyperspectral convolutional neural network classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. PP, no. 99, pp. 1–13, 2017.

[22] P. Latorre-Carmona, V. J. Traver, J. S´anchez, and E. Tajahuerce, “Online reconstruction-free single-pixel image classification,” Im-age & Vision Computing, 2019.

[23] J. M. Haut, M. E. Paoletti, J. Plaza, A. Plaza, and J. Li, “Visual attention-driven hyperspectral image classification,” IEEE Trans-actions on Geoence and Remote Sensing, vol. 57, no. 99, pp. 8065–8080, 2019.