Abstract
Image classification refers to the classification of the input image according to some algorithms. The general steps of image classification include image preprocessing, image feature extraction and image classification judgment. Convolutional neural network (CNN) imitates the visual perception mechanism of biology, solves the complicated engineering of traditional manual feature extraction, and realizes automatic feature extraction from data. However, CNN still has the disadvantages of low efficiency and incomplete feature extraction. In this paper, we propose a depthwise separable squeeze-and-excitation based on multi-feature fusion (DSSEMFF) for image classification. Through feature fusion of multiple models, the network can learn the input features with different levels of images, increase feature complementarity and improve feature extraction ability. By adding the attention module, the network can pay more attention to the targeted area and reduce irrelevant background interference information. Finally, we conduct experiments with other state-of-the-art classification methods, the accuracy is higher than 90% and the error rate is lower than 18% the results show that the effectiveness of the proposed method obtains the better effect.
Similar content being viewed by others
References
Yin, S., Zhang, Ye., & Karim, S. (2018). Large Scale Remote Sensing Image Segmentation Based on Fuzzy Region Competition and Gaussian Mixture Model[J]. IEEE Access., 6, 26069–26080.
Swathi, R., & Srinivas, A. (2020). An Improved Image Registration Method Using E-SIFT Feature Descriptor with Hybrid Optimization Algorithm[J]. Journal of the Indian Society of Remote Sensing, 48(2), 215–226.
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe: Curran Associates, 2012. 1097–1105.
Shin, H. C., Roth, H. R., Gao, M., et al. (2016). Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning[J]. IEEE Transactions on Medical Imaging, 35(5), 1285–1298.
Yang, X., & Zhang, H. (2020). Art image classification with double kernel squeeze-and-excitation neural network[J]. Journal of Image and Graphics, 25(05), 0967–0976.
He KM, Zhang XY, Ren SQ, et al. Identity mappings in deep residual networks. 14th European Conference on ComputerVision. Amsterdam: Springer, 2016. 630–645.
Zagoruyko s, Komodakis N. Wide residual networks.Proceedings of the British Machine Vision Conference(BMVC). York: BMVA Press, 2016. 1–87.
Zhao S, David K, Simon B, et al. Enhancing the Appreciation of Traditional Chinese Painting Using Interactive Technology[J]. Multimodal Technologies & Interaction, 2018, 2(2):16-.
Zhao, S. (2019). An Analysis of Interactive Technology’s Effect on the Appreciation of Traditional Chinese Painting: A Review of Case Studies[J]. The International Journal of New Media, Technology and the Arts, 14(3), 1–12.
Jia Li and J. Z. Wang, "Studying digital imagery of ancient paintings by mixtures of stochastic models," in IEEE Transactions on Image Processing, vol. 13, no. 3, pp. 340–353, March 2004, doi: https://doi.org/10.1109/TIP.2003.821349.
Li, G., Ji, Z., Chang, Y., et al. (2021). ML-ANet: A Transfer Learning Approach Using Adaptation Network for Multi-label Image Classification in Autonomous Driving[J]. Chinese Journal of Mechanical Engineering, 34(1), 1–11.
Wang X, Chen H, Xiang H, et al. Deep Virtual Adversarial Self-training with Consistency Regularization for Semi-supervised Medical Image Classification[J]. Medical Image Analysis, 2021, 70(6):102010.
Lin, C. J., Lin, C. H., & Wang, S. H. (2021). Integrated Image Sensor and Light Convolutional Neural Network for Image Classification[J]. Mathematical Problems in Engineering, 2021, 1–7.
Xu Y, Yu X, Wang T, et al. Pooling region learning of visual word for image classification using bag-of-visual-words model[J]. PLOS ONE, 2020, 15.
Shen, J. (2009). Stochastic modeling western paintings for effective classification[J]. Pattern Recognition, 42(2), 293–301.
Ye Liang, Hong Bao and Hong-Zhe Liu, "A simple method for classification of traditional Chinese Painting and Calligraphy images," 2010 International Conference on Educational and Information Technology, 2010, pp. V3–340-V3–344, doi: https://doi.org/10.1109/ICEIT.2010.5608356.
Wang, Z., Sun, M., Han, Y., et al. (2013). Supervised Heterogeneous Sparse Feature Selection for Chinese Paintings Classification[J]. Journal of Computer-Aided Design and Computer Graphics, 25(12), 1848–1855.
Jiang S Q, Huang Q M. Ye QX and Gao W. An effective method to detect and categorize digitized traditional Chinese paintings. Pattern Recognition Letters, 27(7): 734–746, 2006.
Liong, S., Huang, Y., Li, S., et al. (2020). Automatic traditional Chinese painting classification: A benchmarking analysis[J]. Computational Intelligence, 36(3), 1183–1199.
Sun J, Frishman D. DeepHelicon: Accurate prediction of inter-helical residue contacts in transmembrane proteins by residual neural networks[J]. Journal of Structural Biology, 2020, 212(1):107574.
Gupta S, Patil A T, Purohit M, et al. Residual Neural Network precisely quantifies dysarthria severity-level based on short-duration speech segments[J]. Neural Networks, 2021, 139(6).
Khan Z Y, Niu Z. CNN with Depthwise Separable Convolutions and Combined Kernels for Rating Prediction[J]. Expert Systems with Applications, 2020, 170(5):114528.
Xia X, Cui X, Bing N. Inception-v3 for flower classification[C]// 2017 2nd International Conference on Image, Vision and Computing (ICIVC). IEEE, 2017.
Liu Y, Miao C, Ji J, et al. MMF: A Multi-scale MobileNet based Fusion Method for Infrared and Visible Image[J]. Infrared Physics & Technology, 2021(3):103894.
Gao, H. Li, and S. Yin. Adaptive Convolutional Neural Network-based Information Fusion for Facial Expression Recognition [J]. International Journal of Electronics and Information Engineering. Vol. 13, No. 1, pp. 17–23, 2021.
Yin, S., Li, H. & Teng, L. Airport Detection Based on Improved Faster RCNN in Large Scale Remote Sensing Images [J]. Sensing and Imaging, vol. 21, 2020. https://doi.org/10.1007/s11220-020-00314-2
Wang, X., Yin, S., Sun, K., et al. (2020). GKFC-CNN: Modified Gaussian Kernel Fuzzy C-means and Convolutional Neural Network for Apple Segmentation and Recognition [J]. Journal of Applied Science and Engineering, 23(3), 555–561.
Li, F. F., Fergus, R., & Perona, P. (2006). One-shot learning of object categories. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(4), 594–611.
Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images. Handbook of Systemic Autoimmune Diseases, 2009, 1(4).
Acknowledgements
Key Scientific Research Project of Higher Education in Henan Province, Education Science and Technology (2021) No. 383. Project Number: 22B510016. Project name: Air quality monitoring system based on LoRa spread spectrum modulation technology.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, J., Zhang, J. DSSEMFF: A Depthwise Separable Squeeze-and-excitation Based on Multi-feature Fusion for Image Classification. Sens Imaging 23, 16 (2022). https://doi.org/10.1007/s11220-022-00383-5
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11220-022-00383-5