Abstract
Convolutional neural networks (CNN) is one of the most important branches of deep learning, which always shows the excellent performance on image classification via unique convolution operations. However, the generalization ability of CNN is always limited due to lack of the specific guidelines in hidden-layer design, Kernel design and Weight initialization design. In this paper, a new topological design method is proposed by analyzing abstract edge information (called texture) in feature map based on the experimental and numerical analysis. Especially, the prior number of convolution kernels in the first layer and combinatorial optimization of all hidden layers are applied to initialize the entire network topology. The experiments based on the MNIST, Chest X-ray and CTs dataset indicate that (1) Traditional CNN layers with doubling nodes are not essential to optimize the hidden-layer topology because of the texture features that extracted from different datasets. (2) Improved hidden-layer topology of the CNN can outperform the better performance in classification-tasks and improvement up to 30% compared with the benchmark methods.
Graphical Abstract
Similar content being viewed by others
References
Anand R, Shanthi T, Nithish MS, Lakshman S (2020) Face recognition and classification using googlenet architecture. In: Soft computing for problem solving. Springer, Singapore, pp 261–269
Ayachi R, Afif M, Said Y, Atri M (2020) Traffic signs detection for real-world application of an advanced driving assisting system using deep learning. Neural Process Lett 51(1):837–851
Cai K, Miao X, Wang W, Pang H, Liu Y, Song J (2020) A modified yolov3 model for fish detection based on mobilenetv1 as backbone. Aquacult Eng 91:102117
Cohen JP, Morrison P, Dao L, Roth K, Duong TQ, Ghassemi M (2020) Covid-19 image data collection: Prospective predictions are the future. arXiv preprint arXiv:2006.11988
Deng X, Shao H, Shi L, Wang X, Xie T (2020) A classification-detection approach of COVID-19 based on chest x-ray and CT by using keras pre-trained deep learning models. Comput Model Eng Sci 125(2):579–596
Dheir IM, Mettleq ASA, Elsharif AA, Abu-Naser SS (2020) Classifying nuts types using convolutional neural network. Int J Acad Infor Syst Res (IJAISR) 3(12)
El-Khatib MJ, Abu-Nasser BS, Abu-Naser SS (2019) Glass classification using artificial neural network. Int J Acad Pedagogic Res (IJAPR) 3(23)
Farooq M, Hafeez A (2020) Covid-resnet: a deep learning framework for screening of covid19 from radiographs. arXiv preprint arXiv:2003.14395
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR workshop and conference proceedings, pp 249–256
Kaiming H, Xiangyu Z, Shaoqing R, Jian S (2018) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. Biochem Biophys Res Commun 498(1):254–261
Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90
Li J, Zhang J, Sun Q, Zhang H, Dong J, Che C, Zhang Q (2020) Breast cancer histopathological image classification based on deep second-order pooling network. In: 2020 International joint conference on neural networks (IJCNN). IEEE, pp 1–7
Liang W-J, Zhang H, Zhang G-F, Cao H-X (2019) Rice blast disease recognition using a deep convolutional neural network. Sci Rep 9(1):1–10
Liu J, Wang X (2020) Early recognition of tomato gray leaf spot disease based on mobilenetv2-yolov3 model. Plant Methods 16:1–16
Lu Z, Bai Y, Chen Y, Su C, Lu S, Zhan T, Hong X, Wang S (2020) The classification of gliomas based on a pyramid dilated convolution resnet model. Pattern Recogn Lett 133:173–179
Sengan S, Arokia JesuPrabhu L, Ramachandran V, Priya V, Ravi L, Subramaniyaswamy V (2020) Images super-resolution by optimal deep alexnet architecture for medical application: a novel docaln. J Intell Fuzzy Syst 1–14 (Preprint)
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826
Takahashi N, Mitsufuji Y (2020) D3net: densely connected multidilated densenet for music source separation. arXiv preprint arXiv:2010.01733
Taufiqurrahman S, Handayani A, Hermanto BR, Mengko TLER (2020) Diabetic retinopathy classification using a hybrid and efficient mobilenetv2-svm model. In: 2020 IEEE REGION 10 CONFERENCE (TENCON). IEEE, pp 235–240
Velliangira S, Premalata J (2020) A novel forgery detection in image frames of the videos using enhanced convolutional neural network in face images. Comput Model Eng Sci 125(2):625–645
Wang Y, Zu C, Hu G, Luo Y, Ma Z, He K, Wu X, Zhou J (2018) Automatic tumor segmentation with deep convolutional neural networks for radiotherapy applications. Neural Process Lett 48(3):1323–1334
Yang X, Yao Y (2018) Ensemble selector for attribute reduction. Appl Soft Comput 70:1–11
Yao T, Zhang Q, Wu X, Lin X (2020) Image recognition method of defective button battery base on improved mobilenetv1. In: Chinese conference on image and graphics technologies. Springer, pp 313–324
Yu H, Sun D, Xi X, Yang X, Zheng S, Wang Q (2019) Fuzzy one-class extreme auto-encoder. Neural Process Lett 50(1):701–727
Yuanmei W, Tingsong Y, Yongquan L (2018) Method for determining number of convolution kernel via edge detection approach. Appl Res Comput 35(11):3454–3457
Zhang Z, Li Y, He X, Yuan W (2016) CNN optimization and its application in traffic signs recognition based on GRA. J Residuals Sci Technol 13(6)
Acknowledgements
This project is supported by the National Natural Science Foundation of China (NSFC) (Nos. 61806087, 61902158).
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., Shao, H., Jiang, Y. et al. CNN-Based Hidden-Layer Topological Structure Design and Optimization Methods for Image Classification. Neural Process Lett 54, 2831–2842 (2022). https://doi.org/10.1007/s11063-022-10742-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-022-10742-8