{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:54:42Z","timestamp":1775595282908,"version":"3.50.1"},"reference-count":26,"publisher":"National Library of Serbia","issue":"3","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ComSIS","COMPUT SCI INF SYST","COMPUT SCI INFORM SY","COMPUTER SCI INFORM","COMSIS J"],"published-print":{"date-parts":[[2022]]},"abstract":"<jats:p>At present, the traditional machine learning methods and convolutional neural network (CNN) methods are mostly used in image recognition. The feature extraction process in traditional machine learning for image recognition is mostly executed by manual, and its generalization ability is not strong enough. The earliest convolutional neural network also has many defects, such as high hardware requirements, large training sample size, long training time, slow convergence speed and low accuracy. To solve the above problems, this paper proposes a novel deep LeNet-5 convolutional neural network model for image recognition. On the basis of Lenet-5 model with the guaranteed recognition rate, the network structure is simplified and the training speed is improved. Meanwhile, we modify the Logarithmic Rectified Linear Unit (L ReLU) of the activation function. Finally, the experiments are carried out on the MINIST character library to verify the improved network structure. The recognition ability of the network structure in different parameters is analyzed compared with the state-of-the-art recognition algorithms. In terms of the recognition rate, the proposed method has exceeded 98%. The results show that the accuracy of the proposed structure is significantly higher than that of the other recognition algorithms, which provides a new reference for the current image recognition.<\/jats:p>","DOI":"10.2298\/csis220120036z","type":"journal-article","created":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T14:37:16Z","timestamp":1663598236000},"page":"1463-1480","source":"Crossref","is-referenced-by-count":27,"title":["A novel deep LeNet-5 convolutional neural network model for image recognition"],"prefix":"10.2298","volume":"19","author":[{"given":"Jingsi","family":"Zhang","sequence":"first","affiliation":[{"name":"Faculty of Robot Science and Engineering, Northeastern University Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaosheng","family":"Yu","sequence":"additional","affiliation":[{"name":"Faculty of Robot Science and Engineering, Northeastern University Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoliang","family":"Lei","sequence":"additional","affiliation":[{"name":"Faculty of Robot Science and Engineering, Northeastern University Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengdong","family":"Wu","sequence":"additional","affiliation":[{"name":"Faculty of Robot Science and Engineering, Northeastern University Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1078","reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"Maruo S, Fujishiro Y, Furukawa T. \u201dSimple autofocusing method by image processing using transmission images for large-scale two-photon lithography,\u201d Optics Express, vol. 28, no. 8, 2020.","DOI":"10.1364\/OE.390486"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"Chen J, Zheng H, Xiong H, et al. \u201dFineFool: A Novel DNN Object Contour Attack on Image Recognition based on the Attention Perturbation Adversarial Technique,\u201d Computers & Security, vol. 9:102220, 2021.","DOI":"10.1016\/j.cose.2021.102220"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"Shoulin Yin, Hang Li, Desheng Liu and Shahid Karim. \u201dActive Contour Modal Based on Density-oriented BIRCH Clustering Method for Medical Image Segmentation,\u201d Multimedia Tools and Applications, vol. 79, pp. 31049-31068, 2020.","DOI":"10.1007\/s11042-020-09640-9"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"Khan M A, Rizvi S, Abbas S, et al. \u201dDeep Extreme Learning Machine-Based Optical Character Recognition System for Nastalique Urdu-Like Script Languages,\u201d The Computer Journal, vol. 65, no. 2, pp. 331-344, 2022.","DOI":"10.1093\/comjnl\/bxaa042"},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"Murata M, Kanamaru T, Shirado T, et al. \u201dAutomatic F-term Classification of Japanese Patent Documents Using the k-Nearest Neighborhood Method and the SMART Weighting,\u201d Information & Media Technologies, vol. 14, no. 1, pp. 163-189, 2007.","DOI":"10.5715\/jnlp.14.163"},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"Xia, B., Han, D., Yin, X., Gao, N. \u201dRICNN: A ResNet & Inception Convolutional Neural Network for Intrusion Detection of Abnormal Traffic,\u201d Computer Science and Information Systems, vol. 19, no. 1, pp. 309-326, 2022.","DOI":"10.2298\/CSIS210617055X"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"Gorban A N, Mirkes E M, Tukin I Y. \u201dHow deep should be the depth of convolutional neural networks: a backyard dog case study,\u201d Cognitive Computation, vol. 12, no. 1, pp. 388-397, 2020.","DOI":"10.1007\/s12559-019-09667-7"},{"key":"ref8","doi-asserted-by":"crossref","unstructured":"Kim M J, Yi L, Song H O, et al. \u201dAutomatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images,\u201d Sensors, vol. 21, no. 2, pp. 505, 2021.","DOI":"10.3390\/s21020505"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"X. Yu,W. Long, Y. Li, X. Shi and L. Gao. \u201dImproving the Performance of Convolutional Neural Networks by Fusing Low-Level Features With Different Scales in the Preceding Stage,\u201d IEEE Access, vol. 9, pp. 70273-70285, 2021.","DOI":"10.1109\/ACCESS.2021.3077070"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"Wen L, Li X, Gao L. \u201dA transfer convolutional neural network for fault diagnosis based on ResNet-50,\u201d Neural Computing and Applications, vol. 32, pp. 6111-6124, 2020.","DOI":"10.1007\/s00521-019-04097-w"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"Kg A, Nc A. \u201dAnalysis of Histopathological Images for Prediction of Breast Cancer Using Traditional Classifiers with Pre-Trained CNN - ScienceDirect,\u201d Procedia Computer Science, vol. 167, pp. 878-889, 2020.","DOI":"10.1016\/j.procs.2020.03.427"},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"nan G\u00a8uler a, B E B. \u201dExpert systems for time-varying biomedical signals using eigenvector methods,\u201d Expert Systems with Applications, vol. 32, no. 4, pp. 1045-1058, 2007.","DOI":"10.1016\/j.eswa.2006.02.002"},{"key":"ref13","unstructured":"Glorot X, Bordes A, Bengio Y. \u201dDeep Sparse Rectifier Neural Networks,\u201d Journal of Machine Learning Research, vol. 15, pp. 315-323, 2011."},{"key":"ref14","unstructured":"Gao S. \u201dA Two-channel Attention Mechanism-based MobileNetV2 And Bidirectional Long Short Memory Network For Multi-modal Dimension Dance Emotion Recognition,\u201d Journal of Applied Science and Engineering, vol. 26, no. 4, pp. 455-464, 2022."},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"Fan Y, Rui X, Poslad S, et al. \u201dA better way to monitor haze through image based upon the adjusted LeNet-5 CNN model,\u201d Signal Image and Video Processing, vol. 14, no. 2, 2020.","DOI":"10.1007\/s11760-019-01574-6"},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"Zhang C, Yue X, Wang R, et al. \u201dStudy on Traffic Sign Recognition by Optimized Lenet-5 Algorithm,\u201d International Journal of Pattern Recognition and Artificial Intelligence, vol. 34, no. 1, pp. 2055003.1-2055003.21, 2020.","DOI":"10.1142\/S0218001420550034"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"Zhang Q, Hu X, Zhou S. \u201dThe Detection of Hyperthyroidism by the Modified LeNet-5 Network,\u201d Indian Journal of Pharmaceutical Sciences, vol. 82, 2020.","DOI":"10.36468\/pharmaceutical-sciences.spl.108"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"A. Senior and X. Lei. \u201dFine context, low-rank, softplus deep neural networks for mobile speech recognition,\u201d 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7644-7648, 2014.","DOI":"10.1109\/ICASSP.2014.6855087"},{"key":"ref19","doi-asserted-by":"crossref","unstructured":"F. Jafarzadehpour, A. Sabbagh Molahosseini, A. A. Emrani Zarandi and L. Sousa. \u201dEfficient Modular Adder Designs Based on Thermometer and One-Hot Coding,\u201d IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 27, no. 9, pp. 2142-2155, 2019.","DOI":"10.1109\/TVLSI.2019.2919609"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"Sarp, S., Kuzlu, M., Zhao, Y., Cetin, M., Guler, O. \u201dA Comparison of Deep Learning Algorithms on Image Data for Detecting Floodwater on Roadways,\u201d Computer Science and Information Systems, vol. 19, no. 1, pp. 397-414, 2022.","DOI":"10.2298\/CSIS210313058S"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"Wu Z, Shen C, Hengel A. \u201dWider or Deeper: Revisiting the ResNet Model for Visual Recognition,\u201d Pattern Recognition, vol. 90, pp. 119-133, 2019.","DOI":"10.1016\/j.patcog.2019.01.006"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"L. Sun, K. Liang, Y. Song and Y.Wang. \u201dAn Improved CNN-Based Apple Appearance Quality Classification Method With Small Samples,\u201d IEEE Access, vol. 9, pp. 68054-68065, 2021.","DOI":"10.1109\/ACCESS.2021.3077567"},{"key":"ref23","doi-asserted-by":"crossref","unstructured":"M. Zhang, M. Gong, H. He and S. Zhu. \u201dSymmetric All Convolutional Neural-Network-Based Unsupervised Feature Extraction for Hyperspectral Images Classification,\u201d IEEE Transactions on Cybernetics, vol. 52, no. 5, pp. 2981- 2993, 2022.","DOI":"10.1109\/TCYB.2020.3020540"},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"Z. Zhang. \u201dPAMSGAN: Pyramid Attention Mechanism-Oriented Symmetry Generative Adversarial Network for Motion Image Deblurring,\u201d IEEE Access, vol. 9, pp. 105131-105143, 2021.","DOI":"10.1109\/ACCESS.2021.3099803"},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"S. B. Ahmed, I. A. Hameed, S. Naz, M. I. \u201dRazzak and R. Yusof. Evaluation of Handwritten Urdu Text by Integration of MNIST Dataset Learning Experience,\u201d IEEE Access, vol. 7, pp. 153566-153578, 2019.","DOI":"10.1109\/ACCESS.2019.2946313"},{"key":"ref26","unstructured":"Chuang Bai, Xiang Chen. \u201dResearch on New LeNet-FC Convolutional Neural Network Model Algorithm,\u201d Computer Engineering and Applications, vol. 55, no. 5, pp. 105-111, 2019."}],"container-title":["Computer Science and Information Systems"],"original-title":[],"language":"en","deposited":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:26:45Z","timestamp":1691742405000},"score":1,"resource":{"primary":{"URL":"https:\/\/doiserbia.nb.rs\/Article.aspx?ID=1820-02142200036Z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":26,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.2298\/csis220120036z","relation":{},"ISSN":["1820-0214","2406-1018"],"issn-type":[{"value":"1820-0214","type":"print"},{"value":"2406-1018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}