{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T10:10:16Z","timestamp":1722247816478},"reference-count":34,"publisher":"National Library of Serbia","issue":"4","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"abstract":"<jats:p>To solve the problems of large number of similar Chinese characters, difficult feature extraction and inaccurate recognition, we propose a novel multilevel stacked SqueezeNet model for handwritten Chinese character recognition. First, we design a deep convolutional neural network model for feature grouping extraction and fusion. The multilevel stacked feature group extraction module is used to extract the deep abstract feature information of the image and carry out the fusion between the different feature information modules. Secondly, we use the designed down-sampling and channel amplification modules to reduce the feature dimension while preserving the important information of the image. The feature information is refined and condensed to solve the overlapping and redundant problem of feature information. Thirdly, inter-layer feature fusion algorithm and Softmax classification function constrained by L2 norm are used. We further compress the parameter clipping to avoid the loss of too much accuracy due to the clipping of important parameters. The dynamic network surgery algorithm is used to ensure that the important parameters of the error deletion are reassembled. Experimental results on public data show that the designed recognition model in this paper can effectively improve the recognition rate of handwritten Chinese characters.<\/jats:p>","DOI":"10.2298\/csis221210030d","type":"journal-article","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T12:54:00Z","timestamp":1686142440000},"page":"1771-1795","source":"Crossref","is-referenced-by-count":0,"title":["A novel multilevel stacked SqueezeNet model for handwritten Chinese character recognition"],"prefix":"10.2298","volume":"20","author":[{"given":"Yuankun","family":"Du","sequence":"first","affiliation":[{"name":"School of Big Data and Artificial Intelligence, Zhengzhou University of Science and Technology, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengping","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Zhengzhou University of Science and Technology, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhilong","family":"Liu","sequence":"additional","affiliation":[{"name":"Library of Henan Institute of Animal Husbandry and Economics, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1078","reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: \u201dFast and Robust Online Handwritten Chinese Character Recognition with Deep Spatial & Contextual Information Fusion Network,\u201d IEEE Transactions on Multimedia, doi: 10.1109\/TMM.2022.3143324.","DOI":"10.1109\/TMM.2022.3143324"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"Hu, M., Qu, X., Huang, J., et al.: \u201dAn End-to-End Classifier Based on CNN for In-Air Handwritten-Chinese-Character Recognition,\u201d Applied Sciences, Vol. 12, No. 14, 6862. (2022)","DOI":"10.3390\/app12146862"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"Li, P., Laghari, A., Rashid, M., Gao, J., Gadekallu, T., Javed, A., Yin, S.: \u201dA Deep Multimodal Adversarial Cycle-Consistent Network for Smart Enterprise System,\u201d IEEE Transactions on Industrial Informatics, Vol. 19, No. 1, 693-702. (2023). doi: 10.1109\/TII.2022.3197201.","DOI":"10.1109\/TII.2022.3197201"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"Dan, Y., Zhu, Z., Jin, W., et al.: \u201dS-Swin Transformer: simplified Swin Transformer model for offline handwritten Chinese character recognition,\u201d PeerJ Computer Science, Vol. 8, e1093. (2022)","DOI":"10.7717\/peerj-cs.1093"},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"Dan, Y., Zhu, Z., Jin, W., et al. \u201dPF-ViT: Parallel and Fast Vision Transformer for Offline Handwritten Chinese Character Recognition,\u201d Computational Intelligence and Neuroscience, Vol. 2022. (2022)","DOI":"10.1155\/2022\/8255763"},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"Peng, D., et al.: \u201dRecognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach,\u201d IEEE Transactions on Multimedia, doi: 10.1109\/TMM.2022.3146771.","DOI":"10.1109\/TMM.2022.3146771"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"Wang, L., Yin, S., Hashem, Alyami., et al.: \u201dA novel deep learning-based single shot multibox detector model for object detection in optical remote sensing images,\u201d Geoscience Data Journal, (2022). https:\/\/doi.org\/10.1002\/gdj3.162","DOI":"10.1002\/gdj3.162"},{"key":"ref8","doi-asserted-by":"crossref","unstructured":"Teng, L., Qiao, Y.: \u201dBiSeNet-oriented context attention model for image semantic segmentation,\u201d Computer Science and Information Systems, Vol. 19, No. 3, pp. 1409-1426. (2022)","DOI":"10.2298\/CSIS220321040T"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zuo, W., Chen, Y., et al.: \u201dBeyond a gaussian denoiser: Residual learning of deep cnn for image denoising,\u201d IEEE transactions on image processing, 2017, 26(7): 3142-3155.","DOI":"10.1109\/TIP.2017.2662206"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhang, H., Huang, X., et al.: \u201dVisual normalization of handwritten Chinese characters based on generative adversarial networks,\u201d International Journal of Pattern Recognition and Artificial Intelligence, Vol. 36, No. 3, 2253002. (2022)","DOI":"10.1142\/S0218001422530020"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"Hu, S., Wang, Q., Huang, K., et al.: \u201dRetrieval-based language model adaptation for handwritten Chinese text recognition,\u201d International Journal on Document Analysis and Recognition (IJDAR), 1-11. (2022)","DOI":"10.1007\/s10032-022-00419-2"},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"Yan, K., Guo, J., Zhou, W.: \u201dA Novel Method for Offline Handwritten Chinese Character Recognition Under the Guidance of Print,\u201d Advances in Knowledge Discovery and Data Mining: 25th Pacific-Asia Conference, PAKDD 2021, Virtual Event, May 11C14, 2021, Proceedings, Part II. Cham: Springer International Publishing, 106-117. (2021)","DOI":"10.1007\/978-3-030-75765-6_9"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"Zhou, M., Zhang, X., Yin, F., et al.: \u201dDiscriminative quadratic feature learning for handwritten Chinese character recognition,\u201d Pattern Recognition, Vol. 49, 7-18. (2016)","DOI":"10.1016\/j.patcog.2015.07.007"},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"Qu, X., Wang, W., Lu, K., et al.: \u201dData augmentation and directional feature maps extraction for in-air handwritten Chinese character recognition based on convolutional neural network,\u201d Pattern recognition letters, Vol. 111, 9-15. (2018)","DOI":"10.1016\/j.patrec.2018.04.001"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"Diao, H., Chen, C., Yuan,W., et al.: \u201dDeep residual networks for sleep posture recognition with unobtrusive miniature scale smart mat system,\u201d IEEE Transactions on Biomedical Circuits and Systems, Vol. 15, No. 1, 111-121. (2021)","DOI":"10.1109\/TBCAS.2021.3053602"},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"Cui, R., Liu, H., Zhang C.: \u201dA deep neural framework for continuous sign language recognition by iterative training,\u201d IEEE Transactions on Multimedia, Vol. 21, No. 7, 1880-1891. (2019)","DOI":"10.1109\/TMM.2018.2889563"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"Guo, Z., Zhou, Z., Liu, B., et al.: \u201dAn Improved Neural Network Model Based on Inception-v3 for Oracle Bone Inscription Character Recognition,\u201d Scientific Programming, Vol. 2022. (2022)","DOI":"10.1155\/2022\/7490363"},{"key":"ref18","unstructured":"Heo, Y.: \u201dLoss function optimization for cnn-based fingerprint anti-spoofing,\u201d International Journal of Computer and Information Engineering, Vol. 15, No. 6, 344-348. (2021)"},{"key":"ref19","doi-asserted-by":"crossref","unstructured":"Wang, Z., Du, J.: \u201dFast writer adaptation with style extractor network for handwritten text recognition,\u201d Neural Networks, Vol. 147, 42-52. (2022)","DOI":"10.1016\/j.neunet.2021.12.002"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yin, F., Liu, C.: \u201dImproving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models,\u201d Pattern Recognition, Vol. 65, 251-264. (2017)","DOI":"10.1016\/j.patcog.2016.12.026"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"Greco, A., Saggese, A., Vento, M., et al.: \u201dGender recognition in the wild: a robustness evaluation over corrupted images,\u201d Journal of Ambient Intelligence and Humanized Computing, Vol. 12, 10461-10472. (2021)","DOI":"10.1007\/s12652-020-02750-0"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"McGuire, M., Moore, T.: \u201dPrediction of tornado days in the United States with deep convolutional neural networks,\u201d Computers & Geosciences, Vol. 159, 104990. (2022)","DOI":"10.1016\/j.cageo.2021.104990"},{"key":"ref23","doi-asserted-by":"crossref","unstructured":"Kohler, M., Langer, S.: \u201dOn the rate of convergence of fully connected deep neural network regression estimates,\u201d The Annals of Statistics, Vol. 49, No. 4, 2231-2249. (2021)","DOI":"10.1214\/20-AOS2034"},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"Baaran, E.: \u201dClassification of white blood cells with SVM by selecting SqueezeNet and LIME properties by mRMR method,\u201d Signal, Image and Video Processing, Vol. 16, No. 7, 1821-1829. (2022)","DOI":"10.1007\/s11760-022-02141-2"},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"Yang, M., Tjuawinata, I., and Lam, K.: \u201dK-Means Clustering With Local d?-Privacy for Privacy-Preserving Data Analysis,\u201d IEEE Transactions on Information Forensics and Security, Vol. 17, 2524-2537. (2022) doi: 10.1109\/TIFS.2022.3189532.","DOI":"10.1109\/TIFS.2022.3189532"},{"key":"ref26","unstructured":"Guo, Y., Yao, A., Chen, Y.: \u201dDynamic network surgery for efficient dnns,\u201d Advances in neural information processing systems, Vol. 29. (2016)"},{"key":"ref27","doi-asserted-by":"crossref","unstructured":"Sun, L., Li, W., Ning, X., et al.: \u201dGradient-enhanced softmax for face recognition,\u201d IEICE TRANSACTIONS on Information and Systems, Vol. 103, No. 5, 1185-1189. (2020)","DOI":"10.1587\/transinf.2019EDL8103"},{"key":"ref28","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yin, F., Liu, C.: \u201dImproving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models,\u201d Pattern Recognition, Vol. 65, 251-264. (2017)","DOI":"10.1016\/j.patcog.2016.12.026"},{"key":"ref29","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., et al.: \u201dICDAR 2013 robust reading competition,\u201d 2013 12th international conference on document analysis and recognition. IEEE, 1484-1493. (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref30","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Xu, Z., and Lu, G.: \u201dSPEDCCNN: Spatial Pyramid-Oriented Encoder-Decoder Cascade Convolution Neural Network for Crop Disease Leaf Segmentation,\u201d IEEE Access, Vol. 9, 14849-14866.(2021) doi: 10.1109\/ACCESS.2021.3052769.","DOI":"10.1109\/ACCESS.2021.3052769"},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"Peng, D., Jin, L., Liu, Y., et al.: \u201dPageNet: Towards End-to-EndWeakly Supervised Page-Level Handwritten Chinese Text Recognition,\u201d International Journal of Computer Vision, Vol. 130, No. 11, 2623-2645. (2022)","DOI":"10.1007\/s11263-022-01654-0"},{"key":"ref32","doi-asserted-by":"crossref","unstructured":"Xu, X., Yang, C., Wang, L., et al.: \u201dA sophisticated offline network developed for recognizing handwritten Chinese character efficiently,\u201d Computers and Electrical Engineering, Vol. 100, 107857. (2022)","DOI":"10.1016\/j.compeleceng.2022.107857"},{"key":"ref33","doi-asserted-by":"crossref","unstructured":"Huang, G., Luo, X.,Wang, S., et al.: \u201dHippocampus-heuristic character recognition network for zero-shot learning in Chinese character recognition,\u201d Pattern Recognition, Vol. 130, 108818. (2022)","DOI":"10.1016\/j.patcog.2022.108818"},{"key":"ref34","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yang, Y., Ding, W., et al.: \u201dA residual-attention offline handwritten Chinese text recognition based on fully convolutional neural networks,\u201d IEEE Access, Vol. 9, 132301- 132310. (2021)","DOI":"10.1109\/ACCESS.2021.3115606"}],"container-title":["Computer Science and Information Systems"],"original-title":[],"language":"en","deposited":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T09:32:19Z","timestamp":1722245539000},"score":1,"resource":{"primary":{"URL":"https:\/\/doiserbia.nb.rs\/Article.aspx?ID=1820-02142300030D"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.2298\/csis221210030d","relation":{},"ISSN":["1820-0214","2406-1018"],"issn-type":[{"value":"1820-0214","type":"print"},{"value":"2406-1018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}