{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:39:54Z","timestamp":1781019594094,"version":"3.54.1"},"reference-count":38,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>In the realm of image classification, the capsule network is a network topology that packs the extracted features into many capsules, performs sophisticated capsule screening using a dynamic routing mechanism, and finally recognizes that each capsule corresponds to a category feature. Compared with previous network topologies, the capsule network has more sophisticated operations, uses a large number of parameter matrices and vectors to express picture attributes, and has more powerful image classification capabilities. However, in the practical application field, the capsule network has always been constrained by the quantity of calculation produced by the complicated structure. In the face of basic datasets, it is prone to over-fitting and poor generalization and often cannot satisfy the high computational overhead when facing complex datasets. Based on the aforesaid problems, this research proposes a novel enhanced capsule network topology. The upgraded network boosts the feature extraction ability of the network by incorporating a multi-scale feature extraction module based on proprietary star structure convolution into the standard capsule network. At the same time, additional structural portions of the capsule network are changed, and a variety of optimization approaches such as dense connection, attention mechanism, and low-rank matrix operation are combined. Image classification studies are carried out on different datasets, and the novel structure suggested in this paper has good classification performance on CIFAR-10, CIFAR-100, and CUB datasets. At the same time, we also achieved 98.21% and 95.38% classification accuracy on two complicated datasets of skin cancer ISIC derived and Forged Face EXP.<\/jats:p>","DOI":"10.3390\/jimaging11100355","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T09:45:01Z","timestamp":1760089501000},"page":"355","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Improved Capsule Network for Image Classification Using Multi-Scale Feature Extraction"],"prefix":"10.3390","volume":"11","author":[{"given":"Wenjie","family":"Huang","sequence":"first","affiliation":[{"name":"Main Campus, Automation College, University of Science and Technology Beijing (USTB), Haidian District, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiqing","family":"Kang","sequence":"additional","affiliation":[{"name":"Main Campus, Automation College, University of Science and Technology Beijing (USTB), Haidian District, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1861-852X","authenticated-orcid":false,"given":"Lingyan","family":"Li","sequence":"additional","affiliation":[{"name":"Main Campus, Automation College, University of Science and Technology Beijing (USTB), Haidian District, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhui","family":"Feng","sequence":"additional","affiliation":[{"name":"Main Campus, Automation College, University of Science and Technology Beijing (USTB), Haidian District, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"ref_1","first-page":"109","article-title":"Face Expression Recognition Based on the Combination of ResNet18 and Capsule Network","volume":"44","author":"Liu","year":"2023","journal-title":"J. Qingdao Univ. Sci. Technol. Nat. Sci. Ed."},{"key":"ref_2","first-page":"33","article-title":"A Brief Analysis of Research Status and Future of Capsule Neural Network","volume":"57","author":"He","year":"2021","journal-title":"Comput. Eng. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zhang, W., Tang, P., and Zhao, L.J. (2019). Remote Sensing Image Scene Classification Using CNN-CapsNet. Remote Sens., 11.","DOI":"10.3390\/rs11050494"},{"key":"ref_4","unstructured":"Sabour, S., Frosst, N., and Hinton, G.E. (2017, January 4\u20139). Dynamic Routing Between Capsules. Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS 2017), Long Beach, CA, USA."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"337","DOI":"10.32604\/csse.2023.034242","article-title":"A Hybrid Approach for Plant Disease Detection Using E-GAN and CapsNet","volume":"46","author":"Vasudevan","year":"2023","journal-title":"Comput. Syst. Sci. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"28521","DOI":"10.1007\/s11042-023-14353-w","article-title":"Conv-CapsNet: Capsule-Based Network for COVID-19 Detection through X-ray Scans","volume":"82","author":"Sharma","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.neucom.2022.08.073","article-title":"Capsule Networks for Image Classification: A Review","volume":"509","author":"Pawan","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_8","first-page":"165","article-title":"Research on Capsule Network Model Based on Dynamic Routing Rules","volume":"8","author":"Li","year":"2022","journal-title":"Comput. Program. Skills Maint."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"26425","DOI":"10.1007\/s11042-022-12279-3","article-title":"E-CapsGan: Generative Adversarial Network Using Capsule Network as Feature Encoder","volume":"81","author":"Xiang","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"ref_10","first-page":"1","article-title":"Review of Capsule Network","volume":"49","author":"Yang","year":"2019","journal-title":"J. Shandong Univ. Eng. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1007\/s13042-021-01431-4","article-title":"A Tiny Deep Capsule Network","volume":"13","author":"Sun","year":"2022","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_12","unstructured":"Denil, M., Shakibi, B., Dinh, L., Ranzato, M.A., and de Freitas, N. (2014). Predicting Parameters in Deep Learning. arXiv."},{"key":"ref_13","first-page":"251","article-title":"Survey of Deep Neural Network Model Compression","volume":"29","author":"Lei","year":"2018","journal-title":"J. Softw."},{"key":"ref_14","first-page":"68","article-title":"Fully Automatic Water Extraction from Remote Sensing Images Using Densely Connected Fully Convolutional Neural Network","volume":"35","author":"Liang","year":"2020","journal-title":"Remote Sens. Inf."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Guo, Q., Qiu, X., Liu, P., Shao, Y., Xue, X., and Zhang, Z. (2019, January 2\u20137). Star-Transformer. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Minneapolis, MN, USA.","DOI":"10.18653\/v1\/N19-1133"},{"key":"ref_16","first-page":"59","article-title":"Construction Method of Multi-Scale Self-Routing Capsule Network","volume":"37","author":"Zhang","year":"2022","journal-title":"J. Tianjin Univ. Sci. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Shiri, P., and Baniasadi, A. (2021, January 13\u201316). LE-CapsNet: A Light and Enhanced Capsule Network. Proceedings of the 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), Pasadena, CA, USA.","DOI":"10.1109\/ICMLA52953.2021.00280"},{"key":"ref_18","unstructured":"Xi, E., Bing, Y., and Jin, S. (2017). Capsule Network Performance on Complex Data. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Hu, M.F., Li, Z.Y., and Liu, W. (2022, January 15\u201317). Constructing Better Primary Capsules. Proceedings of the 2022 34th Chinese Control and Decision Conference (CCDC), Hefei, China.","DOI":"10.1109\/CCDC55256.2022.10033850"},{"key":"ref_20","first-page":"208","article-title":"Research and Improvement of Dynamic Routing Based on Capsule Network","volume":"48","author":"Chen","year":"2022","journal-title":"Comput. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Idelbayev, Y., and Carreira-Perpi\u00f1\u00e1n, M.A. (2020, January 13\u201319). Low-Rank Compression of Neural Nets: Learning the Rank of Each Layer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00807"},{"key":"ref_22","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2021). LoRA: Low-Rank Adaptation of Large Language Models. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5388","DOI":"10.1109\/TNNLS.2024.3383392","article-title":"Neural Network Compression Based on Tensor Ring Decomposition","volume":"36","author":"Xie","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Geng, X., Wang, J., Gong, J., Xue, Y., Xu, J., Chen, F., and Huang, X. (2024, January 17\u201322). OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00577"},{"key":"ref_25","first-page":"87","article-title":"An Advanced Explainable and Interpretable ML-Based Framework for Educational Data Mining","volume":"Volume 769","author":"Caruso","year":"2023","journal-title":"Methodologies and Intelligent Systems for Technology Enhanced Learning, Workshops\u201413th International Conference"},{"key":"ref_26","unstructured":"Gugglberger, J., Peer, D., and Rodr\u00edguez-S\u00e1nchez, A. (2022). Momentum Capsule Networks. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Rajasegaran, J., Jayasundara, V., Jayasekara, S., Jayasekara, H., Seneviratne, S., and Rodrigo, R. (2019, January 15\u201320). DeepCaps: Going Deeper with Capsule Networks. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01098"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Vu, D.T., An, L.B.T., Kim, J.Y., and Yu, G.H. (2023). Towards Feasible Capsule Network for Vision Tasks. Appl. Sci., 13.","DOI":"10.3390\/app131810339"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Shiri, P., and Baniasadi, A. (2023, January 7\u20139). DeepCaps+: A Light Variant of DeepCaps. Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023)\u2014Volume 5: VISAPP, Set\u00fabal, Portugal.","DOI":"10.5220\/0011728100003417"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"103687","DOI":"10.1016\/j.cviu.2023.103687","article-title":"A Multi-View-CNN Framework for Deep Representation Learning in Image Classification","volume":"232","author":"Pintelas","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Lilhore, U.K., Sharma, Y.K., Simaiya, S., Alroobaea, R., Baqasah, A.M., Alsafyani, M., and Alhazmi, A. (2025). SkinEHDLF A Hybrid Deep Learning Approach for Accurate Skin Cancer Classification in Complex Systems. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-98205-7"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Abohashish, S.M.M., Amin, H.H., and Elsedimy, E.I. (2025). Enhanced Melanoma and Non-Melanoma Skin Cancer Classification Using a Hybrid LSTM-CNN Model. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-08954-8"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Mustafa, S., Jaffar, A., Rashid, M., Akram, S., and Bhatti, S.M. (2025). Deep Learning-Based Skin Lesion Analysis Using Hybrid ResUNet++ and Modified AlexNet-Random Forest for Enhanced Segmentation and Classification. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0315120"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"15763","DOI":"10.1007\/s11042-022-13847-3","article-title":"Classification of Skin Cancer from Dermoscopic Images Using Deep Neural Network Architectures","volume":"82","author":"Jaisakthi","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Sabir, R., and Mehmood, T. (2024). Classification of Melanoma Skin Cancer Based on Image Dataset Using Different Neural Networks. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-75143-4"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Pintelas, E., Livieris, I.E., and Pintelas, P.E. (2021). A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets. Sensors, 21.","DOI":"10.3390\/s21227731"},{"key":"ref_37","first-page":"44","article-title":"Study on Deepfake Face Detection Using Transfer Learning Approach","volume":"186","author":"Mawa","year":"2024","journal-title":"Int. J. Comput. Appl."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Bian, W. (2023, January 9\u201310). Real-Fake Face Detection Based on Joint Multi-Layer CNN Structure and Data Augmentation. Proceedings of the 1st International Conference on Data Analysis and Machine Learning (DAML 2023), L\u00fcbeck, Germany.","DOI":"10.5220\/0012800300003885"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/10\/355\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T10:36:28Z","timestamp":1760092588000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/10\/355"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"references-count":38,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["jimaging11100355"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11100355","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,10]]}}}