{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:17:04Z","timestamp":1777702624150,"version":"3.51.4"},"reference-count":36,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2018,11,16]],"date-time":"2018-11-16T00:00:00Z","timestamp":1542326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2019,3,16]]},"abstract":"<jats:p>\n                    Handwritten numeral recognition is a challenging problem in the character recognition field due to the large variation in the writing styles of different persons and high similarity in the contour of different numerals. To address this problem, an effective\n                    <jats:italic>multi-task learning network<\/jats:italic>\n                    (MTLN) for handwritten numeral recognition is presented in this paper. Based on the observation that the writing style could play an effective complementary role to the learned feature extracted from numerals, the proposed MTLN simultaneously performs the handwritten numeral learning module and the writing style learning module. Consequently, the determination of scratchy\/non-scratchy in the writing style learning module can effectively assist the handwritten numeral learning module to obtain a more robust and distinguishable feature so as to improve the recognition performance. Extensive experiments on multiple existing handwritten numeral datasets have demonstrated that the proposed MTLN can effectively improve the recognition accuracy, and outperform multiple state-of-the-art methods.\n                  <\/jats:p>","DOI":"10.3233\/jifs-169862","type":"journal-article","created":{"date-parts":[[2018,11,16]],"date-time":"2018-11-16T12:42:13Z","timestamp":1542372133000},"page":"843-850","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-task learning network for handwritten numeral recognition"],"prefix":"10.1177","volume":"36","author":[{"given":"Jinhui","family":"Hou","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Huaqiao University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanqiang","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Huaqiao University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Huaqiao University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Engineering, Huaqiao University, Quanzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Huaqiao University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Canhui","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Engineering, Huaqiao University, Quanzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2018,11,16]]},"reference":[{"key":"e_1_3_2_2_2","author":"Li H.","year":"2016","unstructured":"H.Li and C.Shen, Reading car license plates using deep convolutional neural networks and lstms, arXiv preprint arXiv: 1601.05610, 2016.","journal-title":"Reading car license plates using deep convolutional neural networks and lstms"},{"key":"e_1_3_2_3_2","first-page":"298","article-title":"Vehicle license plate recognition with random convolutional networks","author":"Menotti D.","year":"2014","unstructured":"D.Menotti, G.Chiachia, A.X.Falcao, and V.J.O.Neto, Vehicle license plate recognition with random convolutional networks, Graphics, Patterns and Images, 2014, pp. 298\u2013303.","journal-title":"Graphics, Patterns and Images,"},{"key":"e_1_3_2_4_2","first-page":"1328","article-title":"Handwritten english character recognition using neural network","volume":"3","author":"Pal A.","year":"2010","unstructured":"A.Pal and D.Singh, Handwritten english character recognition using neural network, International Journal of Computer Science & Communication 3 (2010), 1328\u20131331.","journal-title":"International Journal of Computer Science & Communication"},{"key":"e_1_3_2_5_2","first-page":"125","article-title":"Offline handwritten english character recognition based on convolutional neural network","author":"Yuan A.","year":"2012","unstructured":"A.Yuan, G.Bai, L.Jiao and Y.Liu, Offline handwritten english character recognition based on convolutional neural network, Iapr International Workshop on Document Analysis Systems (2012), 125\u2013129.","journal-title":"Iapr International Workshop on Document Analysis Systems"},{"key":"e_1_3_2_6_2","first-page":"1","article-title":"Persian handwritten numeral recognition using complex neural network and non-linear feature extraction","author":"Shokoohi Z.","year":"2013","unstructured":"Z.Shokoohi, A.M.Hormat, F.Mahmoudi and H.Badal-babadi, Persian handwritten numeral recognition using complex neural network and non-linear feature extraction, Pattern Recognition and Image Analysis (2013), 1\u20135.","journal-title":"Pattern Recognition and Image Analysis"},{"key":"e_1_3_2_7_2","first-page":"431","article-title":"Towards optimal convolutional neural network parameters for bengali handwritten numerals recognition","author":"Chowdhury A.M.S.","year":"2017","unstructured":"A.M.S.Chowdhury and M.S.Rahman, Towards optimal convolutional neural network parameters for bengali handwritten numerals recognition, International Conference on Computer and Information Technology, 2017, pp. 431\u2013436.","journal-title":"International Conference on Computer and Information Technology,"},{"key":"e_1_3_2_8_2","first-page":"246","article-title":"An mqdf-cnn hybrid model for offline handwritten chinese character recognition","author":"Wang Y.","year":"2014","unstructured":"Y.Wang, X.Li, C.Liu, X.Ding and Y.Chen, An mqdf-cnn hybrid model for offline handwritten chinese character recognition, International Conference on Frontiers in Handwriting Recognition, 2014, pp. 246\u2013249.","journal-title":"International Conference on Frontiers in Handwriting Recognition,"},{"key":"e_1_3_2_9_2","first-page":"61","article-title":"Recognition confidence analysis of handwritten chinese character with cnn","author":"He M.","year":"2015","unstructured":"M.He, S.Zhang, H.Mao and L.Jin, Recognition confidence analysis of handwritten chinese character with cnn, International Conference on Document Analysis and Recognition, 2015, pp. 61\u201365.","journal-title":"International Conference on Document Analysis and Recognition,"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"issue":"6","key":"e_1_3_2_12_2","first-page":"31","article-title":"Representational learning with extreme learning machine for big data","volume":"28","author":"Kasun L.L.C.","year":"2013","unstructured":"L.L.C.Kasun, H.Zhou, G.Huang and C.M.Vong, Representational learning with extreme learning machine for big data, IEEE Intelligent System 28(6) (2013), 31\u201334.","journal-title":"IEEE Intelligent System"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.05.012"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.09.021"},{"issue":"7","key":"e_1_3_2_15_2","first-page":"2673","article-title":"A hybrid deep learning cnn-elm model and its application in handwritten numeral recognition","volume":"11","author":"Guo L.","year":"2015","unstructured":"L.Guo and S.Ding, A hybrid deep learning cnn-elm model and its application in handwritten numeral recognition, Journal of Computational Information Systems 11(7) (2015), 2673\u20132680.","journal-title":"Journal of Computational Information Systems"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2016.2640698"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2516239"},{"key":"e_1_3_2_18_2","first-page":"1249","article-title":"Learning deep feature representations with domain guided dropout for person re-identification","author":"Xiao T.","year":"2016","unstructured":"T.Xiao, H.Li, W.Ouyang and X.Wang, Learning deep feature representations with domain guided dropout for person re-identification, IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1249\u20131258.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition,"},{"key":"e_1_3_2_19_2","first-page":"1","article-title":"Deep hybrid similarity learning for person re-identification","author":"Zhu J.","year":"2017","unstructured":"J.Zhu, H.Zeng, S.Liao, Z.Lei, C.Cai and L.X.Zheng, Deep hybrid similarity learning for person re-identification, IEEE Transactions on Circuits and Systems for Video Technology, 2017, PP. 1\u20131.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2017.09.003"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57421-9_17"},{"issue":"10","key":"e_1_3_2_22_2","first-page":"1036","article-title":"Multi-column deep neural networks for image classification","volume":"157","author":"Ciresan D.","year":"2012","unstructured":"D.Ciresan, U.Meier and J.Schmidhuber, Multi-column deep neural networks for image classification, Computer Vision and Pattern Recognition 157(10) (2012), 1036\u20131041.","journal-title":"Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_23_2","first-page":"29","article-title":"Training data expansion and boosting of convolutional neural networks forreducing the mnist dataset error rate","author":"Romanuke V.V.","year":"2016","unstructured":"V.V.Romanuke, Training data expansion and boosting of convolutional neural networks forreducing the mnist dataset error rate, Scientific news of NTUU \"Kyiv Polytechnic Institute\", 2016, pp. 29\u201334.","journal-title":"Scientific news of NTUU \"Kyiv Polytechnic Institute\""},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.2991\/ijcis.2017.10.1.38"},{"issue":"2","key":"e_1_3_2_25_2","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky A.","year":"2012","unstructured":"A.Krizhevsky, I.Sutskever and G.E.Hinton, Imagenet classification with deep convolutional neural networks, Neural Information Processing Systems 25(2) (2012), 1097\u20131105.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_2_26_2","author":"Ioffe S.","year":"2015","unstructured":"S.Ioffe and C.Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv: 1502.03167, 2015.","journal-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift"},{"key":"e_1_3_2_27_2","author":"Simonyan K.","year":"2014","unstructured":"K.Simonyan and A.Zisserman, Very deep convolu-tional networks for large-scale image recognition, arXiv: 1409.1556, 2014.","journal-title":"Very deep convolu-tional networks for large-scale image recognition"},{"key":"e_1_3_2_28_2","first-page":"41","article-title":"Multi-task feature learning","author":"Scholkopf B.","year":"2007","unstructured":"B.Scholkopf, J.Platt and T.Hofmann, Multi-task feature learning, Conference on Advances in Neural Information Processing Systems, 2007, pp. 41\u201348.","journal-title":"Conference on Advances in Neural Information Processing Systems,"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_25"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"e_1_3_2_33_2","first-page":"693","article-title":"Efficient learning of deep boltzmann machines","author":"Salakhutdinov R.","year":"2010","unstructured":"R.Salakhutdinov and H.Larochelle, Efficient learning of deep boltzmann machines, International Conference on Artificial Intelligence and Statistics, 2010, pp. 693\u2013700.","journal-title":"International Conference on Artificial Intelligence and Statistics,"},{"key":"e_1_3_2_34_2","author":"Michael A.N.","year":"2015","unstructured":"A.N.Michael, Neural Networks and Deep Learning, 2015, http:\/\/neuralnetworksanddeeplearning.com","journal-title":"Neural Networks and Deep Learning"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005830"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.10.011"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.03.021"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.3233\/JIFS-169862","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-169862","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-169862","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-169862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:36:28Z","timestamp":1777455388000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-169862"}},"subtitle":[],"editor":[{"given":"Wen-Hsiang","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2018,11,16]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,3,16]]}},"alternative-id":["10.3233\/JIFS-169862"],"URL":"https:\/\/doi.org\/10.3233\/jifs-169862","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,16]]}}}