{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T10:46:13Z","timestamp":1761561973246,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319166278"},{"type":"electronic","value":"9783319166285"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-16628-5_22","type":"book-chapter","created":{"date-parts":[[2015,4,11]],"date-time":"2015-04-11T06:31:51Z","timestamp":1428733911000},"page":"303-315","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Hybrid CNN-HMM Model for Street View House Number Recognition"],"prefix":"10.1007","author":[{"given":"Qiang","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohui","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,4,12]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/34.824820","volume":"22","author":"G Nagy","year":"2000","unstructured":"Nagy, G.: Twenty years of document image analysis in PAMI. IEEE Trans. Pattern Anal. Mach. Intell. 22, 38\u201362 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR2","doi-asserted-by":"publisher","first-page":"3131","DOI":"10.1016\/j.patcog.2009.03.014","volume":"42","author":"M Cheriet","year":"2009","unstructured":"Cheriet, M., El Yacoubi, M., Fujisawa, H., Lopresti, D., Lorette, G.: Handwriting recognition research: twenty years of achievement and beyond. Pattern Recogn. 42, 3131\u20133135 (2009)","journal-title":"Pattern Recogn."},{"key":"22_CR3","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1109\/34.273729","volume":"16","author":"J Ohya","year":"1994","unstructured":"Ohya, J., Shio, A., Akamatsu, S.: Recognizing characters in scene images. IEEE Trans. Pattern Anal. Mach. Intell. 16, 214\u2013220 (1994)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: 2011 IEEE International Conference on Computer Vision (ICCV), IEEE, pp. 1457\u20131464 (2011)","key":"22_CR4"},{"unstructured":"Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: 2012 21st International Conference on Pattern Recognition (ICPR), IEEE, pp. 3304\u20133308 (2012)","key":"22_CR5"},{"key":"22_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1007\/978-3-642-19318-7_60","volume-title":"Computer Vision \u2013 ACCV 2010","author":"L Neumann","year":"2011","unstructured":"Neumann, L., Matas, J.: A method for text localization and recognition in real-world images. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part III. LNCS, vol. 6494, pp. 770\u2013783. Springer, Heidelberg (2011)"},{"doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 3538\u20133545 (2012)","key":"22_CR7","DOI":"10.1109\/CVPR.2012.6248097"},{"unstructured":"Alsharif, O., Pineau, J.: End-to-end text recognition with hybrid HMM maxout models (2013). arXiv preprint arXiv:1310.1811","key":"22_CR8"},{"doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H.: PhotoOCR: reading text in uncontrolled conditions. In: ICCV (2013)","key":"22_CR9","DOI":"10.1109\/ICCV.2013.102"},{"doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Scene text localization and recognition with oriented stroke detection. In: ICCV (2013)","key":"22_CR10","DOI":"10.1109\/ICCV.2013.19"},{"doi-asserted-by":"crossref","unstructured":"Ciresan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Convolutional neural network committees for handwritten character classification. In: ICDAR, pp. 1250\u20131254 (2011)","key":"22_CR11","DOI":"10.1109\/ICDAR.2011.229"},{"unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, vol. 1, p. 4 (2012)","key":"22_CR12"},{"unstructured":"Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks (2013). arXiv preprint arXiv:1302.4389","key":"22_CR13"},{"unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. CoRR abs\/1311.2901 (2013)","key":"22_CR14"},{"unstructured":"Goodfellow, I.J., Bulatov, Y., Ibarz, J., Arnoud, S., Shet, V.: Multi-digit number recognition from street view imagery using deep convolutional neural networks (2014). arXiv preprint arXiv:1312.6082","key":"22_CR15"},{"key":"22_CR16","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"unstructured":"Matan, O., Burges, C.J.C., LeCun, Y., Denker, J.S.: Multi-digit recognition using a space displacement neural network. In: NIPS, pp. 488\u2013495 (1991)","key":"22_CR17"},{"key":"22_CR18","volume-title":"Connectionist Speech Recognition: A Hybrid Approach","author":"HA Bourlard","year":"1993","unstructured":"Bourlard, H.A., Morgan, N.: Connectionist Speech Recognition: A Hybrid Approach. Kluwer Academic Publishers, Norwell (1993). ISBN: 0792393961"},{"key":"22_CR19","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20, 30\u201342 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"22_CR20","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sig. Process. Mag. 29, 82\u201397 (2012)","journal-title":"IEEE Sig. Process. Mag."},{"doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp. 6645\u20136649 (2013)","key":"22_CR21","DOI":"10.1109\/ICASSP.2013.6638947"},{"doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Ramabhadran, B., Fousek, P., Novak, P., Mohamed, A.R.: Making deep belief networks effective for large vocabulary continuous speech recognition. In: 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), IEEE, pp. 30\u201335 (2011)","key":"22_CR22","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"22_CR23","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1109\/PROC.1973.9030","volume":"61","author":"GDJ Forney","year":"1973","unstructured":"Forney, G.D.J.: The viterbi algorithm. Proc. IEEE 61, 268\u2013278 (1973)","journal-title":"Proc. IEEE"},{"doi-asserted-by":"crossref","unstructured":"Jarrett, K., Kavukcuoglu, K., Ranzato, M., LeCun, Y.: What is the best multi-stage architecture for object recognition? In: ICCV, pp. 2146\u20132153 (2009)","key":"22_CR24","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"22_CR25","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1214\/aoms\/1177697196","volume":"41","author":"LE Baum","year":"1970","unstructured":"Baum, L.E., Petrie, T., Soules, G., Weiss, N.: A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Ann. Math. Stat. 41, 164\u2013171 (1970)","journal-title":"Ann. Math. Stat."},{"key":"22_CR26","first-page":"1","volume":"3","author":"LE Baum","year":"1972","unstructured":"Baum, L.E.: An inequality and associated maximization technique in statistical estimation for probabilistic functions of a Markov process. Inequalities 3, 1\u201318 (1972)","journal-title":"Inequalities"},{"key":"22_CR27","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1162\/neco.1991.3.4.461","volume":"3","author":"MD Richard","year":"1991","unstructured":"Richard, M.D., Lippmann, R.P.: Neural network classifiers estimate Bayesian a posteriori probabilities. Neural Comput. 3, 461\u2013483 (1991)","journal-title":"Neural Comput."},{"key":"22_CR28","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/79.382443","volume":"12","author":"N Morgan","year":"1995","unstructured":"Morgan, N., Bourlard, H.: Continuous speech recognition. IEEE Sig. Process. Mag. 12, 24\u201342 (1995)","journal-title":"IEEE Sig. Process. Mag."},{"unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, vol. 2011 (2011)","key":"22_CR29"},{"doi-asserted-by":"crossref","unstructured":"Kapadia, S., Valtchev, V., Young, S.: Mmi training for continuous phoneme recognition on the timit database. In: 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1993, vol. 2, pp. 491\u2013494 (1993)","key":"22_CR30","DOI":"10.1109\/ICASSP.1993.319349"},{"key":"22_CR31","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/89.568732","volume":"5","author":"BH Juang","year":"1997","unstructured":"Juang, B.H., Hou, W., Lee, C.H.: Minimum classification error rate methods for speech recognition. IEEE Trans. Speech Audio Process. 5, 257\u2013265 (1997)","journal-title":"IEEE Trans. Speech Audio Process."},{"unstructured":"Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning, ICML 2001, pp. 282\u2013289 (2001)","key":"22_CR32"}],"container-title":["Lecture Notes in Computer Science","Computer Vision - ACCV 2014 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-16628-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T09:44:30Z","timestamp":1675849470000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-16628-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319166278","9783319166285"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-16628-5_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"12 April 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}