{"type":"ScholarlyArticle","title":"A Sequence Labeling Convolutional Network and Its Application to Handwritten String Recognition","authors":[{"name":"Qingqing Wang","slug":"qingqing-wang","given":"Qingqing","family":"Wang","affiliation":"Shanghai Key Laboratory of Multidimensional Information Processing Department of Computer Science and Technology , East China Normal University 3663 North Zhongshan Road , Shanghai 200062 , P. R. China"},{"name":"Yue Lu","slug":"yue-lu","given":"Yue","family":"Lu","affiliation":"Shanghai Key Laboratory of Multidimensional Information Processing Department of Computer Science and Technology , East China Normal University 3663 North Zhongshan Road , Shanghai 200062 , P. R. China"}],"abstract":"Handwritten string recognition has been struggling with connected patterns fiercely. Segmentation-free and over-segmentation frameworks are commonly applied to deal with this issue. For the past years, RNN combining with CTC has occupied the domain of segmentation-free handwritten string recognition, while CNN is just employed as a single character recognizer in the over-segmentation framework. The main challenges for CNN to directly recognize handwritten strings are the appropriate processing of arbitrary input string length, which implies arbitrary input image size, and reasonable design of the output layer. In this paper, we propose a sequence labeling convolutional network for the recognition of handwritten strings, in particular, the connected patterns. We properly design the structure of the network to predict how many characters present in the input images and what exactly they are at every position. Spatial pyramid pooling (SPP) is utilized with a new implementation to handle arbitrary string length. Moreover, we propose a more flexible pooling strategy called FSPP to adapt the network to the straightforward recognition of long strings better. Experiments conducted on handwritten digital strings from two benchmark datasets and our own cell-phone number dataset demonstrate the superiority of the proposed network.","doi":"10.24963/ijcai.2017/411","url":"https://ijcai.org/proceedings/2017/411","pdf":"https://ijcai.org/proceedings/2017/0411.pdf","markdown":"https://ijcai.org/proceedings/2017/411.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/411","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning S-Z","track":"Main track","number":411,"pages":{"first":2950,"last":2956},"keywords":["Machine Learning: Neural Networks","Machine Learning: Deep Learning"],"videos":[],"references":[{"position":1,"raw":"[Diem et al., 2014] Markus Diem, Stefan Fiel, Florian Kle- ber, Robert Sablatnig, Jose M. Saavedra, David Contr- eras, Juan Manuel Barrios, and Luiz S. Oliveira. ICFHR 2014 competition on handwritten digit string recognition in challenging datasets (HDSRC 2014). International Conference on Frontiers in handwriting recognition, pages 779-784, 2014.","title":"ICFHR 2014 competition on handwritten digit string recognition in challenging datasets","authors":"Markus Diem, Stefan Fiel, Florian Kleber, Robert Sablatnig, Jose M Saavedra, David Contreras, Juan Manuel Barrios, Luiz S Oliveira","year":"2014","venue":"International Conference on Frontiers in handwriting recognition","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Goodfellow et al., 2014] Ian J. Goodfellow, Yaroslav Bula- tov, Julian Ibarz, Sacha Arnoud, and Vinay Shet. Multi- digit number recognition from street view imagery using deep convolutional neural networks. arXiv:1312.6082v4, Computer Science, 2014.","title":"Multidigit number recognition from street view imagery using deep convolutional neural networks","authors":"Ian J Goodfellow, Yaroslav Bulatov, Julian Ibarz, Sacha Arnoud, Vinay Shet","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Graves and Schmidhuber, 2008] Alex Graves and Jurgen Schmidhuber. Offline handwriting recognition with multi- dimensional recurrent neural networks. Advances in Neu- ral Information Processing Systems, 21:545-552, 2008.","title":"Alex Graves and Jurgen Schmidhuber. Offline handwriting recognition with multidimensional recurrent neural networks","authors":"Schmidhuber Graves","year":"2008","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Graves et al., 2009] Alex Graves, Marcus Liwicki, Santia- go Femandez, Roman Bertolami, Horst Bunke, and Jurgen Schmidhuber. A novel connectionist system for uncon- strained handwriting recognition. IEEE Transaction on Pattern Recognition and Machine Intelligence, 31(5):855- 868, 2009.","title":"A novel connectionist system for unconstrained handwriting recognition","authors":"Alex Graves, Marcus Liwicki, Santiago Femandez, Roman Bertolami, Horst Bunke, Jurgen Schmidhuber","year":"2009","venue":"IEEE Transaction on Pattern Recognition and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[He et al., 2015] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Spatial pyramid pooling in deep con- volutional networks for visual recognition. IEEE Trans- action on Pattern Recognition and Machine Intelligence, 37(9):1904-1916, 2015.","title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2015","venue":"IEEE Transaction on Pattern Recognition and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Keysers et al., 2016] Daniel Keysers, Thomas Deselaers, Henry A. Rowley, Li-Lun Wang, and Victor Carbune. Multi-language online handwriting recognition. IEEE Transaction on Pattern Recognition and Machine Intelli- gence, DOI: 10.1109/TPAMI.2016.2572693, 2016.","title":"Multi-language online handwriting recognition","authors":"Daniel Keysers, Thomas Deselaers, Henry A Rowley, Li-Lun Wang, Victor Carbune","year":"2016","venue":"IEEE Transaction on Pattern Recognition and Machine Intelligence","doi":"10.1109/tpami.2016.2572693","url":null,"internal_url":null},{"position":7,"raw":"[Liu et al., 2004] Cheng-Lin Liu, Hiroshi Sako, and Hi- romichi Fujisawa. Effects of classifier structures and train- ing regimes on integrated segmentation and recognition of handwritten numeral strings. IEEE Transaction on Pat- tern Recognition and Machine Intelligence, 26(11):1395- 1407, 2004.","title":"Effects of classifier structures and training regimes on integrated segmentation and recognition of handwritten numeral strings","authors":"Cheng-Lin Liu, Hiroshi Sako, Hiromichi Fujisawa","year":"2004","venue":"IEEE Transaction on Pattern Recognition and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Messina and Louradour, 2015] Ronaldo Messina and Jerome Louradour. Segmentation-free handwritten Chi- nese text recognition with LSTM-RNN. International Conference on Document Analysis and Recognition, pages 171-175, 2015.","title":"Ronaldo Messina and Jerome Louradour. Segmentation-free handwritten Chinese text recognition with LSTM-RNN","authors":"Louradour Messina","year":"2015","venue":"International Conference on Document Analysis and Recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Sanchez et al., 2016] Joan Andreu Sanchez, Veronica Romero, Alejandro H. Toselli, and Enrique Vidal. ICFHR2016 competition on handwritten text recognition on the READ dataset. 15th International Conference on Frontiers in Handwriting Recognition, pages 630-635, 2016.","title":"ICFHR2016 competition on handwritten text recognition on the READ dataset","authors":"Joan Andreu Sanchez, Veronica Romero, Alejandro H Toselli, Enrique Vidal","year":"2016","venue":"15th International Conference on Frontiers in Handwriting Recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Szegedy et al., 2015] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabi- novich. Going deeper with conclutions. IEEE Conference on Computer Vision and Pattern Recognition, pages 1-9, 2015.","title":"Going deeper with conclutions","authors":"Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich","year":"2015","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Wang et al., 2012] Qiu-Feng Wang, Fei Yin, and Cheng-Lin Liu. Handwritten Chinese text recognition by integrating multiple contexts. IEEE Transaction on Pattern Recogni- tion and Machine Intelligence, 34(8):1469-1481, 2012.","title":"Handwritten Chinese text recognition by integrating multiple contexts","authors":"Qiu-Feng Wang, Fei Yin, Cheng-Lin Liu","year":"2012","venue":"IEEE Transaction on Pattern Recognition and Machine Intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}