Abstract
The segmentation of Chinese handwritten document image into individual words is an essential step for the character recognition. Conventional methods frequently use feature extraction and classification algorithm to segment. However, since the features of the words mostly depend on people, it is considered a difficult task. In order to avoid this problem, we use a method of object detection—Faster R-CNN. The words are treated as the especial object and people do not concern on features extraction. Experimental results on HIT-MW databases show that our method achieves the preferable performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Seni, G., Cohen, E.: External word segmentation of off-line handwritten text lines. Pattern Recognit. 27(1), 41–52 (1994)
Baird, H.S., Kahan, S., Pavlidis, T.: Components of an omnifont page reader. In: Proceedings of the International Conference on Pattern Recognition, Paris (1986)
Lu, S., et al.: Free-form handwritten Chinese character segmentation based on Chinese character structure. Acta Electronica Sinica 28(5), 102–104 (2000)
Chen, S., et al.: Research on Chinese character segmentation based on connected domain. Appl. Res. Comput. 22(6), 246–248 (2005)
Louloudis, G., Gatos, B., Pratikakis, I., et al.: Text line and word segmentation of handwritten documents. Pattern Recognit. 42(12), 3169–3183 (2009)
Li, Y., et al.: Segmentation of handwritten Chinese characters based on structural clustering and stroke analysis. Comput. Eng. Appl. 44(34), 163–165 (2008)
Kim, G., Govindaraju, V., Srihari, S.N.: A segmentation and recognition strategy for handwritten phrases. In: Proceedings of the 13th International Conference on Pattern Recognition, vol. 4, pp. 510–514. IEEE (1996)
Srihari, S., Srinivasan, H., Babu, P., et al.: Handwritten Arabic word spotting using the CEDARABIC document analysis system, pp. 123–132 (2005)
Ryu, J., Koo, H.I., Cho, N.I.: Word segmentation method for handwritten documents based on structured learning. IEEE Signal Process. Lett. 22(8), 1161–1165 (2015)
Xu, L., et al.: An HMM-based over-segmentation method for touching Chinese handwriting recognition. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR). IEEE (2016)
Su, Z., et al.: Continuous handwritten Chinese character segmentation based on HMM identifier. In: Chinese Conference on Pattern Recognition (2007)
Yann, L., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, Z., Liu, J., Gu, C. (2018). A Chinese Handwriting Word Segmentation Method via Faster R-CNN. In: Park, J., Loia, V., Yi, G., Sung, Y. (eds) Advances in Computer Science and Ubiquitous Computing. CUTE CSA 2017 2017. Lecture Notes in Electrical Engineering, vol 474. Springer, Singapore. https://doi.org/10.1007/978-981-10-7605-3_77
Download citation
DOI: https://doi.org/10.1007/978-981-10-7605-3_77
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-7604-6
Online ISBN: 978-981-10-7605-3
eBook Packages: EngineeringEngineering (R0)