a component-based on-line handwritten tibetan character recognition method using conditional random field

ISCAS OpenIR

	a component-based on-line handwritten tibetan character recognition method using conditional random field
	Ma Long-Long; Wu Jian
	2012
会议名称	13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012
会议录名称	Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR
页码	704-709
会议日期	September 18, 2012 - September 20, 2012
会议地点	Bari, Italy
收录类别	EI
ISSN	1550-5235
ISBN	9780769547749
部门归属	(1) National Engineering Research Center of Fundamental Software Institute of Software Chinese Academy of Sciences Beijing China
摘要	This paper presents a new component-based recognition method using conditional random field (CRF) for on-line handwritten Tibetan characters. The character pattern is over-segmented into a sequence of sub-structure blocks. Integrated segmentation and recognition method based on the CRF model is used to determine the component segmentation points from these block sequences. The CRF model combines component shape likelihood with geometrical likelihood. The parameters are learned using an energy minimization method. We build a componentbased spelling rule model to ensure the correct component appearing at a specific structural position. A character-component generation model is presented to reduce component recognition error rate and accelerate the recognition process. Experimental results on MRG-OHTC database show that the proposed method gives promising performance comparing with the holistic method and the component-based conventional path evaluation method. © 2012 IEEE.; This paper presents a new component-based recognition method using conditional random field (CRF) for on-line handwritten Tibetan characters. The character pattern is over-segmented into a sequence of sub-structure blocks. Integrated segmentation and recognition method based on the CRF model is used to determine the component segmentation points from these block sequences. The CRF model combines component shape likelihood with geometrical likelihood. The parameters are learned using an energy minimization method. We build a componentbased spelling rule model to ensure the correct component appearing at a specific structural position. A character-component generation model is presented to reduce component recognition error rate and accelerate the recognition process. Experimental results on MRG-OHTC database show that the proposed method gives promising performance comparing with the holistic method and the component-based conventional path evaluation method. © 2012 IEEE.
关键词	Random Processes
主办者	Presidenza del Consiglio dei Ministri; Governo Italiano; Ministero dello Sviluppo Economico; IAPR; Rete Puglia
语种	英语
内容类型	会议论文
URI标识	http://ir.iscas.ac.cn/handle/311060/15911
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Ma Long-Long,Wu Jian. a component-based on-line handwritten tibetan character recognition method using conditional random field[C],2012:704-709.