A SVM-HMM Based Online Classifier for Handwritten Chemical Symbols
作者： Yang Zhang , Guangshun Shi , Kai Wang
关键词: Statistical classification 、 Speech recognition 、 Computer science 、 Kernel (linear algebra) 、 Pattern recognition 、 Contextual image classification 、 Support vector machine 、 Artificial intelligence 、 Test data 、 Hidden Markov model 、 Handwriting recognition 、 Classifier (UML)
摘要: This paper presents a novel double-stage classifier for handwritten chemical symbols recognition task. The first stage is rough classification, SVM method used to distinguish non-ring structure (NRS) and organic ring (ORS) symbols, while HMM fine at second stage. A point-sequence-reordering algorithm proposed improve the accuracy of ORS symbols. Our test data set contains 101 9090 training samples 3232 samples. Finally, we obtained top-1 93.10% top-3 98.08% based on set.
ieeecomputersociety.org参考文章(9)
Thorsten Joachims, Making large scale SVM learning practical Technical reports. ,(1999) , 10.17877/DE290R-14262
Alessia Mammone, Marco Turchi, Nello Cristianini, Support vector machines Wiley Interdisciplinary Reviews: Computational Statistics. ,vol. 1, pp. 283- 289 ,(2009) , 10.1002/WICS.49
Tom Y. Ouyang, Randall Davis, Recognition of hand drawn chemical diagrams national conference on artificial intelligence. pp. 846- 851 ,(2007)
Ming Chang, Shi Han, Dongmei Zhang, A Unified Framework for Recognizing Handwritten Chemical Expressions international conference on document analysis and recognition. pp. 1345- 1349 ,(2009) , 10.1109/ICDAR.2009.64
Junko Tokuno, Nobuhito Inami, Shigeki Matsuda, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama, Context-dependent substroke model for HMM-based on-line handwriting recognition international conference on frontiers in handwriting recognition. pp. 78- 83 ,(2002) , 10.1109/IWFHR.2002.1030888
L.R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition Proceedings of the IEEE. ,vol. 77, pp. 267- 296 ,(1989) , 10.1109/5.18626
Xin Wang, Guangshun Shi, Jufeng Yang, The Understanding and Structure Analyzing for Online Handwritten Chemical Formulas international conference on document analysis and recognition. pp. 1056- 1060 ,(2009) , 10.1109/ICDAR.2009.70
Jufeng Yang, Guangshun Shi, Kai Wang, Qian Geng, Qingren Wang, A study of on-line handwritten chemical expressions recognition international conference on pattern recognition. pp. 1- 4 ,(2008) , 10.1109/ICPR.2008.4761824
Yang Zhang, Guangshun Shi, Jufeng Yang, HMM-Based Online Recognition of Handwritten Chemical Symbols international conference on document analysis and recognition. pp. 1255- 1259 ,(2009) , 10.1109/ICDAR.2009.99