On-line handwritten formula recognition using statistical methods

Kosmala, A.; Rigoll, Gerhard

doi:10.1109/icpr.1998.711941

Cited by 32 publications

(19 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classification algorithms for these topics include template matching (Connell and Jain, 2000;Nakayama, 1993), decision trees (Belaid and Haton, 1984;Kerrick and Bovik, 1988), neural networks (Dimitriadis and Coronado, 1995;Marzinkewitsch, 1991), hidden Markov models (Koschinski et al, 1995;Kosmala and Rigoll, 1998), parsing grammars (Costagliola et al, 2004;Mas et al, 2010), support vector machines (Bahlmann et al, 2001;El Meseery et al, 2009), or principal component analysis (Deepu et al, 2004;Zhang et al, 2010). Typically, gesture recognition takes place after a "pointer up" event, although it is possible to perform it continuously, in an incremental fashion (Bau and Mackay, 2008;Kristensson and Denby, 2011).…”

Section: Recognizing Gesturesmentioning

confidence: 99%

Context-Aware Gestures for Mixed-Initiative Text Editing UIs

et al. 2014

View full text Add to dashboard Cite

Oxford University PressLeiva, LA.; Alabau, V.; Romero Gómez, V.; Toselli, AH.; Vidal, E. (2015). Contex-aware gestures for mixed-initiative text editings UIs. Interacting with Computers. 27(6):675-696. doi:10.1093/iwc/iwu019. +34 963878172 Email: {luileito,valabau,vromero,ahector,evidal}@prhlt.upv.es This work is focused on enhancing highly interactive text-editing applications with gestures. Concretely, we study CATTI, a handwriting transcription system that follows a corrective feedback paradigm, where both the user and the system collaborate efficiently to produce a high-quality text transcription. CATTI-like applications demand fast and accurate gesture recognition, for which we observed that current gesture recognizers are not adequate enough. In response to this need we developed MinGestures, a parametric context-aware gesture recognizer. Our contributions include a number of stroke features for disambiguating copy-mark gestures from handwritten text, plus the integration of these gestures in a CATTI application. It becomes finally possible to create highly interactive stroke-based textediting interfaces, without worrying to verify the user intent onscreen.We performed a formal evaluation with 22 e-pen users and 32 mouse users using a gesture vocabulary of 10 symbols. MinGestures achieved an outstanding accuracy (less than 1% error rate) with very high performance (less than 1 ms of recognition times). We then integrated MinGestures in a CATTI prototype and tested the performance of the interactive handwriting system when it is driven by gestures. Our results show that using gestures in interactive handwriting applications is both advantageous and convenient when gestures are simple but context-aware. Taken together, this work suggests that text-editing interfaces not only can be easily augmented with simple gestures, but also may substantially improve user productivity.

show abstract

Section: Recognizing Gesturesmentioning

confidence: 99%

Context-Aware Gestures for Mixed-Initiative Text Editing UIs

et al. 2014

View full text Add to dashboard Cite

show abstract

“…There have also been many other methods [16], [17]. Smithies et al [16] present a progressive segmentation method.…”

Section: Related Workmentioning

confidence: 99%

“…Then the first recognized character from the group with highest confidence level will be removed and the process will restart when there is 4 strokes again. Kosmala et al [17] propose a segmentation method based on HMM. Discrete left to right HMMs without skips and with different numbers of states are used.…”

Section: Related Workmentioning

confidence: 99%

Segmenting Handwritten Math Symbols Using AdaBoost and Multi-scale Shape Context Features

Zanibbi

2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract-This paper presents a new symbol segmentation method based on AdaBoost with confidence weighted predictions for online handwritten mathematical expressions. The handwritten mathematical expression is preprocessed and rendered to an image. Then for each stroke, we compute three kinds of shape context features (stroke pair, local neighborhood and global shape contexts) with different scales, 21 stroke pair geometric features and symbol classification scores for the current stroke and stroke pair. The stroke pair shape context features covers the current stroke and the following stroke in time series. The local neighborhood shape context features includes the current stroke and its three nearest neighbor strokes in distance while the global shape context features covers the expression. Principal component analysis (PCA) is used for dimensionality reduction. We use AdaBoost with confidence weighted predictions for classification. The method does not use any language model. To our best knowledge, there is no previous work which uses shape context features for symbol segmentation. Experiment results show the new symbol segmentation method achieves good recall and precision on the CROHME 2012 dataset.

show abstract

“…These include grammar-based approaches (Chou, 1989;Fateman et al, 1996;Chan and Yeung, 2000a;Toyota et al, 2006), tree transformation (Zanibbi et al, 2002), Hidden Markov Models (HMMs) (Kosmala and Rigoll, 1998) and Minimum Spanning Tree Rojas, 2003, 2005 There could also be different ways of interpreting a relationship between two specific symbols. Therefore, we need to identify the most plausible relationship between input symbols.…”

Section: Progressive Structural Analysismentioning

confidence: 99%

“…In the past few decades, there have been many techniques such as Hidden Markov Model (HMM) (Kosmala and Rigoll, 1998), structural matching (Chan and Yeung, 2000b) and neural networks (Brown, 1992) proposed for symbol recognition. Most of these techniques are able to obtain quite satisfactory results.…”

Section: Symbol Recognitionmentioning

confidence: 99%