Grammar-based techniques for creating ground-truthed sketch corpora

MacLean, Scott; Labahn, George; Lank, Edward; Marzouk, Mirette; Tausky, David

doi:10.1007/s10032-010-0118-4

Cited by 39 publications

(34 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We extract all symbols from a new publicly available, ground-truthed corpus of handwritten mathematical expressions [14], getting 100 different symbol classes. These symbols were written by 20 writers.…”

Section: Dataset and Experiments Resultsmentioning

confidence: 99%

See 1 more Smart Citation

HMM-Based Recognition of Online Handwritten Mathematical Symbols Using Segmental K-Means Initialization and a Modified Pen-Up/Down Feature

Zanibbi

2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract-This paper presents a recognition system based on Hidden Markov Model (HMM) for isolated online handwritten mathematical symbols. We design a continuous left to right HMM for each symbol class and use four online local features, including a new feature: normalized distance to stroke edge. A variant of segmental K-means is used to get initialization of the Gaussian Mixture Models' parameters which represent the observation probability distribution of the HMMs. The system obtains top-1 recognition rate of 82.9% and top-5 recognition rate of 97.8% on a dataset containing 20281 training samples and 2202 testing samples of 93 classes of symbols. For multistroke symbols, the top-1 recognition rate is 74.7% and the top-5 recognition rate is 95.5%. For single-stroke symbols, the top-1 recognition rate is 86.8% and the top-5 recognition rate is 98.9%. applied dynamic time warping algorithm on all the 70 classes of single-stroke symbols. Their top-1 recognition rate is 85.8%, and top-5 recognition rate is 97.0%. Our system gets top-1 recognition rate of 85.5% and top-5 recognition rate of 99.1% on the same 70 classes of singlestroke symbols.

show abstract

Section: Dataset and Experiments Resultsmentioning

confidence: 99%

“…To choose the model size and the number of Gaussian components per state, we did experiments on the ten digits extracted from the corpus of handwritten mathematical expressions [14] to find the effect of number of states and number of Gaussians on the recognition rate. The experiment results are shown in Table I.…”

Section: ) Model Selectionmentioning

confidence: 99%

HMM-Based Recognition of Online Handwritten Mathematical Symbols Using Segmental K-Means Initialization and a Modified Pen-Up/Down Feature

Zanibbi

2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

show abstract

“…Then, the whole system is evaluated by recognizing mathematical expressions. Experimentation was carried out by using MathBrush 3 [23], a large public database of on-line handwritten mathematical expressions. This database was recently made publicly available and there are not comparable results with other systems.…”

Section: Methodsmentioning

confidence: 99%

“…Evaluation and comparison of the structural analysis in mathematical expression recognition has hitherto been difficult because: first, most of the proposals used private data, and second, there has been a lack of standard performance evaluation measures [5,19]. Lately, some public large corpora have been developed [23,32] and also new metrics have been proposed [1,30,41]. Recently a Competition on Recognition of Online Handwritten Mathematical Expressions 1 (CROHME 2011) has been proposed [25].…”

Section: Introductionmentioning

confidence: 99%

Recognition of on-line handwritten mathematical expressions using 2D stochastic context-free grammars and hidden Markov models

Alvaro

Sánchez

Benedí

2014

Pattern Recognition Letters

136

View full text Add to dashboard Cite

This paper describes a formal model for the recognition of on-line handwritten mathematical expressions using 2D stochastic context-free grammars and hidden Markov models. Hidden Markov models are used to recognize mathematical symbols, and a stochastic context-free grammar is used to model the relation between these symbols. This formal model makes possible to use classic algorithms for parsing and stochastic estimation. In this way, first, the model is able to capture many of variability phenomena that appear in on-line handwritten mathematical expressions during the training process. And second, the parsing process can make decisions taking into account only stochastic information, and avoiding heuristic decisions. The proposed model participated in a contest of mathematical expression recognition and it obtained the best results at different levels.

show abstract

“…[7] (off-line) and [8] (online)). As pointed out by both Lapointe and Blostein [2] and Awal et al [3], the math recognition domain now needs standard evaluation metrics to support comparisons of existing and newly developed systems.…”

Section: Previous Work In Evaluating Math Recognitionmentioning

confidence: 99%

Stroke-Based Performance Metrics for Handwritten Mathematical Expressions

Zanibbi

Pillay

Mouchère

et al. 2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract-Evaluating mathematical expression recognition involves a complex interaction of input primitives (e.g. pen/finger strokes), recognized symbols, and recognized spatial structure. Existing performance metrics simplify this problem by separating the assessment of spatial structure from the assessment of symbol segmentation and classification. These metrics do not characterize the overall accuracy of a penbased mathematics recognition, making it difficult to compare math recognition algorithms, and preventing the use of machine learning algorithms requiring a criterion function characterizing overall system performance. To address this problem, we introduce performance metrics that bridge the gap from handwritten strokes to spatial structure. Our metrics are computed using bipartite graphs that represent classification, segmentation and spatial structure at the stroke level. Overall correctness of an expression is measured by counting the number of relabelings of nodes and edges needed to make the bipartite graph for a recognition result match the bipartite graph for ground truth. This metric may also be used with other primitive types (e.g. image pixels).

show abstract

Grammar-based techniques for creating ground-truthed sketch corpora

Cited by 39 publications

References 11 publications

HMM-Based Recognition of Online Handwritten Mathematical Symbols Using Segmental K-Means Initialization and a Modified Pen-Up/Down Feature

HMM-Based Recognition of Online Handwritten Mathematical Symbols Using Segmental K-Means Initialization and a Modified Pen-Up/Down Feature

Recognition of on-line handwritten mathematical expressions using 2D stochastic context-free grammars and hidden Markov models

Stroke-Based Performance Metrics for Handwritten Mathematical Expressions

Contact Info

Product

Resources

About