Mathematical symbol hypothesis recognition with rejection option

Frank Julca-Aguilar 1, 2 Nina Hirata 1 Christian Viard-Gaudin 2 Harold Mouchère 2 Sofiane Medjkoune 2
2 irccyn-ivc
IRCCyN - Institut de Recherche en Communications et en Cybernétique de Nantes
Abstract : In the context of handwritten mathematical expressions recognition, a first step consist on grouping strokes (segmentation) to form symbol hypotheses: groups of strokes that might represent a symbol. Then, the symbol recognition step needs to cope with the identification of wrong segmented symbols (false hypotheses). However, previous works on symbol recognition consider only correctly segmented symbols. In this work, we focus on the problem of mathematical symbol recognition where false hypotheses need to be identified. We extract symbol hypotheses from complete handwritten mathematical expressions and train artificial neural networks to perform both symbol classification of true hypotheses and rejection of false hypotheses. We propose a new shape context-based symbol descriptor: fuzzy shape context. Evaluation is performed on a publicly available dataset that contains 101 symbol classes. Results show that the fuzzy shape context version outperforms the original shape context. Best recognition and false acceptance rates were obtained using a combination of shape contexts and online features: 86% and 17.5% respectively. As false rejection rate, we obtained 8.6% using only online features.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01096531
Contributor : Harold Mouchère <>
Submitted on : Wednesday, December 17, 2014 - 4:16:48 PM
Last modification on : Wednesday, December 19, 2018 - 3:02:08 PM
Long-term archiving on : Monday, March 23, 2015 - 3:41:27 PM

File

Aguilar_ICFHR2014_final.pdf
Publisher files allowed on an open archive

Identifiers

Collections

Citation

Frank Julca-Aguilar, Nina Hirata, Christian Viard-Gaudin, Harold Mouchère, Sofiane Medjkoune. Mathematical symbol hypothesis recognition with rejection option. 14th International Conference on Frontiers in Handwriting Recognition, Sep 2014, Crete, Greece. pp.500 -- 504, ⟨10.1109/ICFHR.2014.90⟩. ⟨hal-01096531⟩

Share

Metrics

Record views

397

Files downloads

506