Benchmarking discriminative approaches for word spotting in handwritten documents
| Autor: | Gautier Bideault, Luc Mioulet, Thierry Paquet, Clément Chatelain |
|---|---|
| Přispěvatelé: | Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU), Equipe Apprentissage (DocApp - LITIS), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie) |
| Rok vydání: | 2015 |
| Předmět: |
Benchmark testing
business.industry Computer science Decoding Speech recognition Conferences [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Benchmarking Spotting computer.software_genre Discriminative model Handwriting recognition Benchmark (computing) Feature extraction Hidden Markov models Artificial intelligence business Hidden Markov model computer Word (computer architecture) Natural language processing |
| Zdroj: | ICDAR 2015 13th International Conference on Document Analysis and Recognition (ICDAR) 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Aug 2015, Tunis, France. pp.201-205, ⟨10.1109/ICDAR.2015.7333752⟩ |
| DOI: | 10.1109/icdar.2015.7333752 |
| Popis: | International audience; In this article, we propose to benchmark the most popular methods for word spotting in handwritten documents. The benchmark includes a pure HMM approach, as well as hybrid discriminative methods MLP-HMM, CRF-HMM, RNN-HMM and BLSTM-CTC-HMM. This study enables us to observe the increase ratio of performance provided by each discriminative stage compared with the pure generative HMM approach. Moreover, we put forward the different abilities of all these discriminative stages from the simplest MLP to the most complex and current state of the art BLSTM-CTC. We also propose a more specific and original study on BLSTM-CTC, showing that when used as a lexicon-free recognizer, it can reach very interesting word-spotting performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|