Benchmarking discriminative approaches for word spotting in handwritten documents

Gautier Bideault (1, 2) , Luc Mioulet (1, 2) , Clément Chatelain (2, 1) , Thierry Paquet (1, 2)

1 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
2 DocApp - LITIS - Equipe Apprentissage

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.

Mots clés: Hidden Markov models; Feature extraction; Benchmark testing; Decoding; Conferences

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Gautier Bideault, Luc Mioulet, Clément Chatelain, Thierry Paquet. Benchmarking discriminative approaches for word spotting in handwritten documents. 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Aug 2015, Tunis, France. pp.201-205, ⟨10.1109/ICDAR.2015.7333752⟩. ⟨hal-02087620⟩