Arabic Printed Word Recognition Using Windowed Bernoulli HMMs
Autor: | Adrià Giménez, Alfons Juan, Ihab Khoury, Jesús Andrés-Ferrer |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2013 |
Předmět: |
Computer science
Arabic Speech recognition Feature extraction ESTADISTICA E INVESTIGACION OPERATIVA ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Context (language use) 02 engineering and technology 01 natural sciences Bernoulli HMMs Arabic Printed Recognition Discriminative model Sliding window protocol 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 010306 general physics Hidden Markov model APTI Binary image Repositioning Sliding Window Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) language.human_language ComputingMethodologies_PATTERNRECOGNITION Computer Science::Computer Vision and Pattern Recognition Word recognition language 020201 artificial intelligence & image processing LENGUAJES Y SISTEMAS INFORMATICOS Word (computer architecture) |
Zdroj: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia instname Image Analysis and Processing – ICIAP 2013 ISBN: 9783642411809 ICIAP (1) |
DOI: | 10.1007/978-3-642-41181-6_34 |
Popis: | [EN] Hidden Markov Models (HMMs) are now widely used for off-line text recognition in many languages and, in particular, Arabic. In previous work, we proposed to directly use columns of raw, binary image pixels, which are directly fed into embedded Bernoulli (mixture) HMMs, that is, embedded HMMs in which the emission probabilities are modeled with Bernoulli mixtures. The idea was to by-pass feature extraction and to ensure that no discriminative information is filtered out during feature extraction, which in some sense is integrated into the recognition model. More recently, we extended the column bit vectors by means of a sliding window of adequate width to better capture image context at each horizontal position of the word image. However, these models might have limited capability to properly model vertical image distortions. In this paper, we have considered three methods of window repositioning after window extraction to overcome this limitation. Each sliding window is translated (repositioned) to align its center to the center of mass. Using this approach, state-of-art results are reported on the Arabic Printed Text Recognition (APTI) database. The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement no 287755. Also supported by the Spanish Government (Plan E, iTrans2 TIN2009-14511 and AECID 2011/2012 grant). |
Databáze: | OpenAIRE |
Externí odkaz: |