RWTH OCR: A Large Vocabulary Optical Character Recognition System for Arabic Scripts

Abstract

We present a novel large vocabulary OCR system, which implements a 5 confidence-and margin-based discriminative training approach for model adap-6 tation of an HMM based recognition system to handle multiple fonts, different 7 handwriting styles, and their variations. Most current HMM approaches are HTK 8 based systems which are maximum-likelihood (ML) trained and which try to adapt 9 their models to different writing styles using writer adaptive training, unsupervised 10 clustering, or additional writer specific data. Here, discriminative training based 11 on the Maximum Mutual Information (MMI) and Minimum Phone Error (MPE) 12 criteria are used instead. For model adaptation during decoding, an unsupervised 13 confidence-based discriminative training within a two-pass decoding process is pro-14 posed. Additionally, we use neural network based features extracted by a hierar-15 chical multi-layer-perceptron (MLP) network either in a hybrid MLP/HMM ap-16 proach or to discriminatively retrain a Gaussian HMM system in a tandem approach. 17 The proposed framework and methods are evaluated for closed-vocabulary isolated 18 handwritten word recognition on the IfN/ENIT Arabic handwriting database, where 19 the word-error-rate is decreased by more than 50% relative compared to a ML 20 trained baseline system. Preliminary results for large-vocabulary Arabic machine 21 printed text recognition tasks are presented on a novel publicly available newspaper 22 database.