Markov models for offline handwriting recognition: a survey

Abstract

Since their first inception more than half a century ago, automatic reading systems have evolved substantially, thereby showing impressive performance on machine-printed text. The recognition of handwriting can, however, still be considered an open research problem due to its substantial variation in appearance. With the introduction of Markovian models to the field, a promising modeling and recognition paradigm was established for automatic offline handwriting recognition. However, so far, no standard procedures for building Markov-model-based recognizers could be established though trends toward unified approaches can be identified. It is therefore the goal of this survey to provide a comprehensive overview of the application of Markov models in the research field of offline handwriting recognition, covering both the widely used hidden Markov models and the less complex Markov-chain or n-gram models. First, we will introduce the typical architecture of a Markov-modelbased offline handwriting recognition system and make the reader familiar with the essential theoretical concepts behind Markovian models. Then, we will give a thorough review of the solutions proposed in the literature for the open problems how to apply Markov-model-based approaches to automatic offline handwriting recognition.

Language Identification for Interactive Handwriting Transcription of Multilingual Documents

“…However, automated techniques for document image analysis and handwriting recognition are still far from perfect [4], and thus post-editing automatically generated output is not clearly better than simply ignoring it. Instead, a more effective approach is to follow a sequential, line-by-line transcription of the whole document, in which a continuously retrained system interacts with the user.…”

Segmentation-free optical character recognition for printed Urdu text

“…We have selected to employ hidden Markov models which have been successfully applied to a number of diverse problems including gesture recognition [36][37][38], speech recognition [39], handwriting recognition [38,40], musical score recognition [41], and optical character recognition [10,[42][43][44]. The steps of feature extraction from ligature clusters and subsequent training are discussed in the following subsections.…”

Interactive handwriting recognition with limited user effort

“…State-of-art HTR systems are grounded on the statistical framework [18]. This framework also constitutes a successful approach for CAT in HTR [21,23,29].…”

“…On the other hand, p(w) is the probability of a sentence w and it is usually modelled using a smoothed n-gram language model. This technology is commonly adopted in current state-of-the-art HTR systems [18]. However, even the best systems do not produce an acceptable automatic transcription of these documents [10], and although post-editing is possible, it may not be better than to manually transcribe documents.…”