Search

[EN] State-of-the-art Handwritten Text Recognition (HTR) systems allow transcribers to speed-up the transcription of handwritten text images. These systems provide transcribers an initial draft transcription that can be corrected with less effort than transcribing the handwritten text images from scratch. Currently, even the draft transcriptions offered by the most advanced HTR systems contain errors. Therefore, the supervision of this draft by a human transcriber is still necessary to obtain the correct transcription of the handwritten text images. This supervision can be eased by using interactive and assistive transcription systems, where the transcriber and the automatic system cooperate in the amending process. In this paper, the draft transcription is provided by an HTR system based on Convolutional and Recurrent Neural Networks with Bidirectional Long-Short Term Memory units, and the assistive system is fed by lattices generated by using Weighted Finite State Transducers. The influence of the lexicon and language restrictions on the performance of our computer assisted transcription system is evaluated on three historical manuscripts. The transcriptions offered by the proposed HTR system present very low error rates for the studied historical manuscripts. However, our assistive transcription system without lexicon or language restrictions is able to provide an additional reduction on the human effort required to correct the transcriptions in more than 50% over the transcriptions offered by the HTR system. (C) 2020 Elsevier B.V. All rights reserved.

[EN] Handwritten document transcription aims to obtain the contents of a document to provide efficient information access to, among other, digitised historical documents. The increasing number of historical documents published by libraries and archives makes this an important task. In this context, the use of image processing and understanding techniques in conjunction with assistive technologies reduces the time and human effort required for obtaining the final perfect transcription. The assistive transcription system proposes a hypothesis, usually derived from a recognition process of the handwritten text image. Then, the professional transcriber feedback can be used to obtain an improved hypothesis and speed-up the final transcription. In this framework, a speech signal corresponding to the dictation of the handwritten text can be used as an additional source of information. This multimodal approach, that combines the image of the handwritten text with the speech of the dictation of its contents, could make better the hypotheses (initial and improved) offered to the transcriber. In this paper we study the feasibility of a multimodal interactive transcription system for an assistive paradigm known as Computer Assisted Transcription of Text Images. Different techniques are tested for obtaining the multimodal combination in this framework. The use of the proposed multimodal approach reveals a significant reduction of transcription effort with some multimodal combination techniques, allowing for a faster transcription process.

This is the peer reviewed version of the following article: Granell, Emilio, Romero, Verónica, Martínez-Hinarejos, Carlos-D.. (2018). Multimodality, interactivity, and crowdsourcing for document transcription.Computational Intelligence, 34, 2, 398-419. DOI: 10.1111/coin.12169, which has been published in final form at http://doi.org/10.1111/coin.12169.. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving., [EN] Knowledge mining from documents usually use document engineering techniques that allow the user to access the information contained in documents of interest. In this framework, transcription may provide efficient access to the contents of handwritten documents. Manual transcription is a time-consuming task that can be sped up by using different mechanisms. A first possibility is employing state-of-the-art handwritten text recognition systems to obtain an initial draft transcription that can be manually amended. A second option is employing crowdsourcing to obtain a massive but not error-free draft transcription. In this case, when collaborators employ mobile devices, speech dictation can be used as a transcription source, and speech and handwritten text recognition can be fused to provide a better draft transcription, which can be amended with even less effort. A final option is using interactive assistive frameworks, where the automatic system that provides the draft transcription and the transcriber cooperate to generate the final transcription. The novel contributions presented in this work include the study of the data fusion on a multimodal crowdsourcing framework and its integration with an interactive system. The use of the proposed solutions reduces the required transcription effort and optimizes the overall performance and usability, allowing for a better transcription process.

[EN] The digitization of historical handwritten document images is important for the preservation of cultural heritage. Moreover, the transcription of text images obtained from digitization is necessary to provide efficient information access to the content of these documents. Handwritten Text Recognition (HTR) has become an important research topic in the areas of image and computational language processing that allows us to obtain transcriptions from text images. State-of-the-art HTR systems are, however, far from perfect. One difficulty is that they have to cope with image noise and handwriting variability. Another difficulty is the presence of a large amount of Out-Of-Vocabulary (OOV) words in ancient historical texts. A solution to this problem is to use external lexical resources, but such resources might be scarce or unavailable given the nature and the age of such documents. This work proposes a solution to avoid this limitation. It consists of associating a powerful optical recognition system that will cope with image noise and variability, with a language model based on sub-lexical units that will model OOV words. Such a language modeling approach reduces the size of the lexicon while increasing the lexicon coverage. Experiments are first conducted on the publicly available Rodrigo dataset, which contains the digitization of an ancient Spanish manuscript, with a recognizer based on Hidden Markov Models (HMMs). They show that sub-lexical units outperform word units in terms of Word Error Rate (WER), Character Error Rate (CER) and OOV word accuracy rate. This approach is then applied to deep net classifiers, namely Bi-directional Long-Short Term Memory (BLSTMs) and Convolutional Recurrent Neural Nets (CRNNs). Results show that CRNNs outperform HMMs and BLSTMs, reaching the lowest WER and CER for this image dataset and significantly improving OOV recognition.