Stochastic error-correcting parsing for OCR post-processing

Pérez-Cortés, Juan-Carlos; Amengual, Juan Carlos; Arlandis, Joaquim; Llobet, Rafael

doi:10.1109/icpr.2000.902944

Cited by 27 publications

(18 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The method consists of building and composing WFSTs that encode different pieces of information and represent distinct models, extending the ideas of language modeling through Stochastic Error Correcting Parsing proposed in [9] and [15].…”

Section: Description Of the Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Composition of Constraint, Hypothesis and Error Models to improve interaction in Human–Machine Interfaces

Navarro-Cerdan¹,

Llobet²,

Arlandis³

et al. 2016

Information Fusion

View full text Add to dashboard Cite

a b s t r a c tAlthough there are many tasks where output strings are automatically generated from a set of evidence, they are not perfect and human intervention is often required to correct the result. In this paper we present a generic Symbol Input Interaction Method for Human-Machine Interfaces that combines multisource information: an input Hypothesis Model, an Error Model, a Constraint Model and a user interaction scheme.We use Weighted Finite-State Transducers (WFSTs) to represent the different sources of information available: the initial hypotheses, the possible errors, the constraints imposed by the task (interaction language) and the user input. The fusion of these models to find the most probable output string can be performed efficiently by using carefully selected transducer operations. The proposed system initially suggests an output based on the set of hypotheses, possible errors and Constraint Models. Then, if human intervention is needed, a multimodal approach, where the user input is combined with the aforementioned models, is applied to produce, with a minimum user effort, the desired output. This approach offers the practical advantages of a de-coupled model (e.g. input-system + parameterized rules + post-processor), keeping at the same time the error-recovery power of an integrated approach, where all the steps of the process are performed in the same formal machine (as in a typical HMM in speech recognition) to avoid that an error at a given step remains unrecoverable in the subsequent steps. After a presentation of the theoretical basis of the proposed multisource information system, its application to two real world problems, as an example of the possibilities of this architecture, is addressed. The experimental results obtained demonstrate that a significant user effort can be saved when using the proposed procedure. A simple demonstration, to better understand and evaluate the proposed system, is available on the web https://demos.iti.upv.es/hi/.

show abstract

Section: Description Of the Methodsmentioning

confidence: 99%

“…More sophisticated methods based on n−grams or on finite-state machines have also been extensively studied [6][7][8][9]. In them, a candidate input string is parsed and an output string is generated from the set of transitions in the automaton with the lowest cost (highest probability).…”

Section: Introductionmentioning

confidence: 99%

Composition of Constraint, Hypothesis and Error Models to improve interaction in Human–Machine Interfaces

Navarro-Cerdan¹,

Llobet²,

Arlandis³

et al. 2016

Information Fusion

View full text Add to dashboard Cite

show abstract

“…A common goal of OCR post-processing systems [2] is to ensure that the words or sentences generated by corrections to the OCR output are correct in the sense that they belong to the language of the task and the specialty. The key issue of post-processing is how to use context information to determine a plausible word from multiple candidate word as a final result to be outputted.…”

Section: Ocr Post-processing Techniquesmentioning

confidence: 99%

Research on OCR Post-processing Applications for Handwritten Recognition Based on Analysis of Scientific Materials

Hu¹,

Lin²,

Wu³

2011

Advances in Computer Science, Intelligent System and Environment

View full text Add to dashboard Cite

Abstract. This paper studied the application of OCR post-processing techniques in Real estate transactions registration and proposed a dictionarybased post-processing method. This paper introduced briefly the design of database and post-processing program of this system. Average accuracy rate was enhanced largely compared to that of pretreatment when the system conducted models test. The experimental results showed that this model was very practical, and can significantly improve the recognition accuracy rate, which verified the validity of the approach.

show abstract

“…In the past, most of the studies in error detection [2], [3] have focussed on English or very few Latin languages like German. In 1992, Kukich [1] performed experimental analysis with merely few thousands of words, while the methods discussed in 2011 by Smith [4] use a corpus as large as 100 Billion words.…”

Section: Introductionmentioning

confidence: 99%

Error Detection in Highly Inflectional Languages

Sankaran

Jawahar

2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract-Error detection in OCR output using dictionaries and statistical language models (SLMs) have become common practice for some time now, while designing post-processors. Multiple strategies have been used successfully in English to achieve this. However, this has not yet translated towards improving error detection performance in many inflectional languages, specially Indian languages. Challenges such as large unique word list, lack of linguistic resources, lack of reliable language models, etc. are some of the reasons for this. In this paper, we investigate the major challenges in developing error detection techniques for highly inflectional Indian languages. We compare and contrast several attributes of English with inflectional languages such as Telugu and Malayalam. We make observations by analyzing statistics computed from popular corpora and relate these observations to the error detection schemes. We propose a method which can detect errors for Telugu and Malayalam, with an F-Score comparable to some of the less inflectional languages like Hindi. Our method learns from the error patterns and SLMs.

show abstract

Stochastic error-correcting parsing for OCR post-processing

Cited by 27 publications

References 12 publications

Composition of Constraint, Hypothesis and Error Models to improve interaction in Human–Machine Interfaces

Composition of Constraint, Hypothesis and Error Models to improve interaction in Human–Machine Interfaces

Research on OCR Post-processing Applications for Handwritten Recognition Based on Analysis of Scientific Materials

Error Detection in Highly Inflectional Languages

Contact Info

Product

Resources

About