A document retrieval method from handwritten characters based on OCR and character shape information

Kameshiro, T.; Hirano, Teruaki; Okada, Y.; Yoda, F.

doi:10.1109/icdar.2001.953859

Cited by 5 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OCR is widely used for many realworld applications, including automated data entry and license plate recognition [39]. OCR can also serve as the main preprocessing step for natural language processing (NLP) tasks such as text classification [2,31,63], document retrieval [17,26,51], machine translation [19,62], and even cancer classification [66]. All of these applications critically depend on the correctness of OCR because the consequences of mistakes are very serious-from wrong cars being fined for violations to incorrect medical diagnoses.…”

Section: Optical Character Recognitionmentioning

confidence: 99%

Fooling OCR Systems with Adversarial Text Images

Song,

Shmatikov

2018

Preprint

View full text Add to dashboard Cite

We demonstrate that state-of-the-art optical character recognition (OCR) based on deep learning is vulnerable to adversarial images. Minor modifications to images of printed text, which do not change the meaning of the text to a human reader, cause the OCR system to "recognize" a different text where certain words chosen by the adversary are replaced by their semantic opposites. This completely changes the meaning of the output produced by the OCR system and by the NLP applications that use OCR for preprocessing their inputs.

show abstract

Section: Optical Character Recognitionmentioning

confidence: 99%

Fooling OCR Systems with Adversarial Text Images

Song,

Shmatikov

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…For document retrieval from large database, it is necessary to build an index containing multiple candidate recognition results so as to overcome the recognition error. According to the indexing technique, handwritten document retrieval methods can be categorized into two groups: indexing by character recognition (transcription) 4,17,18 and lexicondriven indexing. 1,42 Transcription-based text search relies on the character recognition accuracy.…”

Section: Introductionmentioning

confidence: 99%

Keyword Spotting From Online Chinese Handwritten Documents Using One-Versus-All Character Classification Model

Zhang

Wang

Liu

et al. 2013

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

In this paper, we propose a method for text-query-based keyword spotting from online Chinese handwritten documents using character classi¯cation model. The similarity between the query word and handwriting is obtained by combining the character classi¯cation scores. The classi¯er is trained by one-versus-all strategy so that it gives high similarity to the target class and low scores to the others. Using character classi¯cation-based word similarity also helps overcome the out-of-vocabulary (OOV) problem. We use a character-synchronous dynamic search algorithm to e±ciently spot the query word in large database. The retrieval performance is further improved by using competing character confusion and writer-adaptive thresholds. Our experimental results on a large handwriting database CASIA-OLHWDB justify the superiority of oneversus-all trained classi¯ers and the bene¯ts of con¯dence transformation, character confusion and adaptive thresholds. Particularly, a one-versus-all trained prototype classi¯er performs as well as a linear support vector machine (SVM) classi¯er, but consumes much less storage of index¯le. The experimental comparison with keyword spotting based on handwritten text recognition also demonstrates the e®ectiveness of the proposed method.

show abstract

“…We will not be able to take full advantage of this enormous store of document images without using new document image retrieval techniques, and. many investigators have already contributed to the development of these techniques [1,2,3].…”

Section: Introductionmentioning

confidence: 99%

Document Retrieval System Tolerant of Segmentation Errors of Document Images

Nagasaki

Takahashi

Marukawa

Ninth International Workshop on Frontiers in Handwriting Recognition

View full text Add to dashboard Cite

This paper describes a new document retrieval method that is tolerant of OCR segmentation errors in document images. To overcome the segmentation and recognition errors that most OCR-based retrieval systems suffer from, the proposed method consists of two processing phases. First, the OCR engine first generates multiple character-segmentation and recognition hypotheses. Then the retrieval engine extracts keywords from the recognition hypotheses by using lexicon-driven dynamic programming (DP) matching. We have applied this method to both handwritten and printed document images and have demonstrated its effectiveness in reducing false drops and false alarms.

show abstract

A document retrieval method from handwritten characters based on OCR and character shape information

Cited by 5 publications

References 4 publications

Fooling OCR Systems with Adversarial Text Images

Fooling OCR Systems with Adversarial Text Images

Keyword Spotting From Online Chinese Handwritten Documents Using One-Versus-All Character Classification Model

Document Retrieval System Tolerant of Segmentation Errors of Document Images

Contact Info

Product

Resources

About