Camera-based Kanji OCR for mobile-phones: practical issues

Koga, Masashi; Mine, Ryuji; Kameyama, T.; Takahashi, Tomohiro; Yamazaki, Minoru; Yamaguchi, Takuma

doi:10.1109/icdar.2005.65

Cited by 35 publications

(20 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we discuss the implications of our findings. Existing machine-based image search or translation applications (e.g., [14,19], Word Lens and Goggles) provide very limited performance in real world conditions (such as complex background, dark environment, blurred photos, irregular fonts/handwritings), and cannot satisfy users who want to ask concrete questions. Whereas the proposed crowdsourcing-based approach showed the potential to deliver reliable service under above-mentioned situations and answer user's concrete questions on demand.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Drawing on mobile crowds via social media

et al. 2011

View full text Add to dashboard Cite

Recent years have witnessed the impact of crowdsourcing model, social media, and pervasive computing. We believe that the more significant impact is latent in the convergence of these ideas on the mobile platform. In this paper, we introduce a mobile crowdsourcing platform that is built on top of social media. A mobile crowdsourcing application called UbiAsk is presented as one study case. UbiAsk is designed for assisting foreign visitors by involving the local crowd to answer their imagebased questions at hand in a timely fashion. Existing social media platforms are used to rapidly allocate microtasks to a wide network of local residents. The resulting data are visualized using a mapping tool as well as augmented reality (AR) technology, result in a visual information pool for public use. We ran a controlled field experiment in Japan for 6 weeks with 55 participants. The results demonstrated a reliable performance on response speed and response quantity: half of the requests were answered within 10 min, 75% of requests were answered within 30 min, and on average every request had 4.2 answers. Especially in the afternoon, evening and night, nearly 88% requests were answered in average approximately 10 min, with more than 4 answers per request. In terms of participation motivation, we found the top active crowdworkers were more driven by intrinsic motivations rather than any of the extrinsic incentives (game-based incentives and social incentives) we designed.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Most of them applied ORC technologies to recognize images and then use machine translation technologies to translate the text into desired language. Masashi Koga et al [19] discussed a camera-based mobile image translation application using Kanji OCR. Their main target source text is machine-printed documents.…”

Section: Mobile Image Search and Translationmentioning

confidence: 99%

Drawing on mobile crowds via social media

et al. 2011

View full text Add to dashboard Cite

show abstract

“…A similar system is presented for Chinese-English mixed script business card images in [10]. An outline of a prototype Kanji OCR for recognizing machine printed Japanese texts and translating them into English is proposed in [11]. An approach of character recognition system for Chinese scripts has been presented in [12].…”

Section: Previous Workmentioning

confidence: 99%

Optical Character Recognition from Text Image

Jana¹,

Chowdhury²,

Islam³

2014

IJCATR

View full text Add to dashboard Cite

Optical Character Recognition (OCR) is a system that provides a full alphanumeric recognition of printed or handwritten characters by simply scanning the text image. OCR system interprets the printed or handwritten characters image and converts it into corresponding editable text document. The text image is divided into regions by isolating each line, then individual characters with spaces. After character extraction, the texture and topological features like corner points, features of different regions, ratio of character area and convex area of all characters of text image are calculated. Previously features of each uppercase and lowercase letter, digit, and symbols are stored as a template. Based on the texture and topological features, the system recognizes the exact character using feature matching between the extracted character and the template of all characters as a measure of similarity.

show abstract

“…On the other hand, Koga et al proposed discriminant feature extraction followed by dictionary word matching [15], which also showed significant improvement. Shin et al adopted a super-resolution method as an image restoration from a single image for a biometric technique of iris recognition [16].…”

Section: Related Workmentioning

confidence: 99%

Design and Implementation of OCR Correction Model for Numeric Digits based on a Context Sensitive and Multiple Streams

2011

The KIPS Transactions:PartD

View full text Add to dashboard Cite

On an automated business document processing system maintaining financial data, errors on query based retrieval of numbers are critical to overall performance and usability of the system. Automatic spelling correction methods have been emerged and have played important role in development of information retrieval system. However scope of the methods was limited to the symbols, for example alphabetic letter strings, which can be reserved in the form of trainable templates or custom dictionary. On the other hand, numbers, a sequence of digits, are not the objects that can be reserved into a dictionary but a pure markov sequence. In this paper we proposed a new OCR model for spelling correction for numbers using the multiple streams and the context based correction on top of probabilistic information retrieval framework.We implemented the proposed error correction model as a sub-module and integrated into an existing automated invoice document processing system. We also presented the comparative test results that indicated significant enhancement of overall precision of the system by our model.

show abstract

Camera-based Kanji OCR for mobile-phones: practical issues

Cited by 35 publications

References 5 publications

Drawing on mobile crowds via social media

Drawing on mobile crowds via social media

Optical Character Recognition from Text Image

Design and Implementation of OCR Correction Model for Numeric Digits based on a Context Sensitive and Multiple Streams

Contact Info

Product

Resources

About