scispace - formally typeset
Search or ask a question
Author

Toshihiro Kanahori

Other affiliations: University of Birmingham
Bio: Toshihiro Kanahori is an academic researcher from University of Tsukuba. The author has contributed to research in topics: Braille & Software. The author has an hindex of 7, co-authored 15 publications receiving 282 citations. Previous affiliations of Toshihiro Kanahori include University of Birmingham.

Papers
More filters
Proceedings ArticleDOI
20 Nov 2003
TL;DR: An integrated OCR system for mathematical documents, called INFTY, is presented, which shows high character recognition rates on both mathematical expressions and ordinary texts, and sufficient performance on the structure analysis of the mathematical expressions.
Abstract: An integrated OCR system for mathematical documents, called INFTY, is presented. INFTY consists of four procedures, i.e., layout analysis, character recognition, structure analysis of mathematical expressions, and manual error correction. In those procedures, several novel techniques are utilized for better recognition performance. Experimental results on about 500 pages of mathematical documents showed high character recognition rates on both mathematical expressions and ordinary texts, and sufficient performance on the structure analysis of the mathematical expressions.

182 citations

Book ChapterDOI
07 Jul 2004
TL;DR: Infty as mentioned in this paper is a practical integrated system for scientific documents including mathematical formulae, which consists of three components of applications: an OCR system named "InftyReader", an editor named ''InftyEditor'' and converting tools into various formats.
Abstract: This paper describes shortly a practical integrated system for scientific documents including mathematical formulae, named ‘Infty’ The system consists of three components of applications: an OCR system named ‘InftyReader’, an editor named ‘InftyEditor’ and converting tools into various formats Those applications are linked each other via XML files

49 citations

Proceedings ArticleDOI
03 Aug 2003
TL;DR: Improvements in the two improved processes, the detection of matrices and the segmentation of elements, are described and the experimental results are reported.
Abstract: We proposed a method for recognizing matrices which contain abbreviation symbols, and a format for representing the structure of matrices, and reported experimental results in our paper (2002). The method consisted of 4 processes: detection of matrices, segmentation of elements, construction of networks and analysis of the matrix structure. In the paper, our work is described with a focus on the construction of networks and the analysis of the matrix structure. However, we concluded that improvements in the other two processes were very important for obtaining a high accuracy rate for recognition. In this paper, we describe the two improved processes, the detection of matrices and the segmentation of elements, and we report the experimental results.

15 citations

Book ChapterDOI
11 Aug 2006
TL;DR: A first step towards an integrated system of semantic validation and correction of mathematical formula recognition is presented by combining the Infty system with a semantic analyser for matrix expressions.
Abstract: Capturing and understanding mathematics from print form is an important task in translating written mathematical knowledge into electronic form. While the problem of syntactically recognising mathematical formulas from scanned images has received attention, very little work has been done on semantic validation and correction of recognised formulas. We present a first step towards such an integrated system by combining the Infty system with a semantic analyser for matrix expressions. We applied the combined system in experiments on the semantic analysis of matrix images scanned from textbooks. While the first results are encouraging, they also demonstrate many ambiguities one has to deal with when analysing matrix expressions in different contexts. We give a detailed overview of the problems we encountered that motivate further research into semantic validation of mathematical formula recognition.

10 citations

Proceedings ArticleDOI
27 Apr 2006
TL;DR: A new system that can refine a text embedded PDF document recognizing the PDF as images and integrating its text information into the recognition results of Infty is proposed.
Abstract: We are developing a recognition system, named 'Infty', for scientific documents including those with mathematical formulae. In this paper, we propose a new system that can refine a text embedded PDF document recognizing the PDF as images and integrating its text information into the recognition results of Infty. This system can be combined with other OCR systems that output recognition results as text embedded in a PDF document. Using this system, mathematical information can be added to books, journals and papers in existing digital libraries. We evaluate effects of this system, comparing its recognition rates with those of ABBYY FineReader. The evaluation shows that this system can add mathematical information to PDF documents generated by FineReader without loss of quality of the ordinary text parts.

8 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: This paper surveys the state of the art in recognition and retrieval of mathematical expressions, organized around four key problems in math retrieval (query construction, normalization, indexing, and relevance feedback), and four key problem in math recognition (detecting expressions, detecting and classifying symbols, analyzing symbol layout, and constructing a representation of meaning).
Abstract: Document recognition and retrieval technologies complement one another, providing improved access to increasingly large document collections. While recognition and retrieval of textual information is fairly mature, with wide-spread availability of optical character recognition and text-based search engines, recognition and retrieval of graphics such as images, figures, tables, diagrams, and mathematical expressions are in comparatively early stages of research. This paper surveys the state of the art in recognition and retrieval of mathematical expressions, organized around four key problems in math retrieval (query construction, normalization, indexing, and relevance feedback), and four key problems in math recognition (detecting expressions, detecting and classifying symbols, analyzing symbol layout, and constructing a representation of meaning). Of special interest is the machine learning problem of jointly optimizing the component algorithms in a math recognition system, and developing effective indexing, retrieval and relevance feedback algorithms for math retrieval. Another important open problem is developing user interfaces that seamlessly integrate recognition and retrieval. Activity in these important research areas is increasing, in part because math notation provides an excellent domain for studying problems common to many document and graphics recognition and retrieval applications, and also because mature applications will likely provide substantial benefits for education, research, and mathematical literacy.

267 citations

Proceedings ArticleDOI
09 Oct 2005
TL;DR: The development of the tactile graphics assistant is summarized, which will enable tactile graphics specialists to be more efficient in creating tactile graphics both in batches and individually.
Abstract: Access to graphical images (bar charts, diagrams, line graphs, etc.) that are in a tactile form (representation through which content can be accessed by touch) is inadequate for students who are blind and take mathematics, science, and engineering courses. We describe our analysis of the current work practices of tactile graphics specialists who create tactile forms of graphical images. We propose automated means by which to improve the efficiency of current work practices.We describe the implementation of various components of this new automated process, which includes image classification, segmentation, simplification, and layout. We summarize our development of the tactile graphics assistant, which will enable tactile graphics specialists to be more efficient in creating tactile graphics both in batches and individually. We describe our unique team of researchers, practitioners, and student consultants who are blind, all of whom are needed to successfully develop this new way of translating tactile graphics.

116 citations

Journal ArticleDOI
TL;DR: In this article, a formal model for the recognition of on-line handwritten mathematical expressions using 2D stochastic context-free grammars and hidden Markov models is described.

107 citations

Journal ArticleDOI
TL;DR: SectLabel is described, a module that further develops existing software to detect the logical structure of a document from existing PDF files, using the formalism of conditional random fields.
Abstract: Scholarly digital libraries increasingly provide analytics to information within documents themselves. This includes information about the logical document structure of use to downstream components, such as search, navigation, and summarization. In this paper, the authors describe SectLabel, a module that further develops existing software to detect the logical structure of a document from existing PDF files, using the formalism of conditional random fields. While previous work has assumed access only to the raw text representation of the document, a key aspect of this work is to integrate the use of a richer representation of the document that includes features from optical character recognition OCR, such as font size and text position. Experiments reveal that using such rich features improves logical structure detection by a significant 9 F1 points, over a suitable baseline, motivating the use of richer document representations in other digital library applications.

104 citations

Patent
Luc Vincent1, Ray Smith1
15 Jul 2011
TL;DR: In this paper, the authors present techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process, including documents.
Abstract: Techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process.

91 citations