By Topic

Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on

Date 14-16 Aug. 1995

Go

Filter Results

Displaying Results 1 - 25 of 152
  • Author index

    Publication Year: 1995, Page(s):A1 - A7
    Request permission for commercial reuse | PDF file iconPDF (361 KB)
    Freely Available from IEEE
  • Extraction of slant character candidates from maps using circular templates

    Publication Year: 1995, Page(s):936 - 939 vol.2
    Cited by:  Papers (1)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB)

    The paper proposes a method for extracting slant characters from complicated background figures efficiently and rapidly. In this method, slant character candidates are extracted using the black pixel density features, that is, matching rate of two different sized circular templates, which are inscribing and circumscribing a target character, with an original image. In order to estimate performance... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic understanding of symbol-connected diagrams

    Publication Year: 1995, Page(s):803 - 806 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (392 KB)

    A symbol-connected diagram is mainly composed of symbols and their connections. All symbols can be categorized into two groups: shape symbols and structure symbols. This paper proposes a system for automatic understanding of symbol-connected diagrams based on a graph, called the consistent attributed graph (CAG), which represents the diagram in a bottom-up fashion. The shape symbol processing is c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hyperdocument generation using OCR and icon detection

    Publication Year: 1995, Page(s):1180 - 1183 vol.2
    Cited by:  Papers (1)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    In this contribution we consider the construction of hyperdocuments; converting scanned paper documents into electronic hypertext. Hyperlink creation is automated by analyzing the structure and content of the scanned document. The focus is on hyperlinks between the text and labels in a picture. A number of tools for such hyperlink detection are described. Practical results are presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recursive morphological sieve method for searching pictorial point symbols on maps

    Publication Year: 1995, Page(s):931 - 935 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (552 KB)

    Point symbols on a map represent interesting and significant positional data, such as airports, ski areas and natural parks. Identification of point symbols and finding their positions are important for automatic map understanding. Point symbols on maps may partially overlap on each other. More often they are touched or connected by line symbols, and their background consists of colored and/or tex... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The role of taxonomy in drawing interpretation

    Publication Year: 1995, Page(s):799 - 802 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (476 KB)

    The objective of this paper is to demonstrate how taxonomic structures in knowledge representation can be exploited for drawing interpretation tasks. After a brief survey of the different levels of knowledge representation used by today's interpretation systems, same basic assumptions about the nature of drawing interpretation and the representation of knowledge are discussed. Based on these widel... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Conjoined location and recognition of street names within a postal address delivery line

    Publication Year: 1995, Page(s):1024 - 1027 vol.2
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (392 KB)

    This paper describes a global model designed to jointly detect and recognize a street name within a delivery line of an handwritten address block image. The model used is based on Hidden Markov Models (HMM). The lines are firstly preprocessed, then segmented and characterized by two types of features. We create a HMM for each street name by simply concatenating the corresponding letter models, ele... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classification and functional decomposition of business documents

    Publication Year: 1995, Page(s):563 - 566 vol.2
    Cited by:  Papers (5)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (372 KB)

    This paper describes recent efforts to develop a document classification system. Our classification approach uses two steps: first, the document is sorted by the number of columns and second, functional landmarks are detected to determine the class. Results for detecting and classifying business class documents are included View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Handwritten ZIP code recognition using lexicon free word recognition algorithm

    Publication Year: 1995, Page(s):906 - 910 vol.2
    Cited by:  Papers (16)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (492 KB)

    The paper describes a new approach to ZIP code recognition using a word recognition algorithm, where a numeral string is recognized as a word. The paper also describes an end to end ZIP code recognition system consisting of tilt/slant correction, line segmentation, word segmentation, ZIP code location, as well as the ZIP code recognition. Evaluation tests are performed using address block image sa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A method for table structure analysis using DP matching

    Publication Year: 1995, Page(s):583 - 586 vol.2
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB)

    This paper presents a novel method for table structure analysis. Many documents have table areas, and some have both table and figure areas. It is very important to be able to classify table and figure areas automatically. Furthermore, in tables, the column and row in which a character string is located are very important pieces of information. To detect and analyze table areas, the following meth... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tools for interactive map conversion and vectorization

    Publication Year: 1995, Page(s):927 - 930 vol.2
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB)

    The process of converting an analog map into structured digitized information requires several different operations, which are all time-consuming when performed manually. Strictly automatic processing is not always a possible solution, and an interactive approach can then be an alternative. The paper describes a tool for map conversion, focusing on the functionality for extraction of line structur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A framework for validating recognized results in understanding table-form document images

    Publication Year: 1995, Page(s):536 - 539 vol.2
    Cited by:  Papers (4)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB)

    We address the knowledge representation for understanding table-form documents. In particular, we focus on the knowledge for establishing the correctness of recognized results in addition to the traditional syntactic/constructive-oriented understanding framework. In order to attain to this subject, we introduce the semantic information to specify domains and relationships among individual items de... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient techniques for telephone company line drawing interpretation

    Publication Year: 1995, Page(s):795 - 798 vol.2
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (348 KB)

    In this paper we present the idea of using customizable tools to develop systems to interpret telephone company drawings. These drawings are composed primarily of horizontal and vertical lines. By selecting the intersections as primitives, routines are developed to establish spatial relations of the primitives which are used to describe the structures. Another aspect that as presented is the benef... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simultaneous word segmentation from document images using recursive morphological closing transform

    Publication Year: 1995, Page(s):761 - 764 vol.2
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    This paper describes a word segmentation algorithm which is based on the recursive morphological closing transform. The algorithm is trainable for any given document image population and is capable of detecting words on a document image simultaneously. We describe an experimental protocol to train and evaluate our word segmentation algorithm based on a set of layout ground-truthed document images.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interpretation of conceptual diagrams from line segments and strings

    Publication Year: 1995, Page(s):960 - 963 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB)

    A conceptual diagram is a kind of diagram which represents a logical structure among concepts using simple physical objects (loops, lines and character strings). This paper presents a method of interpretation of conceptual diagrams. In conceptual diagrams, a single physical object plays various logical roles depending on surrounding physical objects, because there are no specific ruled of writing ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A system for segmenting and recognising totally unconstrained handwritten numeral strings

    Publication Year: 1995, Page(s):1003 - 1009 vol.2
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (712 KB)

    We propose a system for segmentation and recognition of totally unconstrained handwritten numeral strings. The system is built upon a number of components, namely, a presegmentation module, an isolated numeral recognizer, a segmentation-free module and a merging module. Presegmentation consists in dividing the input numeral string image into groups of numerals each of which represents an integer n... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A general analysis system for document's layout structure recognition

    Publication Year: 1995, Page(s):597 - 600 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (332 KB)

    This paper introduces a new method for transforming the images of a document into its layout structure by the use of an analysis system and several models. The analysis system is independent of the document, and can recognize various documents with the help of some generic models. The definition of a model is based on a document's generic layout structure. The models contain rules necessary for id... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reading encrypted postal indicia

    Publication Year: 1995, Page(s):1018 - 1023 vol.2
    Cited by:  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    The next generation of postal processing equipment will incorporate some method of verifying the postal revenue block (postal indicia) as a means of reducing postal fraud. The introduction of new digital printing technologies necessitates the encryption of revenue block information. This paper presents an approach for the verification process which includes algorithms for reading an encrypted post... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A map acquisition, storage, indexing, and retrieval system

    Publication Year: 1995, Page(s):992 - 996 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (500 KB)

    A system for the acquisition, storage, indexing, and retrieval of map images is presented. The input to this system are raster images of separate map layers and map composites. A legend driven map interpretation system converts layer images from a physical to a logical representation. This logical representation is used to automatically index both the composite and the layer images. Methods for in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contextual postprocessing of a Korean OCR system by linguistic constraints

    Publication Year: 1995, Page(s):557 - 562 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (464 KB)

    The approach in this paper focuses on the contextual postprocessing by selecting the most feasible word from multiple output strings of an OCR system. The correction is applied only when the selection fails. The selected word is confirmed by the collocation between the word and the adjacent words. The five functions applied in the system are (1) to select a word from candidate words, (2) to correc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A system for automatic Chinese seal imprint verification

    Publication Year: 1995, Page(s):660 - 664 vol.2
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (460 KB)

    Chinese seal imprint verification by computer is very difficult, but is much needed by the application. An improved method for seal imprint verification based on stroke edge matching combined with image difference analysis is proposed. Experimental results show that the proposed approach is excellent in consistency, reliability and adaptability and is feasible for practical applications View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Iconic paper

    Publication Year: 1995, Page(s):1174 - 1179 vol.2
    Cited by:  Patents (56)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (680 KB)

    Iconic paper can be used to retrieve documents from an electronic database. It provides on a physical sheet of paper a representation that can be used by humans for recognition, and by machines for indexing. A document in the database can be accessed by a gesture indicating a particular icon on the page. A novel presentation of the document supports both indexing and recognition, thereby allowing ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A clustering method and radius tuning by end users

    Publication Year: 1995, Page(s):698 - 701 vol.2
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    In this paper we describe a top-down clustering method consisting of an intra class step and an inter class step. In the intra class step all the samples for each category are initially divided into a small number of clusters, then the largest cluster is split and its members reallocated. The largest cluster is decided based on a new concept, “Volume” of a cluster that is a hybrid of e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Preprocessing raw binary images by means of contours

    Publication Year: 1995, Page(s):640 - 643 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (324 KB)

    In a binary image contours may be seen as the discriminating curve between objects and background. Contours of connected components are always a Jordan curve. One symbol (e.g., a character) may consist of more than one such curve. Processing these curves is a one-dimensional task. Almost all common processing steps can be designed to work on contours rather than on the two-dimensional image. Moreo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Base line correction for handwritten word recognition

    Publication Year: 1995, Page(s):902 - 905 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (320 KB)

    The authors have researched two-letter state name (state name abbreviation) recognition and full state name recognition. According to this research, they think that the accuracy of the character segmentation is essential to recognize the word correctly, and it depends on the normalization of the word image. The normalization includes smoothing, underline removal, spurious blob removal, slant and b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.