Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on

20-22 Oct. 1993

Filter Results

Displaying Results 1 - 25 of 219
  • Recognition and representation of text characters using rubber band

    Publication Year: 1993, Page(s):955 - 958
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (301 KB)

    An important step in the communication of text including unknown characters is the representation of characters. To realize bilateral exchange of texts, representation of unknown characters, such as foreign characters, created characters, design characters, and historical characters which are not being widely used nowadays is an essential subject. In particular, although many Asian countries are u... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Raster to object conversion aided by knowledge based image processing

    Publication Year: 1993, Page(s):951 - 954
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (461 KB)

    The conceptual framework and the design of the prototype of a common toolkit for map and office document interpretation developed in the ROCKI project are described. The conceptual framework features a novel three-step knowledge-based approach to the interpretation process. The first is the primitive interpretation which identifies elementary graphical objects. These are further processed (object ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Some ergonomic improvements of text error detection and prevention in DTP-systems

    Publication Year: 1993, Page(s):947 - 950
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (305 KB)

    Methods of word processing (WP) and optical character recognition (OCR) are considered. A classification of typing errors and methods of their detection are presented. It is shown that combining simplified WP and OCR gives the same effect as using each sophisticated method separately. Prevention should be made on input level by visual checking, according to the WYSIWYG principle. The new devices o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hand-printed character recognition system using artificial neural networks

    Publication Year: 1993, Page(s):943 - 946
    Cited by:  Papers (8)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (356 KB)

    A new technique is proposed for the recognition of hand-printed Latin characters using artificial neural networks together with conventional techniques. One advantage of this technique is that it combines rule-based (structural) and classification tests. Another advantage is that it it more efficient for large and complex sets. The technique can be divided into five major steps: (1) digitization o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A tree structured neural network

    Publication Year: 1993, Page(s):939 - 941
    Cited by:  Papers (4)  |  Patents (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    A tree structured system for pattern classification is proposed. It uses the feedforward neural network with back-propagation (FN) as a building block. A single FN is used to classify all of the given patterns, then a confusion matrix is carefully studied and used to divide the patterns into groups. This process is repeated by training new FNs with these groups then dividing them into subgroups an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multilayer perceptron and uppercase handwritten characters recognition

    Publication Year: 1993, Page(s):935 - 938
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (295 KB)

    After an introduction to the problem of the automatic character recognition and on multilayer perceptron used for classification, the author describes what one can hope to get from a multilayer perceptron. Some of the problems that can occur during the training and present a fast learning algorithm are also described. This algorithm was tested to train a multilayer perceptron to recognize multiscr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation and classification for mixed text/image documents using neural network

    Publication Year: 1993, Page(s):930 - 934
    Cited by:  Papers (21)  |  Patents (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (471 KB)

    A segmentation and classification method for separating a document image into printed character, handwritten character, photograph, and painted image regions is presented. A document image is segmented into rectangular areas. Each of which contains a cluster of image elements. A layered feed-forward neural network is then used to classify each segmented area using the histograms of gradient vector... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identifying ability of a recognition method based on the field of induction

    Publication Year: 1993, Page(s):926 - 929
    Cited by:  Papers (2)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    A new recognition method based on the field of induction is proposed. This method is based on observations of the field as well as on psychological and physiological knowledge. To adapt this method for use with handwritten characters, it is necessary to determine its ability to identify these characters. It is clarified that this method has a good ability to identify handwritten characters.<<... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent interactive map recognition using neural networks

    Publication Year: 1993, Page(s):922 - 925
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (355 KB)

    An intelligent interactive map recognition method using the case learning ability of neural networks as proposed. It effectively uses operator judgements about local segmentations of map figures as neural network learning data. With this method, the recognition accuracy can be improved and the number of interactive operations needed in the recognition process can be decreased through the operation... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A symbol recognition system

    Publication Year: 1993, Page(s):918 - 921
    Cited by:  Papers (12)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (381 KB)

    A hierarchical neural network approach is presented for the automatic conversion of image documents (ACID), which specifically describes a prototype symbol recognition system (SRS) for automatic computer processing of electrical engineering drawings. This approach achieves a significant reduction of human involvement in the symbol model encoding and recognition processes in contrast to such tradit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Symbol recognition and surface reconstruction from topographic map by parallel method

    Publication Year: 1993, Page(s):914 - 917
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (412 KB)

    The authors reconstruct three dimensional surfaces described by contours on topographic maps. When the elevations of the contours are available, this is an easy problem to solve. However, the authors do not have these elevations and can use only sparsely distributed elevation values noted on the map. This is a difficult problem even for humans to solve. They have developed a method for reconstruct... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new algorithm separating text strings from map images

    Publication Year: 1993, Page(s):910 - 913
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    To enter geographic data into computers, people desire to have a system which can scan a paper-based map and feed the raster map image into a computer. Then the computer should automatically extract the geographic information from the map image by image analysis and understanding techniques. A new algorithm which can separate text strings of various fonts, sizes, and styles from other graphic data... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Musical score recognition: A hierarchical and recursive approach

    Publication Year: 1993, Page(s):906 - 909
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (350 KB)

    Musical scores for live music show specific characteristics: large format, orchestral score, bad quality of (photo) copies. Moreover such music is generally handwritten. The author addresses the music recognition problem for such scores, and show a dedicated filtering that has been developed, both for segmentation and correction of copy defects. Recognition process involves geometrical and topogra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A robust detector for music staves

    Publication Year: 1993, Page(s):902 - 905
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (353 KB)

    A method for the automatic recognition of music staves based on a prediction-and-check technique is presented in order to extract staves. It can detect lines with some curvature, discontinuities, and inclination. Lines are asserted to be a part of a staff if they can be grouped by five, thus completing the staff. This last phase also identifies additional staff lines.<<ETX>> View full abstract»

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

    Publication Year: 1993, Page(s):898 - 901
    Cited by:  Papers (13)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (365 KB)

    The different steps to recognize printed music are described. The first step is to detect and to eliminate the staff lines. A robust method based on finding regions where are only the staff lines, linking between them the staff lines pieces in these regions is used. After staff lines elimination, symbols are isolated and a representation called attributed graph is constructed for each symbol. Thin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Logo recognition using geometric invariants

    Publication Year: 1993, Page(s):894 - 897
    Cited by:  Papers (25)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (350 KB)

    The problem of logo recognition is of great interest in the document domain, especially for databases, because of its potential for identifying the source of the document and its generality as a recognition problem. By recognizing the logo, one obtains semantic information about the document, which may be useful in deciding whether or not to analyze the textual components. A multi-level stages app... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards automatic evaluation of drawing analysis performance-A statistical model of cadastral map

    Publication Year: 1993, Page(s):890 - 893
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (340 KB)

    Automatic evaluation of drawing-to-CAD conversion performance is addressed. The generating model of artificial images in the domain of cadastral maps was built. The proposed model was close to the authentic drawings on the level of graphic primitives and on the level of map understanding. The shape of the parcel was characterized by the number of corners, line lengths and respective angles. The mo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A study on a method of dividing machine-parts into functional groups for technical illustrations

    Publication Year: 1993, Page(s):886 - 889
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (316 KB)

    The authors previously presented a computer generation method of technical illustrations of a machine from its CAD model. However, parts of complicated structures in a machine are more comprehensible when they are expressed in the form of TIs which consist of several illustrations representing functional subgroups of a machine than in a picture containing the total massive structures. There arises... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Machine visualization, understanding and interpretation of polyhedral line-drawings in document analysis

    Publication Year: 1993, Page(s):882 - 885
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (358 KB)

    The author deals with high level visualization, understanding, and interpretation of three-dimensional (3-D) polyhedral objects from two-dimensional (2-D) line-drawing images for document analysis. A new scheme is presented, which is aimed at learning, representing and recognizing 3-D objects with only very few learning samples. It can strengthen advantages of some current key methods while overco... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An object-oriented kernel for geographical information systems

    Publication Year: 1993, Page(s):878 - 881
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    The development of a graphical kernel for geographical information systems is reported. It is based on a multi-dimensional data structure called GBD tree which provides an efficient environment for spatial data retrieval. Graphic entities are classified and represented by a small set of primitive geometrical entities which are implemented as a C++ class library. Applications can derive their own d... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A color map processing system PU-CMPS

    Publication Year: 1993, Page(s):874 - 877
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (266 KB)

    A color map processing system PU-CMPS (color map processing system of Peking University) is introduced. The main functions of PU-CMPS are color-separating, segmentation, vectorizing, recognizing, and automatic editing. First, PU-CMPS strips each kind of color from the original color map. Then, segmentation is implemented to separate the character (including number and small graphic symbols), dash ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multipurpose drawing understanding system with flexible object-oriented framework

    Publication Year: 1993, Page(s):870 - 873
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (386 KB)

    An object-oriented drawing understanding system named OO-Mudams, which can flexibly adapt to various types of drawings by defining their model, is proposed. OO-Mudams is a model-driven system, with reasoning engine, management of internal database for reasoning results, and model definition for users. By defining the models, the system can be customized to process various kinds of drawings includi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Paper drawings to 3-D CAD: a proposed agenda

    Publication Year: 1993, Page(s):866 - 867
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (494 KB)

    The authors try to explain why conversion of engineering drawings into CAD format has been stuck for so long in low-level operations such as vectorization, basic layer separation, and very limited symbol recognition, and what can be done to improve this situation. Based on their own expertise in syntactic and semantic analysis of technical drawings, they propose a scheme for achieving high-level c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A contextual processing for an OCR system, based on pattern learning

    Publication Year: 1993, Page(s):862 - 865
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (400 KB)

    The authors propose a strong contextual stage, which can be implemented in any OCR system for multifont printed documents, based on an automatic pattern training. The goal is to increase the final performance of the recognizer by giving an appropriate stage which uses information about pattern redundancies in the text. Instead of making a standard word by word analysis, the proposed stage will cor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On using syntactic constraints in text recognition

    Publication Year: 1993, Page(s):858 - 861
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (302 KB)

    The human reading process makes use of a number of knowledge sources which communicate with each other in arriving at correct interpretation. In order to obtain human competing performance in machines, this knowledge integration capability has to be built into the machines. A strategy for integration of the natural language syntactic knowledge in the text recognition task is presented. The syntact... View full abstract»

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