IEE Workshop on Handwriting Analysis and Recognition - A European Perspective

23-23 May 1996

Filter Results

Displaying Results 1 - 10 of 10
  • User tools for assessing visuo-motor integration through analysis of figure copying tasks

    Publication Year: 1996, Page(s):1/1 - 1/3
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (162 KB)

    Diagnostic and evaluative procedures for dyspraxic children are being increasingly recognised as important. This paper describes some aspects of a project which is investigating the potential for automating the administration and evaluation of accepted tests of visuo-motor integration, and which can facilitate both static and dynamic analysis of patient activity. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computer analysis of visuo-spatial function in the assessment of stroke patients

    Publication Year: 1996, Page(s):2/1 - 2/3
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (161 KB)

    Existing post-stroke rehabilitation assessment includes a series of pencil and paper tests which serve as an indicator of neuropsychological conditions. The application of computer analysis of the patient's hand-written test response provides increased accuracy in clinical evaluation through assessment of both the traditional static test results and dynamic test data (pen velocity, test time etc.)... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimised hand-printed character recognition using neural network cascades

    Publication Year: 1996, Page(s):3/1 - 3/5
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (300 KB)

    The sn-tuple classifier based character recogniser has achieved significantly higher computational efficiency than most other current handwritten character recognisers with similar recognition performance. By combining the sn-tuple classifier with other classifiers, it is possible to further improve recognition rates while retaining its efficiency advantages. In this paper, we present theoretical ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Can scanning n-tuple classifiers be improved by pre-transforming training data?

    Publication Year: 1996, Page(s):4/1 - 4/6
    Cited by:  Papers (2)  |  Patents (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (349 KB)

    A new method of applying n-tuple recognition techniques to handwritten OCR has recently been reported, which involves scanning an n-tuple classifier over a chain-code of the image. In scanning n-tuple systems, the traditional advantages of n-tuple recognition i.e. training and recognition speed are retained, while offering superior recognition accuracy, as demonstrated by results on three widely u... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Novel neural architectures for recognition of handwritten characters

    Publication Year: 1996, Page(s):5/1 - 5/3
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (216 KB)

    This paper presents an overview of novel networking strategies for neural networks which significantly improves the training and recognition performance of such networks whilst maintaining the generalisation capabilities achieved by existing architectures. A number of different architectures are introduced based on two major principles. The first of these employs RAM-based neurons arranged in mult... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of handwritten characters with a multi-expert system

    Publication Year: 1996, Page(s):6/1 - 6/4
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (247 KB)

    A new multi-expert handwritten classification system has been introduced. It is shown that an intelligent combination of decisions taken by multiple experts can greatly enhance the final classification performance. A logical structure for the formation of a practical multi-expert hierarchical structure implementing multiple decision combination is presented and its performance is evaluated on both... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of extended generalized linear discriminant functions (EGLDF) to optical character recognition

    Publication Year: 1996, Page(s):7/1 - 714
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (611 KB)

    An extension to generalized linear discriminant functions, known as "EGLDF", is applied to obtain very accurate classifiers for planar shapes based on contour coding and string edit distances. In this approach edit weights can be made dependent on the (local) "positions" of the prototypes to be matched with the test strings, thus allowing for very fine discrimination based on both global and local... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computationally efficient contextual processing for handwritten forms

    Publication Year: 1996, Page(s):8/1 - 8/5
    Cited by:  Patents (5)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (347 KB)

    In handwriting recognition, recognisers often deliver several alternative recognition results for each component with confidence values attached. The decision on the correct interpretation is then deferred until after use of syntactic and/or contextual constraints, so that undue loss of information is avoided. This paper outlines a semantic neural network approach to a generic contextual postproce... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple knowledge sources for word recognition

    Publication Year: 1996, Page(s):9/1 - 9/3
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (228 KB)

    It is not possible to get complete disambiguation of handwriting from pattern recognition alone since a written word can be interpreted in a number of different ways. The combination of several sources of information, each of which is capable of extracting a different characteristic of cursive handwriting, is more likely to be successful than pattern recognition alone. The way to produce a machine... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The use of extended trigrams for contextual word recognition

    Publication Year: 1996, Page(s):10/1 - 10/5
    Cited by:  Patents (7)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (363 KB)

    This paper proposes a system for offline recognition of hand printed words that makes extensive use of information about trigrams in any given dictionary. The system segments and recognises individual characters then groups them into trigrams which are purged according to information taken from the dictionary. These are converted into strings which are further purged. These strings are then put to... View full abstract»

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