Sökning: "Handwriting Recognition"

Hittade 5 avhandlingar innehållade orden Handwriting Recognition.

  1. 1. Machine-Printed and Handwritten Ethiopic Script Recognition

    Författare :Yaregal Assabie; [2009]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; HMM; Handwriting Recognition; OCR; Direction Field Tensor; Ethiopic Character Recognition; Amharic Word Recognition; Structure Tensor;

    Sammanfattning : A written language is represented by using machine-printed or handwritten symbols called characters. For automatic recognition of written languages, handwritten script can be captured offline (by a scanner) and online (by electronic digital devices), whereas machine-printed text is captured offline. LÄS MER

  2. 2. Extensions and Applications of Affine Shape

    Detta är en avhandling från Centre for Mathematical Sciences, Lund University

    Författare :Rikard Berthilsson; [1999]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Systems engineering; Matematik; Mathematics; density of shape; maximum likelihood; matching constraint; surface; curve; handwriting; recognition; affine shape; reconstruction; computer technology; Data- och systemvetenskap;

    Sammanfattning : A central problem in computer vision is to reconstruct the three-dimensional structure of a scene from a set of two-dimensional images. Traditionally this is done by extracting a set of characteristic points in the scene and to compute a reconstruction of these points. LÄS MER

  3. 3. Template Based Recognition of On-Line Handwriting

    Detta är en avhandling från Centre for Mathematical Sciences, Lund University

    Författare :Jakob Sternby; [2008]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; on-line handwriting recognition segmentation dynamic programming clustering discriminative clustering;

    Sammanfattning : Software for recognition of handwriting has been available for several decades now and research on the subject have produced several different strategies for producing competitive recognition accuracies, especially in the case of isolated single characters. The problem of recognizing samples of handwriting with arbitrary connections between constituent characters (emph{unconstrained handwriting}) adds considerable complexity in form of the segmentation problem. LÄS MER

  4. 4. Core Points - Variable and Reduced Parameterization for Symbol Recognition

    Detta är en avhandling från Centre for Mathematical Sciences, Lund University

    Författare :Jakob Sternby; [2005]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

    Sammanfattning : Recent research in the field of on-line handwriting recognition has been focused on statistical systems such as Hidden Markov Models, Neural Networks or a combination of these. There are however merits of employing an approach based on template matching. LÄS MER

  5. 5. On the Metric-based Approach to Supervised Concept Learning

    Detta är en avhandling från Ronneby : Blekinge Institute of Technology

    Författare :Niklas Lavesson; Blekinge Tekniska Högskola.; [2008]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; classifier evaluation; supervised learning; metric; criteria;

    Sammanfattning : Den tekniska utvecklingen har förändrat vår livsstil och utökat den globala ekonomins fokus från produktion av varor till insamling och förädling av information. En konsekvens av denna förändring är att vi blir mer beroende av databaser för lagring och databehandling. LÄS MER