Online cursive script recognition using local affine transformation

The problem of extraction, description, and estimation of handwriting deformation in online character recognition is discussed. First, feature-point correspondence is extracted between an input pattern and a reference pattern by elastic matching and a deformation vector field (DVF) is generated. Second, the DVF is expanded into an infinite series by applying iterative local affine transformations. Finally, the interpattern distance is calculated between the input pattern and the reference pattern superposed by low-order components of local affine transformations. Recognition tests made on cursive kanji character data have revealed the high discrimination ability of this method.<>