Advanced search


Juan C. Pérez-Cortés, Enrique Vidal, L. Sanchez. Un Sistema Geométrico de Reconocimiento Óptico de Caracteres. Actas del Simposium Nacional de Reconocimiento de Formas y Analisis de Imágenes (SNRFAI92), 1992.

A new representaion method, called LLF (Local Line Fitting), for recognition of handwritten charcters is presented. Based on simple geometric computations, the method is very efficient yielding a relatively low-dimensional and distortion invariant representation. An important characteristic of the approach is that no preprocessing of the input image is required. A black&white or gray-scale pixel representation is directly used without thinning, contour following, binarization, etc. Therefore, the recognition speed that can be achieved is very high. Experiments using this parametrization method and several classification procedures on handwritten digits and letters are reported.