Recently, with the rapid development and continuous improvement of biometric identification technology, writer identification based on handwriting has become an important technology of biometric personal identification. This technology has been widely used in the public security, administration of justice, electronic business and finance areas. The off-line handwriting identification is a technique that aims to decide the identity of writers according to handwriting image. This paper proposes a contour-directional feature for the issue of text-independent writer identification of offline Chinese handwritingThis paper includes three parts:pre-processing, feature extraction, and classifier design. In the first part, pre-processing, the OTSU algorithm is used for image binarization, then the edge detect on Binary image. In the feature extraction, this paper proposes contour-directional feature for the issue of text-independent writer identification of offline handwriting. The contour-directional feature encodes orientation and curvature information in a local grid around every edge pixel to give an intrinsic characteristic of individual handwriting style. In the classifier design, the improved weighted Chi-square metric is applied to measure the similarity of two feature vector.The system is tested on a handwriting database of HIT-MW database involving390writers and envelop address database involving25writers. The experimental results shows the algorithm proposed here is feasible and effective... |