IMAGE SMOOTH MAGNIFICATION SEGMENTATION BASED ON CURVE EXPRESSION

摘要：

Propose some algorithms about image smooth magnification and character segmentation, aiming at the difficult factor of little license plate region segmentation, in license plate recognition. In the algorithm, describe the relationship between image and surface, with Cardinal curve construction and sampling methods, magnify image smoothly in transverse and longitudinal direction, take image binarization with iterative method, make longitudinal projection, calculate and modify projection segmentation attributes, segment license plate characters. The experiments shows that the algorithm magnify image, wipe off noise at the same time, and realize license plate character segmentation more easily.

关键词： License Plate Segmentation Image Magnification Curve Ezpression Cardinal Curve Projection Segmentation Attributes

作者: XIAO-FENG CHEN BAO-CHANG PAN SHENG-LIN ZHENG

作者单位: Dept.of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 2899-2904

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）