基于边缘和模板匹配的印鉴自动鉴别方法

利用计算机鉴别印鉴真伪具有广泛的应用前景．提出一种基于边缘和模板匹配的印鉴自动鉴别方法，该方法先将印鉴图象分成若干个子区域，然后提取反映真假印鉴本质特征的若干参数，用它们形成局部和全局特征，最后用ＢＰ神经网进行判决．实验结果表明，该鉴别方法具有较强的适应性和可靠性，已达到实用水平．

Automatic Seal Imprint Verification Based on Stroke Edge Matching and Template Matching

An approach for automatic seal imprint verification based on stroke edge matching and template matching is presented. Firstly, the seal imprint is divided into some partial regions and the local and global intrinsic features are extracted. Then, the final decision is made by BP neural network. The experimental results show that the proposed approach is excellent in adaptability and reliability, and can be put into practical use.