A new approach to recognition of deformed patterns
A new approach to recognition of deformed patterns
复制标题
一种识别变形图案的新方法
DOI：
10.1016/0031-3203(94)90087-6
复制
发表时间：
1994
期刊：
影响因子：
--
通讯作者：
H. Haken
中科院分区：
文献类型：
--
作者：
A. Daffertshofer;H. Haken
通过引入原始和变形模式之间的距离和适当的成本函数，我们推导出一个梯度动力学的变换函数，将一个模式转换成另一个。在其最简单的形式中，成本函数是从弹性介质中借来的，但在进一步的改进中，相应的Lamé常数是根据图案选择的。在线图案的情况下，引入借助于高斯分布的涂抹，并使其依赖于时间。数值模拟表明了本方法的可行性，例如，用于识别手写字符或显示不同面部表情的人脸。
By introducing a distance between original and deformed patterns and an adequate cost function we derive a gradient dynamics for transformation functions that transform one pattern into another one. In its simplest form the cost function is lent from an elastic medium but in further improvements the corresponding Lamé constants are chosen pattern dependent. In the case of line patterns a smearing out by means of a Gaussian distribution is introduced and made time dependent. The numerical simulations show the feasibility of the present approach, for instance, for the recognition of handwritten characters or of faces showing different facial expressions.