Learn More
Hand-printed character recognition is an important application in our life. A method called the feature-to-feature adhesion method is developed to achieve the task. There are two geometrical relations constructed in an earlier method. This work rewrites geometrical relations and constructs them into the Hopfield model to improve the matching result. We also(More)
Since the kernel function in support vector machine is arbitrary, it carries no physical meaning in practical applications. This work presents a bi-perceptron network that works in real physical space. All network parameters can be obtained in a constructive way without training. It is a divide-and-conquer way with perfect performance. We show how to(More)
  • 1