基于Zernike矩和神经网络的角点筛选方法

SELECTION METHODS OF THE IMPORTANT CORNERS BASED ON ZERNIKE MOMENTS AND NEURAL NETWORKS

在计算机视觉领域中角点特征的提取具有相当重要的地位 ,因为角点包含了丰富的信息。本文的目的在于提取某类图像上的重要特征角点。其主要思路是首先利用角点检测方法提取图像中的角点之后 ,然后再通过Zernike矩和神经网络对它们进行筛选 ,从而达到自提取特征角点的目的。最后通过实验验证了本算法的有效性。尽管本文是针对某类图像进行了特征点提取的 ,但相信对于一般情况下的目标特征检测也具有一定的借鉴意义。

Corner selection plays an important role in the field of computer vision since the image corners include a large mount of useful information. The purpose of this paper is to study the selection method of the important corners in the given type of image. Firstly the image corners are obtained by using some type of image corners detection method, and then the more important corners are selected by using Zernike moments and neural networks. .The effectiveness of the new method is confirmed by the experiment in the end of this paper. Although the algorithm is only verified in some type of images, but it should be believed that the method can be extended to other similar situations.