Symmetry axis extraction by a neural network
Symmetry axis extraction by a neural network
复制标题
DOI：
10.1016/j.neucom.2005.11.010
复制
发表时间：
2006-10-01
期刊：
影响因子：
6
通讯作者：
Kikuchi, Masayuki
中科院分区：
文献类型：
--
作者：
Fukushima, Kunihiko;Kikuchi, Masayuki
本文提出了一种从视觉图案中提取对称轴的人工神经网络。输入图形可以是平面图形、复杂的线条图或CCD相机拍摄的灰度自然图像。该网络具有分层的多层结构，类似于新认知器的较低阶段。它由对比度提取层、边缘提取层（简单和复杂类型）和对称轴提取层组成。该网络首先从输入图像中提取有方向的边缘，然后尝试提取对称轴。我们的网络检查对称条件，不是直接从定向边缘，而是从它们的模糊版本。模糊信号的使用不仅大大降低了计算成本，而且使网络对输入模式的变形具有较大的容忍度。重要的是要得到模糊的信号，而不是直接从输入图像，但从定向边缘。虽然经过模糊处理后边缘位置信息变得模糊，但原始图像的大部分重要特征仍然保持稳定。但是，如果直接对输入图像进行模糊处理，则会丢失图像中的大部分重要特征。(c) 2006 Elsevier B.V.版权所有
This paper proposes an artificial neural network that extracts axes of symmetry from visual patterns. The input patterns can be plane figures, complicated line drawings or gray-scaled natural images taken by CCD cameras.The network has a hierarchical multi-layered architecture, which resembles that of the lower stages of the neocognitron. It consists of a contrast-extracting layer, edge-extracting layers (simple and complex types), and layers extracting symmetry axes. The network extracts oriented edges from the input image first, and then tries to extract axes of symmetry.Our network checks conditions of symmetry, not directly from the oriented edges, but from a blurred version of them. The use of blurred signals not only reduces the computational cost greatly, but also endows the network with a large tolerance to deformation of input patterns. It is important to get blurred signals, not directly from an input image, but from the oriented edges. Although information of edge locations becomes ambiguous after the blurring operation, most of important features of the original image can still remain stable. If the input image is directly blurred, however, most of the important features in the image will be lost. (c) 2006 Elsevier B.V. All rights reserved.