| 具有旋转不变性的纹理分割方法 |
| |
| 引用本文： | 汪涛, 吴吟, 邢小良, 庄新华. 具有旋转不变性的纹理分割方法. 自动化学报, 1992, 18(4): 456-463. |
| |
| 作者姓名： | 汪涛 吴吟 邢小良 庄新华 |
| |
| 作者单位： | 1.浙江大学计算机科学与工程系,杭州 |
| |
| 基金项目： | 国家自然科学基金，国防科技基金 |
| |
| 摘 要： | 本文提出了一种具有旋转不变性的纹理分割算法.纹理图象被模拟为三层次过程综合作用形成的,它们是区域过程、纹理过程和退化过程.整个方法包括具有旋转不变性的纹理特征抽取、纹理特征的光滑、基于三层次神经元网络的初始分割以及利用多值Boltzmann机的进一步分割.对自然纹理图象的分割结果证明了算法的有效性.
|
| 关 键 词： | 纹理分割 旋转不变性 层次神经元网络 多值Boltzmann机 |
| 收稿时间： | 1990-07-10 |
A Rotation-Invariant Approach for the Segmentation of Textured Images |
| |
| Wang Tao, Wu Yin, Xing Xiaoliang, Zhuang Xinhua. A Rotation-Invariant Approach for the Segmentation of Textured Images. ACTA AUTOMATICA SINICA, 1992, 18(4): 456-463. |
| |
| Authors: | Wang Tao Wu Yin Xing Xiaoliang Zhuang Xinhua |
| |
| Affiliation: | 1. Depariment of Computer Science&Engineering Zhejiang University,Hangzhou |
| |
| Abstract: | This paper presents a rotation-invariant approach for segmenting textured images. The textured images are modeled as three hierarchical processes, namely, the region process, the texture process, and the degradation process. The whole procedure includes extraction of rotation-invariant features, smoothing of these features, initial segmentation based on three-layered neural networks, and extensive segmentation using multi-valued Boltzmann machines. Experiments on natural textures have shown its efficiency. |
| |
| Keywords: | Texture segmentation rotation-invariancy layered nerual network multivalued Boltzmann machine |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
