• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Artificial Intelligence IC-AI'2000 Vol.3, Jun 26-29, 2000, Las Vegas, Nevada, USA >Chaotic pattern segmentation of mixed figures
【24h】

Chaotic pattern segmentation of mixed figures

机译：混合图形的混沌模式分割

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Many pattern segmentation systems have been developed by artificial neural networks. Those systems, such as the perceptron and the associative memory are very effective to map an input to one of the memorized patterns. However, if we try to extract plural patterns from a mixed figure at once, we have to embed a specialized mechanism in their system. The segmentation problem is still one of difficult problems in image processing and speech recognition. This paper proposes a new pattern segmentation system using chaotic dynamics. This system can discriminate several patterns at once, even if they are overlapped to each other. And the proposed system is also reconfigurable, because the system consists of two simple components, 'back-propagation' and 'chaotic neuron model'. To extract mixed figures, we provide a new idea, which is a combination of two components.
机译：通过人工神经网络已经开发了许多模式分割系统。诸如感知器和关联记忆之类的系统对于将输入映射到其中一种记忆模式非常有效。但是，如果尝试从混合图形中一次提取多个模式，则必须在其系统中嵌入专门的机制。分割问题仍然是图像处理和语音识别中的难题之一。本文提出了一种利用混沌动力学的新型模式分割系统。即使它们相互重叠，该系统也可以一次识别几种模式。由于该系统由两个简单的组件“反向传播”和“混沌神经元模型”组成，因此该系统也是可重构的。为了提取混合数字，我们提供了一个新的想法，它是两个组成部分的组合。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号