• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Agriculture and Hydrology Applications of Remote Sensing; Proceedings of SPIE-The International Society for Optical Engineering; vol.6411 >On the optimal choice of parameters in using fuzzy clustering algorithm for segmentation of plant disease leaf images
【24h】

On the optimal choice of parameters in using fuzzy clustering algorithm for segmentation of plant disease leaf images

机译：基于模糊聚类算法的植物病叶图像分割参数的最优选择

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

As an important classifier, fuzzy c-means clustering technique has been widely used in segmentation of image. It is an adaptive segmentation method for plant disease images. However, it has some uncertain factors, when it is used for specific segmentation problem, that are input parameters value. The input parameters include the feature of the date set, the optimal number of cluster, and the degree of fuzziness. These parameters affect the speed and precision of fuzzy clustering segmentation. In this paper, the optimal choice of parameters in a fuzzy c-means algorithm for segmentation of plant disease image was discussed and investigated. Using the pixels gray and means of neighborhood pixels as input feature data; an adapting the FCM algorithm parameters based on fuzzy partition entropy, fuzzy partition coefficient, and compactness measures was used to choose the optimal cluster number; and experiments was used for choosing the degree of fuzziness. The Results show that the optimal clustering number for disease leaf segmentation problem is 4 and the degree of fuzziness is 2.
机译：作为一种重要的分类器，模糊c均值聚类技术已广泛应用于图像分割中。这是一种用于植物病害图像的自适应分割方法。但是，当用于特定的分割问题时，它具有一些不确定因素，即输入参数值。输入参数包括日期集的功能，最佳聚类数和模糊程度。这些参数影响模糊聚类分割的速度和精度。本文讨论并研究了模糊c-均值算法在植物病害图像分割中参数的最优选择。使用灰色像素和邻近像素的平均值作为输入特征数据；利用基于模糊分区熵，模糊分区系数和紧致度的自适应FCM算法参数选择最优聚类数。实验用于选择模糊程度。结果表明，病叶分割问题的最佳聚类数为4，模糊度为2。

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