节点文献
基于混合学习矢量量化算法的遥感影像分类
Remote sensing image classification based on hybrid learning vector quantization algorithm
【摘要】 在分析了Kohonen自组织特征映射网络(SOFM)和学习矢量量化(LVQ)算法的基础上,提出一种基于改进的SOFM算法和LVQ2算法的混合学习矢量量化(HLVQ)方法,并建立了基于HLVQ的遥感影像非监督和监督分类的一般模型。通过与传统的统计分类方法和LVQ2网络分类器比较,HLVQ分类器总的分类性能更好、识别率更高。
【Abstract】 After analyzing self-organizing feature map algorithm and learning vector quantization algorithm developed by Kohonen, a hybrid learning vector quantization algorithm combining the modified SOFM algorithm and the LVQ2 algorithm are proposed, then a general HLVQ-based classification model for remote sensing image is established. Compared with the conventionally statistical method and LVQ2 classifier, the HLVQ classifier has more advantages on recognition rate and general classification performance.
【关键词】 自组织特征映射;
学习矢量量化;
混合学习矢量量化;
遥感影像分类;
【Key words】 self-organizing feature map; learning vector quantization; hybrid learning vector quantization; remote sensing image classification;
【Key words】 self-organizing feature map; learning vector quantization; hybrid learning vector quantization; remote sensing image classification;
【基金】 国家自然科学基金(20022032);辽宁省博士启动基金资助课题
- 【文献出处】 系统工程与电子技术 ,Systems Engineering and Electronics , 编辑部邮箱 ,2005年06期
- 【分类号】TP751
- 【下载频次】185