基于波谱库的特色农作物智能专家分类系统设计

农作物的长势监测和产量估算一直是遥感技术应用的重要方面，而一个好的农作物分类算法对于农作物产量和长势进行监测十分关键。目前对于一些特色农作物而言，这方面的研究比较缺乏。因此拳研究设计了符合特色农作物的长势监测和产量测算功能模块，将数据挖掘和知识发现应用到专家分类算法中，自行开发了适合农作物数据发现和挖掘的归纳学习算法，充分利用了波谱库中大量的波谱数据、相关属性和空间数据，形成了基于波谱库的特色农作物智能专家分类系统。

The Design of Intelligent Expert Classifier for Featured Crop Combining Spectral Library

Crop condition monitoring and yield estimation is an important remote sensing application field at all times and it essentially requires a good classification algorithm for featured crop information extraction. However, there are few researches dealing with intelligent expert classifier about their classification by remote sensing. So the research design a module which is used to monitor crop condition and estimate yield in spectral library of featured crops and here present an approach to combine inductive learning with expert system classification methods. Spatial data mining techniques are used to discover knowledge from spectral library for expert system and inductive learning algorithm, which is designed speciaUy for typical crops data, is developed independently. It makes use of a lot of spectral data, attribute data and spatial data of Spectral library, and form intelligent expert classifier for featured crops based on spectral library.