| 一种基于多项式逻辑回归高光谱影像分类方法的改进 |
| |
| 引用本文： | 胡俊,谭琨,吴立新.一种基于多项式逻辑回归高光谱影像分类方法的改进[J].遥感技术与应用,2015,30(1):135-139. |
| |
| 作者姓名： | 胡俊 谭琨 吴立新 |
| |
| 作者单位： | (中国矿业大学资源环境信息工程重点实验室,江苏 徐州221116) |
| |
| 基金项目： | 国家自然科学基金项目（41101423）,中央高校基本科研业务费专项资金( 2010QNA18),中国博士后科学基金资助项目(2011M500128),江苏高校优势学科建设工程资助项目(SZBF2011\|6\|B35)。 |
| |
| 摘 要： | 针对多项式逻辑回归分类器在参数寻优过程中精度提升不明显和运行速度缓慢的问题,提出一种利用DFP修正拟牛顿算法进行多项式逻辑回归参数求解的方法来提高多项式逻辑回归参数优化的效率,该算法以弦截法代替牛顿算法中的二阶Hessian矩阵,并采用DFP修正法不断修正。利用该算法对两幅高光谱影像进行分类实验,结果表明:与传统的多项式回归分类方法相比,该算法在分类精度和效率方面都有明显的改进。
|
| 关 键 词： | 高光谱影像分类 多项式逻辑回归 DFP修正拟牛顿算法 高光谱影像分类 多项式逻辑回归 DFP修正拟牛顿算法 |
| 收稿时间： | 2013-12-28 |
An Improved Hyperspectral Image Clasification Algorithm based on Multinomial Logistic Regression |
| |
| Hu Jun,Tan Kun,Wu Lixin.An Improved Hyperspectral Image Clasification Algorithm based on Multinomial Logistic Regression[J].Remote Sensing Technology and Application,2015,30(1):135-139. |
| |
| Authors: | Hu Jun Tan Kun Wu Lixin |
| |
| Affiliation: | (Jiangsu Key Laboratory of Resources and Environment Information Engineering,;
China University of Mining and Technology,Xuzhou 221116,China) |
| |
| Abstract: | An improved classification algorithm is proposed to use multinomial logistic regression with DFP quasi\|newton to solve the problem of slowly improving classification accuracy and time consuming when used multinomial logistic regression classifier.The second order Hessian matrix is replaced by secant method in newton method and using DFP to improve the performance.After two different hyperspectral image experiments by using presented method,the result shows that this method has a big improvement in both accuracy and time consuming than the traditional multinomial logistic regression method. |
| |
| Keywords: | Hyperspectral image Multinomial logistic regression DFP quasi-newton |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《遥感技术与应用》浏览原始摘要信息 |
|
点击此处可从《遥感技术与应用》下载全文 |
