A New Weighting Scheme with Multiple Classifiers Fusion for Image Classification

多分類器融合權重分配法之研究

曾裕強(Y. C. Tzeng) ； 陳錕山(K. S. Chen)

《航測及遙測學刊》 12卷4期 (2007/12) Pp. 509-526

https://doi.org/10.6574/JPRS.2007.12(4).17

摘要

資料融合的關鍵技術之一乃如何有效萃取來自不同感測器的互補資訊。本文即探討利用多分類器系統來達到這個目的。多分類器系統中的必要手段爲不同資料來源的權重分配；本文分別提出三種方案:變異減低法、均方根距離法與平均距離法。實例中我們利用SAR 影像與光學影像融合於地物分類作爲分析評估上述權重分配的性能。結果顯示整體分類精度有大幅度的提升，而三種方案中均方根距離法與平均距離法皆優於變異減低法。

關鍵字

影像融合 ； SAR ； 地物分類 ； 多分類器

並列摘要

One of the key prospects of data fusion is focused on exploiting the complementary information among different sensors. In this paper, the multiple classifiers approach is utilized for the multisource classification/data fusion to fully utilize as much of the available information among different data sources as possible. Three different weighting policies (variance reduction technique, rms distance weighting, and average distance weighting) applied to the multiple classifiers approach are introduced. The performance of each combination method was demonstrated and compared with the fusion of the SAR and optical images for the terrain cover classification. Experimental results show that the classification accuracy is dramatically improved by making use of the proposed method. In addition, both the multiple classifiers using the rms (root mean squared) distance weighting and the average distance weighting outperform that of using the variance reduction technique.

並列關鍵字

Image fusion ； SAR ； terrain classification ； Multiple Classifiers