中文摘要：

针对单一特征在识别油菜病害上存在的局限性,提出一种基于D-S证据理论融合多特征的油菜病害识别方法。首先对预处理后的油菜图片提取颜色矩、颜色共生矩阵两种特征,通过欧氏距离来构建D-S证据理论所必需的基本概率分配（BPA）,最后运用D-S证据组合规则进行决策级融合,依据决策条件输出最终分类识别结果。针对存在最终识别结果被误识别为不确定问题,通过引入方差来对决策方法进行改进,避免了这一现象的产生。利用该方法在采集到的油菜样本上进行实验,取得了97.09%的识别率。实验表明,该方法能有效提高油菜病害识别率。

英文摘要：

In order to overcome the limitation of single feature in crop disease recognition, this paper presents a method of recognizing rape disease based on D-S evidence theory and multi-feature fusion. Firstly, color matrix and color co-occurrence matrix are extracted as color feature and texture feature from the rape leaves after a series of image processing. Then, with the help of Euclidean distance, the basic probability assignment （BPA） which is necessary for D-S evidence theory can be constructed. Finally, using D-S combination rule of evidence to achieve the decision fusion and outputting the final recognition results through the decision-making conditions. In view of the situation that the final recognition result may he misrecognized as uncertain, this paper improves the decision-making method by introducing the variance, which can avoid this defect. The experiment on the collected rape images obtains the recognition rate of 97.09%. The experiments show that the method proposed in this paper can increase the rape disease recognition rate effectively.