基于支持向量机与多特征选择的农作物彩色病斑边缘-计算机系统应用.PDFVIP

计 算 机 系 统 应 用 2014 年 第 23 卷 第 9 期 基于支持向量机与多特征选择的农作物彩色病斑边缘 检测① 濮永仙 (德宏师专 计科系, 德宏 678400) 摘 要: 为正确提取作物病害图像病斑, 提出了一种基于支持向量机与多特征选择的作物彩色病斑边缘检测方法. 该方法用(2d+1)×(2d+1)大小的窗口遍历图像, 计算图像亮度和色度通道的方差、均值差、最大梯度, 以及空间位置 特征和均值色差作为特征向量, 实现支持向量机对病斑边缘识别. 为提高检测病斑边缘的效率, 提出了在遍历过程 中, 若特征值都小于阈值时, 则跳过 d 行, d 列再遍历. 实验表明, 该方法比传统的边缘检测算子具有更好的病斑边 缘识别能力. 关键词: 支持向量机; 多特征; 农作物; 彩色病斑; 边缘检测 Color Disease Spot Edge Detection of Crop Based on Multifeature Selection and Support Vector Machine PU Yong-Xian (Computer Science Department, Dehong Teachers’ College, Dehong 678400, China) Abstract: In order to correctly extract the lesion of crop disease images, proposes a method to detect color edge of crop disease based on support vector machines and multi feature selection. The method uses (2d + 1) * (2d + 1) as the size of the window through the image. It also is used on the image luminance and chrominance channels calculate variance, mean value difference, maximum gradient, characteristics of space position and mean color difference. In order to accurately identify the edge of disease spot, the characteristics of vector-valued input support vector machine is employed. To improve the efficiency of disease spot of edge detection, a method is proposed in the traversal process, if the eigenvalues are smaller than the threshold, skip d row, d column to traverse. The experimental shows that the method has better than the traditional edge detection operator disease spot edge recognition ability. Key words: support vector machine; multi-feature; crops; color disease spot; edge detection 边缘检测是图像处理中的一种分割技术. 边缘是 的效果; 毛罕平, 张柏毅等[2,3]利用模糊 C 均值聚类对 以图像局部特征不连续的形式出现, 即图像局部特征 棉花、玉米病害图像的病斑进行分割, 取得了一定的 发生剧烈变化的地方, 这些特征包括灰度、颜色、纹 成效; 任玉刚等[4]利用分水岭算法对黄瓜病害图像病 理等. 在作