摘要
探讨基于支持向量机的高分辨率遥感图像中某型号飞机的检测识别问题。提出将小波变换结合灰度共生矩阵法提取目标样本信息特征的一种新方法,通过对Brodatz纹理进行测试,实验表明该方法有效提高了纹理分类识别率。此外,将支持向量机方法运用于遥感图像目标识别中,用分块区域搜索的方法检测到目标所在区域,实现对目标的检测识别。试验表明,该方法快速、高效且具备一定的鲁棒性。
In recent years, support vector machines (SVMs) have demonstrated excellent performance in a variety of pattern recognition. This paper applies SVM for recognition of remote sensing target, using translation-invariant features generated from the discrete frame transform and Hu's invariant moments. Compared to the traditional features extraction, the proposed method produces more accurate classification results on the Brodatz texture album. To alleviate the problem of selecting the right kernel parameter in the SVM, we use a fusion scheme based on multiple SVMs, each with a different setting of the kernel parameter.
出处
《计算机与数字工程》
2007年第7期123-126,共4页
Computer & Digital Engineering
关键词
支持向量机
小波变换
遥感图像
纹理
support vector machines, wavelet transform,remote sensing,Texture
