摘要
本文提出了一种基于支持向量机的坦克识别算法。在对图像预处理之后,运用颜色和纹理信息进行分割,采用基于数学形态学的算法求得边缘像素,提取具有RST不变性的轮廓特征向量,输入支持向量机进行训练和识别。将支持向量机与传统的人工神经网络的算法进行了对比实验,实验表明基于支持向量机的坦克识别算法具有更好的性能。
A tank recognition algorithm based on Support Vector Machine (SVM) is proposed. The process of the algorithm is as follows: pre-processing images first, then segmenting the images based on color and texture, next extracting the edges of object based on mathematical morphology and extracting the outline feature vectors of the object, finally training a SVM to classify tanks. An experiment showed that the algorithm based on SVM has better performance than an algorithm based on Artificial Neural Network (ANN).
出处
《影像技术》
CAS
2005年第2期18-22,共5页
Image Technology
关键词
坦克识别
支持向量机
轮廓特征向量
Tank Recognition
Support Vector Machine
Outline Feature Vector
