中文摘要：

随着卫星图片分辨率的提高，为了更准确的对机场区域飞机进行识别，首先对图像分割得到待处理的有限识别区域，然后采用局部特征和整体特征对图像中各区域进行判定，排除干扰区域。同时为了减少飞机识别时间，用图像配准方法将测试飞机方向固定，这样飞机库中不需要全方位的飞机图片，大大减少了飞机数量，减小了计算复杂度。实验结果表明该方法在飞机识别中有较好的识别效果。

英文摘要：

With the improvement of the satellite image resolution, in order to distinguish the aircrafts in the airport more ac-curately, the limited recognition area is got first through image segmentation, and then each area of the image is judged accor- ding to the local feature and global feature in the image, so as to suppress the interference region. For the sake of reducing air-craft recognition time, the image matching methods is used to fix the plane direction so that all-around airplane images are not needed, thus the number of aircraft images and calculation complexity are greatly reduced. The experimental results show that this method has a good recognition effect in the identification of aircraft.