Recognition of spatial weak targets based on fractal geometry

摘要

Recognition of the interesting targets is the key techniques of precise guided weapon systems. Because fractal dimension is an interesting textual feature of an image, it has been used in many pattern recognition applications including classification and segmentation. According to the fractal feature of man-made objects in infrared images, a new algorithm is presented to detect the airplanes in this paper. And then we can partition and identify the potential targets using this fractal algorithm. Simulations illustrate that the airplane is successfully identified with the algorithm. The algorithm only requires moderate operations, so it is easy to be implemented for automatic target detection in real-time systems. The results of the experiments show that the fractal dimension can efficiently reflect the object surface complexity or irregularity in images. The algorithm is a powerful tool in identifying airplanes from infrared images.