基于灰度相似性度量的弹孔识别方法

Bullet Holes Recognization Based on Grey Similarity Measurement

针对现有自动报靶系统对弱小弹孔目标识别能力差的缺点，提出了一种新的弹孔识别方法。该方法在分析弹孔图像特征基础上，采用灰度相似性概念对弹孔图像的特征进行描述，用像素点灰度的次序统计量定量表示射击前后靶纸图像的灰度变化特征，依据弹孔图像灰度值变化特征从疑似区域中确认弹孔位置。实验结果表明：和现有针对灰度图像的弹孔识别方法相比，该方法对于与背景颜色相似度低于98％的弹孔实现了有效识别，具有更加准确的弹孔识别能力。

In view of the shortage existing in the method for small bullet holes recognization, a new method for bullet holes recognization is introduced. By analyzing the image characteristics of bullet holes which are described by grey similarity, the ordered statistics of pixels＇ grey values are computed to get the differences between the preshot image and the after-shot image, and then the area are extracted from which the bullet hole features are recognized by analyzing the image. Compared with the existing method in view of grey image, the experimental results show that the approach proposed can recognize the bullet holes which has 2 % difference relative to background more accurately.