基于SIFT特征和ISM的X射线图像危险品检测方法

Dangerous Material Detection Method in X-ray Image Based on SIFT Feature and ISM

针对行李安检时X射线图像中的危险品检测问题,提出一种基于尺度不变特征变换(SIFT)和隐式形状模型(ISM)的检测方法;首先,采集不同姿态的危险品X射线图像,并标注目标位置,构建训练数据集;然后,通过SIFT算法提取目标关键点,并以此构建目标的ISM模型;在检测过程中,将提取的目标SIFT描述符与ISM模型中的视觉描述符进行匹配,通过投票机制来判断目标是否为危险品;通过手枪和酒瓶的检测实验表明,该方法能够从X射线图像中准确检测出危险品,且对目标姿态变化具有鲁棒性。

For the issues that the dangerous material detection in X-ray images,a method based on scale invariant feature transform(SIFT)and implicit shape model(ISM)is proposed.First,it collect the X-ray images of dangerous objects with different gestures,and label the target position to construct the training data set.Then,the target key points is extracted by SIFT algorithm,and the target ISM model is constructed.In the detection process,the extracted target SIFT descriptor is matched with the visual descriptor of ISM model,and through the voting mechanism to determine whether the target is dangerous goods.Experiments with pistols and bottles show that this method can detect dangerous material accurately from X-ray images and is robust to target attitude changes.