旋转不变的X线图像相关度拼接

针对现有X线图像拼接方法中分别存在的需要固定标志物、鲁棒性差及全景图像存在伪影等问题,提出一种旋转不变的图像自动拼接方法.基于特征点配准,结合改进的、旋转不变的相关度法进行特征匹配,对图像重合度要求较低.在图像融合中则采用2维动态权值和平衡曝光度等策略.经实验验证,本文配准算法在保证结果准确性的同时提高了鲁棒性；本文融合算法可有效地平衡曝光度差异,并避免拼接伪影,极大地提高了全景图像质量.

X-ray image mosaic based on rotation invariant correlation

In order to solve the problems of traditional X-ray image mosaic methods, such as the demand for fixed signs, poor robustness, and artifacts in panoramic images,we propose an automatic rotation-independent image mosaic method. This method is based on feature point registration and an improved correlation which is invariant to rotation. It needs lower overlapping areas among images. Two-dimensional dynamic weight and balance exposure have been adopted in image-fusion. Our experiments show that the registration algorithm can improve the accuracy of the results as well as the robustness, and the fusion algorithm can effectively balance the exposure difference and eliminate the mosaic artifacts, greatly improving the quality of the panoramic images.