基于二进制自相似描述符的多模态图像配准

Multimodal Image Registration Based on Binary Self-similar Descriptors

摘要:

针对LSS(Local Self-similarity)局部自相似描述符不适用于多模态图像配准的问题,提出了一种新的自相似描述符,能够有效用于实现多模态图像配准。首先对多模态图像采用相位一致性算法提取图像的最大矩,然后对由最大矩信息得到的边缘图像进行Harris特征点提取,接下来基于边缘图像生成二值图像,并基于二值图像构造二值化自相似描述符,最后对多模态图像进行描述符相似性计算以及特征点匹配。通过对比实验表明,所提二值化自相似描述符能够取代传统的LSS自相似描述符,有效提高了自相似描述符对多模态图像的兼容性和运行效率。

Abstract:

Aiming at the problem that Local Self-similarity descriptor (LSS) is not suitable for multi-modal image registration, a novel self-similarity descriptor is proposed, which can be effectively used for multi-modal image registration. First, the phase congruency algorithm is used to extract the maximum moment of the multimodal image. Second, Harris keypoints are extracted from the edge images obtained from the maximum moment information. Third, a binary image is generated based on the edge image, and a binary self-similar descriptor is constructed based on the binary image. Finally, the similarity calculation of descriptors and keypoints matching are carried out for multimodal images. Comparative experiments show that the proposed binary self-similar descriptor can replace the traditional self-similar descriptor, and effectively improve the compatibility and efficiency of the self-similar descriptor for multimodal images.