Rigid image registration by General Adaptive Neighborhood matching

PATTERN RECOGNITION

卷:55

Article

Debayle, Johan¹  Presles, Benoit^2,3 

[1] Ecole Natl Super Mines, SPIN LGF UMR CNRS 5307, 158 Cours Fauriel,CS 62362, F-42023 St Etienne 2, France

[2] Univ Lyon 1, INSERM, U1044, INSA Lyon,CREATIS,CNRS UMR 5220, F-69622 Villeurbanne, France

[3] Univ Lyon, Leon Berard Canc Ctr, Lyon, France

关键词: Block matching;    Displacement field;    General Adaptive Neighborhoods;    Image registration;    Shape metric;   

DOI  :  10.1016/j.patcog.2016.01.024

来源: Elsevier

【 摘 要 】

This paper aims to propose a new feature and intensity-based image registration method. The proposed approach is based on the block matching algorithm (Ourselin et al., 2000 [11): a displacement field is locally computed by matching spatially invariant intensity sub-blocks of the images before performing an optimization algorithm from this vector field to estimate the transformation. Our approach proposes a new way to calculate the displacement field by matching spatially variant sub-blocks of the images, called General Adaptive Neighborhoods (GANs) (Debayle and Pinoli, 2006 [2]). These neighborhoods are adaptive with respect to both the intensities and the spatial structures of the image. They represent the patterns within the grayscale images. This paper also presents a consistent shape metric used to match the GANs. The performed qualitative and quantitative experiments show that the proposed GAN matching method provides accurate displacement fields enabling us to perform image rigid registration, even for data from different modalities, that outperforms the classical block matching algorithm with respect to robustness and accuracy criteria. (C) 2016 Elsevier Ltd. All rights reserved.

【 授权许可】

Free