Multi-modal image registration using edge neighbourhood descriptor

• Published in: Electronics letters Vol. 50; no. 10; pp. 752 - 754
• Main Authors: Cao, Zhulou, Dong, Enqing
• Format: Journal Article
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 08.05.2014; Institution of Engineering and Technology; John Wiley & Sons, Inc
• Subjects: Applied sciences; Artificial intelligence; Complexity; computational complexity; Computer science; control theory; systems; Dealing; Distortion; edge detection; edge neighbourhood descriptor; Entropy; entropy calculation complexity; Exact sciences and technology; Image and vision processing and display technology; Image registration; intensity distortion; local patch‐based entropy image; Mathematical analysis; Medical; medical image processing; multimodal medical image registration; mutual information method; Pattern recognition. Digital image processing. Computational geometry; intensity distortion; mutual information method; entropy; local patch-based entropy image; image registration; entropy calculation complexity; edge neighbourhood descriptor; edge detection; multimodal medical image registration; medical image processing; computational complexity; distortion; Image registration; Medical imagery; Experimental result; Image processing; Mutual information; Multiple image
• ISSN: 0013-5194; 1350-911X; 1350-911X
• DOI: 10.1049/el.2014.0795

Multi-modal medical image registration remains a challenging and active area of research owing to the difficulty of dealing with intensity distortions. Local patch-based entropy images were recently proposed to address this problem. However, this method suffers from the complexity of calculation of the entropy. Proposed is a new dense descriptor for an image, named the edge neighbourhood descriptor, which assigns different values to different image regions, namely the image background, image edges, edge neighbourhoods and the remaining area. The edge neighbourhood descriptor is faster than the entropy image. Experimental results show that this new descriptor can improve registration accuracy compared with the results of the entropy image and the mutual information method.