基于学习局部几何相似性医学图像放大.pdfVIP

ISSN 1000-9825, CODEN RUXUEW E-mail: jos@ Journal of Software , Vol.20, No.5, May 2009, pp.1146− 1155 doi: 10.3724/SP.J.1001.2009.03546 Tel/Fax: +86-10 © by Institute of Software , the Chinese Academy of Sciences . All rights reserved. ∗ 基于学习的局部几何相似性的医学图像放大 1,2 1,2+ 3 潘 琪 , 罗笑南 , 朱继武 1( 中山大学 信息科学与技术学院,广东 广州 510275) 2(教育部数字家庭重点实验室( 中山大学),广东 广州 510275) 3(广东药学院 医药商学院,广东 广州 510006) Learning-Based Medical Image Magnification Algorithm by Local Geometric Similarity PAN Qi1,2, LUO Xiao-Nan1,2+, ZHU Ji-Wu3 1(School of Information Science and Technology (SIST), SUN YAT-SEN University, Guangzhou 510275, China) 2(Key Laboratory of Digital Life (SUN YAT-SEN University), Ministry of Education, Guangzhou 510275, China) 3(Department of Marketing, Guangdong Pharmaceutical University, Guangzhou 510006, China) + Corresponding author: E-mail: lnslxn@, Pan Q, Luo XN, Zhu JW. Learning-Based medical image magnification algorithm by local geometric similarity. Journal of Software, 2009,20(5):1146−1155. /1000-9825/3546.htm Abstract : Image magnification is an important technology in medical image processing. High detail areas in medical images most often have a definite geometric structure or pattern, such as in the case of edges. This paper proposes a learning-based method. Geometric features extracted from the available neighboring pixels in the Low-resolution (LR) image form the training set. Assuming the training set is locally