Adaptive optics retinal image registration from scale-invariant feature transform
文献类型:期刊论文
作者 | Li Hao; Yang Hansheng; Shi Guohua; Zhang Yudong |
刊名 | OPTIK
![]() |
出版日期 | 2011 |
卷号 | 122期号:9页码:839-841 |
通讯作者 | Li H (Li Hao) |
中文摘要 | With the use of adaptive optics(AO), high-resolution microscopic imaging of the living human retina in the single cell level has been achieved. In an AO retinal imaging system, with a small field size (about 1 degrees, 300 mu m) the motion of the eye severely affects the stabilization of the real-time video images results in significant distortions of the retina images. Scale-invariant feature transform (SIFT) algorithm is applied to automatically abstract corner points with subpixel resolution and match the points in two frames. With the matched corner points, we estimate and remove the motions of 20 frames of photoreceptor cells and capillary blood vessels, respectively. The maximal translational motion is about 30 and 44 pixels in the 20 frames whose size is 416 x 416 pixels. More general motions can be considered by the SIFT algorithm, but only simple translational motion can be considered by cross-correlation algorithm. (C) 2010 Elsevier GmbH. All rights reserved. |
英文摘要 | With the use of adaptive optics(AO), high-resolution microscopic imaging of the living human retina in the single cell level has been achieved. In an AO retinal imaging system, with a small field size (about 1 degrees, 300 mu m) the motion of the eye severely affects the stabilization of the real-time video images results in significant distortions of the retina images. Scale-invariant feature transform (SIFT) algorithm is applied to automatically abstract corner points with subpixel resolution and match the points in two frames. With the matched corner points, we estimate and remove the motions of 20 frames of photoreceptor cells and capillary blood vessels, respectively. The maximal translational motion is about 30 and 44 pixels in the 20 frames whose size is 416 x 416 pixels. More general motions can be considered by the SIFT algorithm, but only simple translational motion can be considered by cross-correlation algorithm. (C) 2010 Elsevier GmbH. All rights reserved. |
语种 | 英语 |
源URL | [http://ir.ioe.ac.cn/handle/181551/6204] ![]() |
专题 | 光电技术研究所_自适应光学技术研究室(八室) |
作者单位 | 中国科学院光电技术研究所 |
推荐引用方式 GB/T 7714 | Li Hao,Yang Hansheng,Shi Guohua,et al. Adaptive optics retinal image registration from scale-invariant feature transform[J]. OPTIK,2011,122(9):839-841. |
APA | Li Hao,Yang Hansheng,Shi Guohua,&Zhang Yudong.(2011).Adaptive optics retinal image registration from scale-invariant feature transform.OPTIK,122(9),839-841. |
MLA | Li Hao,et al."Adaptive optics retinal image registration from scale-invariant feature transform".OPTIK 122.9(2011):839-841. |
入库方式: OAI收割
来源:光电技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。