Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Chencong Xing"'
Publikováno v:
International Journal of Computational Intelligence Systems, Vol 14, Iss 1 (2021)
Few-shot image segmentation intends to segment query images (test images) given only a few support samples with annotations. However, previous works ignore the impact of the object scales, especially in the support images. Meanwhile, current models o
Externí odkaz:
https://doaj.org/article/17c577dd85ee4db39d586285e48ff14a
Publikováno v:
Eye.
Background Fundus microvasculature may be visually observed by ophthalmoscope and has been widely used in clinical practice. Due to the limitations of available equipment and technology, most studies only utilized the two-dimensional planar features
Publikováno v:
International Journal of Computational Intelligence Systems, Vol 14, Iss 1 (2021)
Few-shot image segmentation intends to segment query images (test images) given only a few support samples with annotations. However, previous works ignore the impact of the object scales, especially in the support images. Meanwhile, current models o
Autor:
Zhaomin Yao, Zhiruo Zhang, Kunlin He, Yilin Hou, Bowen Shao, Xiaohan Sun, Gancheng Zhu, Shuai Liu, Huahui Zhou, Chencong Xing, Meiyu Duan, Fengfeng Zhou, Jianyuan Zhang, Lan Huang, Yang Tao, Zhenyu Zhang
Publikováno v:
Frontiers in Optics / Laser Science.
Two-dimensional images of fundus blood vessels are easy to obtain with low diagnostic accuracy. This study realized the reconstruction of three-dimensional vascular structures from two-dimensional fundus images to improve the accuracy to 95%.