Retinal Image Quality Classification Using Fine-Tuned CNN
文献类型：会议论文
| 作者 | Sun, Jing; Wan, Cheng; Cheng, Jun; Yu, Fengli; Liu, Jiang |
| 出版日期 | 2017 |
| 会议日期 | 2017-09-14 |
| 关键词 | CONVOLUTIONAL NEURAL-NETWORKS |
| 卷号 | 10554 |
| DOI | 10.1007/978-3-319-67561-9_14 |
| 英文摘要 | Retinal image quality classification makes a great difference in automated diabetic retinopathy screening systems. With the increase of application of portable fundus cameras, we can get a large number of retinal images, but there are quite a number of images in poor quality because of uneven illumination, occlusion and patients movements. Using the dataset with poor quality training networks for DR screening system will lead to the decrease of accuracy. In this paper, we first explore four CNN architectures (AlexNet, GoogLeNet, VGG-16, and ResNet-50) from ImageNet image classification task to our Retinal fundus images quality classification, then we pick top two networks out and jointly fine-tune the two networks. The total loss of the network we proposed is equal to the sum of the losses of all channels. We demonstrate the super performance of our proposed algorithm on a large retinal fundus image dataset and achieve an optimal accuracy of 97.12%, outperforming the current methods in this area. |
| 会议录出版者 | Lecture Notes in Computer Science |
| 学科主题 | Computer Science ; Imaging Science & Photographic Technology |
| ISSN号 | 0302-9743 |
| ISBN号 | 978-3-319-67561-9; 978-3-319-67560-2 |
| 源URL | [http://ir.nimte.ac.cn/handle/174433/23436]  |
| 专题 | 会议专题 会议专题_会议论文 |
| 推荐引用方式 GB/T 7714 | Sun, Jing,Wan, Cheng,Cheng, Jun,et al. Retinal Image Quality Classification Using Fine-Tuned CNN[C]. 见:. 2017-09-14. |
入库方式： OAI收割
来源：宁波材料技术与工程研究所
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。