2019
DOI: 10.1007/s11760-019-01544-y
|View full text |Cite
|
Sign up to set email alerts
|

Automated quality classification of colour fundus images based on a modified residual dense block network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 13 publications
(6 citation statements)
references
References 23 publications
0
6
0
Order By: Relevance
“…Experiments on the DR1 and MESSIDOR public datasets indicated that knowledge learned in other large datasets (source domain) could be better classified in small datasets (target domain) via transfer learning. 25 developed an enhanced residual dense block CNN, which could effectively classify fundus images into “good quality” and “low quality” to avoid delaying patient treatment and solve the problem of quality classification of fundus images. 26 offered a six-level cataract grading method that focuses on multifeature fusion and extracted features from the residual network (ResNet-18) and gray-level cooccurrence matrix (GLCM), with promising results.…”
Section: Related Workmentioning
confidence: 99%
“…Experiments on the DR1 and MESSIDOR public datasets indicated that knowledge learned in other large datasets (source domain) could be better classified in small datasets (target domain) via transfer learning. 25 developed an enhanced residual dense block CNN, which could effectively classify fundus images into “good quality” and “low quality” to avoid delaying patient treatment and solve the problem of quality classification of fundus images. 26 offered a six-level cataract grading method that focuses on multifeature fusion and extracted features from the residual network (ResNet-18) and gray-level cooccurrence matrix (GLCM), with promising results.…”
Section: Related Workmentioning
confidence: 99%
“…Some related results have been published on fundus image classification. In order not to delay the treatment of patients and to solve the quality classification of fundus images, Zhang et al proposed an improved residual dense block convolutional neural network to effectively divide fundus images into "good quality" and "poor quality" [30]. Zhang et al described a six-level cataract grading method focusing on multi-feature fusion, which extracted features from residual network (ResNet-18) and gray level co-occurrence matrix (GLCM), the results show advanced performance [31].…”
Section: Fundus Images Recognitionmentioning
confidence: 99%
“…Zago et al [16] used a pretrained model of the ImageNet database to extract general features and evaluate the classification performance of retinal quality by fine-tuning the weight parameters. Zhang et al [17] combined residual and dense network blocks to obtain more detailed features of fundus images. Chalakkal et al [18] proposed a two-stage evaluation method.…”
Section: Related Workmentioning
confidence: 99%
“…Zhang et al. [17] combined residual and dense network blocks to obtain more detailed features of fundus images. Chalakkal et al.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation