SDUW-Net: An Effective Retinal Vessel Segmentation Model
| Autor: | Xinrong Cao, Hongliang Kang, Hongkai Lin |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Process (computing) Retinal 02 engineering and technology Fundus (eye) 01 natural sciences 010305 fluids & plasmas Convolution chemistry.chemical_compound chemistry 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Segmentation Noise (video) Artificial intelligence business |
| Zdroj: | Machine Learning for Cyber Security ISBN: 9783030624620 ML4CS (3) |
| DOI: | 10.1007/978-3-030-62463-7_18 |
| Popis: | Retinal vessel segmentation is the main step in the analysis of fundus images. However, gray-scales’ uneven distribution, complex structure, and serious noise interference bring difficulties of automatic retinal vessels segmentation on fundus images. To solve these problems, we present an effective retinal vessel segmentation model, SDUW-Net, in this paper. The same scale dense connection is designed to improve U-Net’s structure and remove different scales dense connections to accelerate the training speed. We use skip connections to merges the features between shallow layers and deep layers to retain more features that may be lost in the process of down sampling and convolution. Experimental results on the DRIVE dataset show that the retinal vessels can be effectively segmented out by our proposed SDUW-Net, which has AUC of 0.9811 with low computation and short training time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|