A5044683742- Advanced Image Processing Techniques
- Image Processing Techniques and Applications
- Advanced Vision and Imaging
- Image and Video Stabilization
- Retinal Imaging and Analysis
- Iterative Learning Control Systems
- Brain Tumor Detection and Classification
- Retinal and Optic Conditions
- Advanced Image Fusion Techniques
- Adaptive Control of Nonlinear Systems
- Advanced Control Systems Optimization
Nanjing University of Aeronautics and Astronautics
2022-2023
Since the neural network was introduced into super-resolution (SR) field, many SR deep models have been proposed and achieved excellent results. However, there are two main drawbacks: one is that methods based on best peak-signal-to-noise ratio (PSNR) do not enough comfortable visual quality; other although generative adversarial (GAN) satisfactory quality, structure of reconstructed image has apparent defects. Therefore, according to characteristics human eyes sensitive high-frequency...
The segmentation model based on UNET can better deal with the extraction of blood vessels in medical retinal images, but it is generally poor microvessels. Therefore, this paper proposes a vessel semantic fusion, attention mechanism and multi-scale features(SAM-UNet). First, SAM-UNet designs convolution multiple sizes layers to extract features, ensuring its higher ability less computation. Then, constructs encoder-decoder fusion module communicate information, layer-layer information...