Application of an Improved U-Net Neural Network on Fracture Segmentation from Outcrop Images.
Zhibao WangZiming ZhangLu BaiYuze YangQiang MaPublished in: IGARSS (2022)
Keyphrases
- neural network
- segmentation algorithm
- segmentation method
- test images
- segmented images
- image analysis
- unsupervised segmentation
- segmentation errors
- adaptive thresholding
- edge detection
- input image
- image regions
- segmentation accuracy
- image database
- grey level
- ground truth
- microscopic images
- image data
- image retrieval
- image registration
- image features
- three dimensional
- pixel wise
- intensity images
- gray value
- gray level images
- pixel level
- neural network is trained
- cardiac magnetic resonance
- accurate segmentation
- artificial neural networks
- microscope images
- brain mr images
- image segmentation
- fully automatic
- x ray
- object recognition
- multiscale
- outdoor scenes
- bounding box
- image pixels
- multiple objects
- automatic segmentation
- automated segmentation
- microscopy images
- shape prior
- region growing
- piece wise
- region of interest