BSDA-Net: A Boundary Shape and Distance Aware Joint Learning Framework for Segmenting and Classifying OCTA Images.
Li LinZhonghua WangJiewei WuYijin HuangJunyan LyuPujin ChengJiong WuXiaoying TangPublished in: CoRR (2021)
Keyphrases
- region based segmentation
- image data
- hausdorff distance
- region features
- three dimensional
- learning algorithm
- image segmentation
- distance map
- image gradient
- texture information
- object boundaries
- shape model
- image regions
- image classification
- image database
- input image
- object recognition
- digitized images
- geometrical properties
- prior shape knowledge
- image edges
- closed curves
- test images
- segmentation method
- edge detection