Object Extraction From Very High-Resolution Images Using a Convolutional Neural Network Based on a Noisy Large-Scale Dataset.
Panle LiXiaohui HeXijie ChengXu GaoRunchuan LiMengjia QiaoDaidong LiFangbing QiuZhiqiang LiPublished in: IEEE Access (2019)
Keyphrases
- object extraction
- prior shape information
- image database
- input image
- image understanding
- image classification
- million images
- image data
- image analysis
- segmentation method
- image retrieval
- object segmentation
- segmentation algorithm
- small number
- image features
- computer vision
- test images
- image annotation
- ground truth
- image content
- three dimensional
- similarity measure
- image processing