FSAM: A fast self-adaptive method for correcting non-uniform illumination for 3D reconstruction.
Muwei JianJunyu DongKin-Man LamPublished in: Comput. Ind. (2013)
Keyphrases
- synthetic data
- computationally efficient
- segmentation method
- fully automatic
- objective function
- detection method
- pairwise
- significant improvement
- computational cost
- optimization algorithm
- high accuracy
- evaluation method
- high precision
- support vector machine
- preprocessing
- image quality
- input data
- computational complexity
- similarity measure
- feature selection
- structure from motion
- learning algorithm
- machine learning