Identification of kernels in a convolutional neural network: connections between the level set equation and deep learning for image segmentation.
Jonas A. ActorDavid T. FuentesBéatrice RivièrePublished in: Medical Imaging: Image Processing (2020)
Keyphrases
- deep learning
- level set
- image segmentation
- level set method
- method for image segmentation
- active contours
- unsupervised feature learning
- curve evolution
- finite difference
- unsupervised learning
- shape prior
- signed distance function
- partial differential equations
- hamilton jacobi
- region competition
- geodesic active contours
- machine learning
- image segmentation methods
- evolution equation
- variational framework
- restricted boltzmann machine
- energy function
- level set framework
- markov random field
- weakly supervised
- energy functional
- piecewise constant
- multiphase segmentation
- image processing
- mental models
- variational level set method
- deep belief networks
- region growing
- higher order
- multiscale
- segmentation method
- graph cuts
- chan vese
- feature space
- computer vision