Deep convolutional neural networks with spatial regularization, volume and star-shape priors for image segmentation

DOI10.1007/s10851-022-01087-xOpenAlexW4224024937MaRDI QIDQ2103871

Xiangyue Wang, Jun Liu, Xue-Cheng Tai

Publication date: 9 December 2022

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2002.03989

zbMATH Keywords

threshold dynamicsimage segmentationvolume preservingentropic regularizationDCNNspatial regularizationstar-shape

Mathematics Subject Classification ID

Computer science (68-XX) Information and communication theory, circuits (94-XX)

Related Items (1)

Connections between Operator-Splitting Methods and Deep Neural Networks with Applications in Image Segmentation

Uses Software

• DeepLab
• GrabCut
• SegNet
• U-Net
• CCNet
• Skin-Lesion-Analyzer

Cites Work

• Unnamed Item
• Unnamed Item
• Techniques for gradient-based bilevel optimization with non-smooth lower level problems
• Global minimization for continuous multiphase partitioning problems using a dual approach
• Image segmentation using some piecewise constant level set methods with MBO type of projection
• On the scaling of multidimensional matrices
• Motion of multiple junctions: A level set approach
• Convex analysis approach to d. c. programming: Theory, algorithms and applications
• A simple scheme for volume-preserving motion by mean curvature
• An efficient iterative thresholding method for image segmentation
• Auction dynamics: a volume constrained MBO scheme
• Mean curvature, threshold dynamics, and phase field theory on finite graphs
• Short-time heat flow and functions of bounded variation in \(\mathbb R^N\)
• Threshold dynamics for the piecewise constant Mumford-Shah functional
• An MBO Scheme on Graphs for Classification and Image Processing
• Optimal approximations by piecewise smooth functions and associated variational problems
• Active contours without edges
• Convolution-Generated Motion and Generalized Huygens' Principles for Interface Motion
• Linkage Between Piecewise Constant Mumford--Shah Model and Rudin--Osher--Fatemi Model and Its Virtue in Image Segmentation
• A Smoothed Dual Approach for Variational Wasserstein Problems
• Threshold Dynamics for Networks with Arbitrary Surface Tensions
• A Weighted Dictionary Learning Model for Denoising Images Corrupted by Mixed Noise
• A regularized convolutional neural network for semantic image segmentation
• Convex analysis and monotone operator theory in Hilbert spaces

This page was built for publication: Deep convolutional neural networks with spatial regularization, volume and star-shape priors for image segmentation