Here some typical and suggestive research works dedicating in Active Contours or Level Sets are provided, grouped according to the ways by which they capture image information, including learning-based models, edge-baesd models, region-based models and shape-prior-based models. Also, some ACMs for global optimization are introduced, can be found at the end of this page.
These models segment images using the features captured by Deep Convolutional Neural Network (DCNN). As a result, more hierarchical image information can be learned, leading to more accurate results. But the dataset containing large amounts of annotated images is required, like the following two papers:
Deep Level Sets for Salient Object Detection. Ping Hu, Bing Shuai, Jun Liu, and Gang Wang, CVPR 2017.
Learning Deep Structured Active Contours End-to-End. Diego Marcos, Devis Tuia, Benjamin Kellenberger, Lisa Zhang, Min Bai, Renjie Liao, Raquel Urtasun, CVPR 2018. [code]
These models segment images based on the assumption that objects to be segmented have distinct boundaries. To this end, their energy functionals are designed to move active contours towards the place where intensities change sharply, in which gradient information is the most frequently used cue. But segmentation process is prone to be disturbed by noise and clutter scene.
Distance Regularized Level Set Evolution and Its Application to Image Segmentation. Chunming Li, Chenyang Xu, Changfeng Gui, and Martin D. Fox, IEEE Trans on Image Processin, 2010. [code]
Decoupled Active Contour (DAC) for Boundary Detection. Akshaya K. Mishra, Paul W. Fieguth, and David A. Clausi, IEEE Trans on Pattern Analysis and Machine Intelligence, 2011.
Generally, these models use a certain kind of descriptor (e.g. intensity, color, texture) or their combinations to describe different regions in input images. The goal of these models is to divide input images into several regions in which descriptors are distributed evenly. Because segmentation process depends on the image information from all pixels, more robust results can be achieved than edge-based models. For intensity and texture descriptors, some typical models are listed as follows:
- Intensity descriptor
Minimization of Region-Scalable Fitting Energy for Image Segmentation. Chunming Li, Chiu-Yen Kao, John C. Gore, and Zhaohua Ding, IEEE Trans on Image Processing, 2008. [website and code]
Active Contours Driven by Local Gaussian Distribution Fitting Energy. Li Wang, Lei He, Arabinda Mishra, and Chunming Li, Signal Processing, 2009. [code]
Active Contours Driven by Local Image Fitting Energy. Kaihua Zhang, Huihui Song, and Lei Zhang, Pattern Recognition, 2010. [code]
A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities with Application to MRI. Chunming Li, Rui Huang, Zhaohua Ding, J. Chris Gatenby, Dimitris N. Metaxas, and John C. Gore, IEEE Trans on Image Processing, 2011. [website and code]
A Level Set Approach to Image Segmentation with Intensity Inhomogeneity. Kaihua Zhanga, Lei Zhanga, Kin-Man Lamb, and David Zhang, IEEE Trans on Cybernetics, 2016. [website code]
- Texture descriptor
Active unsupervised texture segmentation on a diffusion based feature space. M. Rousson, T. Brox, and R. Deriche, CVPR 2003.
Local Histogram Based Segmentation Using the Wasserstein Distance. Kangyu Ni, Xavier Bresson, Tony Chan, and Selim Esedoglu, International Journal of Computer Vision, 2009. [code]
Incorporating Patch Subspace Model in Mumford–Shah Type Active Contours. Junyan Wang, and Kap Luk Chan, IEEE Trans on Image Processing, 2013. [code]
Sparse Texture Active Contour. Yi Gao, Sylvain Bouix, Martha Shenton, and Allen Tannenbaum, IEEE Trans on Image Processing, 2013.
Enhanced Decoupled Active Contour Using Structural and Textural Variation Energy Functionals. Dorothy Lui, Christian Scharfenberger, Khalil Fergani, Alexander Wong, and David A. Clausi, IEEE Trans on Image Processing, 2014. [website and code]
Hybrid Structural and Texture Distinctiveness Vector Field Convolution for Region Segmentation. K.Fergani, D.Lui, C.Scharfenberger, A.Wong, and D.A.Clausi, Computer Vision and Image Understanding, 2014.
Using Prior Shapes in Geometric Active Contours in a Variational Framework. Yunmei Chen, Hemant D. Tagare, Sheshadri Thiruvenkadam, Feng Huang, David Wilson, Kaundinya S. Gopinath, Richard W. Briggs, and Edward A. Geiser, International Journal of Computer Vision, 2002.
Level Set Based Shape Prior Segmentation. Tony Chan, and Wei Zhu, CVPR 2005.
A Variational Model for Object Segmentation Using Boundary Information and Shape Prior Driven by the Mumford-Shah Functional. Xavier Bresson, Pierre Vandergheynst, Jean-Philippe Thiran, International Journal of Computer Vision, 2006. [code]
ACMs for Global Minimization
Algorithms for finding global minimizers of image segmentation and denoising models. Tony F. Chan, Selim Esedoglu, and Mila Nikolova, SIAM Journal on Applied Mathematics, 2006.
Fast Global Minimization of the Active Contour/Snake Model. Xavier Bresson, Selim Esedoḡlu, Pierre Vandergheynst, Jean-Philippe Thiran, and Stanley Osher, Journal of Mathematical Imaging and Vision, 2007.[code]
Geometric Applications of the Split Bregman Method: Segmentation and Surface Reconstruction. Tom Goldstein, Xavier Bresson, Stanley Osher, Journal of Scientific Computing, 2010. [website and code]
Fast and globally convex multiphase active contours for brain MRI segmentation. Juan C. Moreno, V.B. Surya Prasath, Hugo Proença, and K. Palaniappan, Computer Vision and Image Understanding, 2014.