Unsupervised texture segmentation using Gabor filters
Pattern Recognition
International Journal of Computer Vision
Unsupervised Texture Segmentation in a Deterministic Annealing Framework
IEEE Transactions on Pattern Analysis and Machine Intelligence
Interactive segmentation with Intelligent Scissors
Graphical Models and Image Processing
ACM SIGGRAPH 2004 Papers
"GrabCut": interactive foreground extraction using iterated graph cuts
ACM SIGGRAPH 2004 Papers
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Random Walks for Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Global Minimization of the Active Contour/Snake Model
Journal of Mathematical Imaging and Vision
GeoS: Geodesic Image Segmentation
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Color-texture segmentation using unsupervised graph cuts
Pattern Recognition
Image segmentation based on GrabCut framework integrating multiscale nonlinear structure tensor
IEEE Transactions on Image Processing
Geometric Applications of the Split Bregman Method: Segmentation and Surface Reconstruction
Journal of Scientific Computing
IEEE Transactions on Image Processing
Integrated active contours for texture segmentation
IEEE Transactions on Image Processing
Texture analysis and classification with tree-structured wavelet transform
IEEE Transactions on Image Processing
Semi-supervised clustering via multi-level random walk
Pattern Recognition
Hi-index | 0.01 |
The problem of segmenting a foreground object out from its complex background is of great interest in image processing and computer vision. Many interactive segmentation algorithms such as graph cut have been successfully developed. In this paper, we present four technical components to improve graph cut based algorithms, which are combining both color and texture information for graph cut, including structure tensors in the graph cut model, incorporating active contours into the segmentation process, and using a ''softbrush'' tool to impose soft constraints to refine problematic boundaries. The integration of these components provides an interactive segmentation method that overcomes the difficulties of previous segmentation algorithms in handling images containing textures or low contrast boundaries and producing a smooth and accurate segmentation boundary. Experiments on various images from the Brodatz, Berkeley and MSRC data sets are conducted and the experimental results demonstrate the high effectiveness of the proposed method to a wide range of images.