Contour and texture analysis for image segmentation

DOI10.1023/A:1011174803800zbMath0972.68604OpenAlexW2141376824MaRDI QIDQ5944475

Jianbo Shi, Serge Belongie, Jitendra Malik, Thomas Leung

Publication date: 19 November 2001

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1023/a:1011174803800

zbMATH Keywords

segmentationgrayscale image

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10) Computing methodologies and applications (68U99)

Related Items (29)

Multiway \(p\)-spectral graph cuts on Grassmann manifolds ⋮ A biologically motivated multiresolution approach to contour detection ⋮ Improved mean shift segmentation approach for natural images ⋮ Graph Refinement via Simultaneously Low-Rank and Sparse Approximation ⋮ Enabling scalable spectral clustering for image segmentation ⋮ Data Analytics on Graphs Part I: Graphs and Spectra on Graphs ⋮ Normalized cuts revisited: a reformulation for segmentation with linear grouping constraints ⋮ Inference and learning with hierarchical shape models ⋮ Learning behavioural context ⋮ \textit{Kernel cuts}: kernel and spectral clustering meet regularization ⋮ View-based recognition of real-world textures. ⋮ An unconditionally stable hybrid method for image segmentation ⋮ Hypergraph Clustering Using a New Laplacian Tensor with Applications in Image Processing ⋮ Spectral clustering with eigenvector selection ⋮ Fast marching based superpixels ⋮ An optimization-based multilevel algorithm for variational image segmentation models ⋮ Unnamed Item ⋮ Detecting Markov random fields hidden in white noise ⋮ Cartoon and texture decomposition for color image in opponent color space ⋮ A variational model and its numerical solution for local, selective and automatic segmentation ⋮ Customized first and second order statistics based operators to support advanced texture analysis of MRI images ⋮ A bit rate adaptation model for 3D video ⋮ Efficient grey-level image segmentation using an optimised MUSIG (OptiMUSIG) activation function ⋮ Color-texture segmentation using unsupervised graph cuts ⋮ Evaluating performance of image segmentation criteria and techniques ⋮ An approximate distribution for the normalized cut ⋮ Data spectroscopy: eigenspaces of convolution operators and clustering ⋮ Noise robust and rotation invariant framework for texture analysis and classification ⋮ SymNMF: nonnegative low-rank approximation of a similarity matrix for graph clustering

Uses Software

• BSDS

This page was built for publication: Contour and texture analysis for image segmentation