A Replica Inference Approach to Unsupervised Multi-Scale Image Segmentation
arXiv:1106.5793 · doi:10.1103/PhysRevE.85.016101
Abstract
We apply a replica inference based Potts model method to unsupervised image segmentation on multiple scales. This approach was inspired by the statistical mechanics problem of "community detection" and its phase diagram. Specifically, the problem is cast as identifying tightly bound clusters ("communities" or "solutes") against a background or "solvent". Within our multiresolution approach, we compute information theory based correlations among multiple solutions ("replicas") of the same graph over a range of resolutions. Significant multiresolution structures are identified by replica correlations as manifest in information theory overlaps. With the aid of these correlations as well as thermodynamic measures, the phase diagram of the corresponding Potts model is analyzed both at zero and finite temperatures. Optimal parameters corresponding to a sensible unsupervised segmentation correspond to the "easy phase" of the Potts model. Our algorithm is fast and shown to be at least as accurate as the best algorithms to date and to be especially suited to the detection of camouflaged images.
arXiv comment26 pages, 22 figures
References in corpus (18)
- Community structure in social and biological networks
- Community detection in graphs
- Resolution limit in community detection
- Statistical Mechanics of Community Detection
- Community detection in complex networks using Extremal Optimization
- Analysis of the structure of complex networks at different resolution levels
- Phase transition in the detection of modules in sparse networks
- Multiresolution community detection for megascale networks by information-based replica correlations
- Community Detection as an Inference Problem
- Local resolution-limit-free Potts model for community detection
- Limited resolution in complex network community detection with Potts model approach
- Phase transitions in random Potts systems and the community detection problem: spin-glass type and dynamic perspectives
- Locally preferred structure in simple atomic liquids
- Community Detection in Complex Networks by Dynamical Simplex Evolution
- Mesoscopic analysis of networks: applications to exploratory analysis and data clustering
- A Q-Ising model application for linear-time image segmentation
- Limited resolution and multiresolution methods in complex network community detection
- Detection of hidden structures on all scales in amorphous materials and complex physical systems: basic notions and applications to networks, lattice systems, and glasses
Cited by in corpus (14)
- Statistical Mechanics of Multiplex Ensembles: Entropy and Overlap
- Enhancing Crystal Structure Prediction by decomposition methods based on graph theory
- Limits and performances of algorithms based on simulated annealing in solving sparse hard inference problems
- Spatial correlations in attribute communities
- Using complex networks towards information retrieval and diagnostics in multidimensional imaging
- Learning-based Defect Recognition for Quasi-Periodic Microscope Images
- Stochastic Replica Voting Machine Prediction of Stable Cubic and Double Perovskite Materials and Binary Alloys
- Global disorder transition in the community structure of large-q Potts systems
- The stability to instability transition in the structure of large scale networks
- Automatic Segmentation of Fluorescence Lifetime Microscopy Images of Cells Using Multi-Resolution Community Detection
- Local multiresolution order in community detection
- Inference of hidden structures in complex physical systems by multi-scale clustering
- The Stochastic Replica Approach to Machine Learning: Stability and Parameter Optimization
- Unsupervised Community Detection with a Potts Model Hamiltonian, an Efficient Algorithmic Solution, and Applications in Digital Pathology