Double random field models for remote sensing image segmentation

Authors:
Feng Li;Jiaxiong Peng
Affiliations:
Institute of Pattern Recognition & Artificial Intelligence, Huazhong University of Science & Technology, State Education Commission Key Laboratory, Wuhan and National Laboratory on Machine Percept ...;Institute of Pattern Recognition & Artificial Intelligence, Huazhong University of Science & Technology, State Education Commission Key Laboratory, Wuhan, Hubei 430074, PR China
Venue:
Pattern Recognition Letters
Year:
2004

Citing 9
Cited 5

Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
Simultaneous Parameter Estimation and Segmentation of Gibbs Random Fields Using Simulated Annealing

IEEE Transactions on Pattern Analysis and Machine Intelligence
An iterative Gibbsian technique for reconstruction of m-ary images

Pattern Recognition
Multiple Resolution Segmentation of Textured Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Iterative Growing and Pruning Algorithm for Classification Tree Design

IEEE Transactions on Pattern Analysis and Machine Intelligence
Texture Analysis through a Markovian Modelling and FuzzyClassification: Application to Urban Area Extraction fromSatellite Images

International Journal of Computer Vision
Applications of universal context modeling to lossless compression of gray-scale images

IEEE Transactions on Image Processing
Segmentation of textured images using a multiresolution Gaussian autoregressive model

IEEE Transactions on Image Processing
Estimating Gaussian Markov random field parameters in a nonstationary framework: application to remote sensing imaging

IEEE Transactions on Image Processing

Fast and active texture segmentation based on orientation and local variance

Journal of Visual Communication and Image Representation
Unsupervised texture segmentation/classification using 2-D autoregressive modeling and the stochastic expectation-maximization algorithm

Pattern Recognition Letters
A segmentation method for images compressed by fuzzy transforms

Fuzzy Sets and Systems
Novel classification and segmentation techniques with application to remotely sensed images

Transactions on rough sets VII
A novel MAP-MRF approach for multispectral image contextual classification using combination of suboptimal iterative algorithms

Pattern Recognition Letters

Quantified Score

Hi-index	0.10

Visualization

Abstract

By incorporating the local statistics of an image, a semi-causal non-stationary autoregressive random field can be applied to a non-stationary image for segmentation. Because this non-stationary random field can provide a better description of the image texture than the stationary one, an image can be better segmented. Besides low-order dependence among pixels in image for above-mentioned texture random field, the paper also introduces high-order dependence as a new classification feature to recognize the real object. Entropy rate that depicts the high-order dependence feature can also be estimated by using random field model. The proposed technique is applied to extract urban areas from a Landsat image.