Pattern Recognition
A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Optimal thresholding—a new approach
Pattern Recognition Letters
Integral Ratio: A New Class of Global Thresholding Techniques for Handwriting Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face detection using multimodal density models
Computer Vision and Image Understanding
Optimal multi-thresholding using a hybrid optimization approach
Pattern Recognition Letters
A multi-level thresholding approach using a hybrid optimal estimation algorithm
Pattern Recognition Letters
Shape matching and registration by data-driven EM
Computer Vision and Image Understanding
On the modeling of DCT and subband image data for compression
IEEE Transactions on Image Processing
IEEE Transactions on Circuits and Systems for Video Technology
Infinite generalized gaussian mixture modeling and applications
ICIAR'11 Proceedings of the 8th international conference on Image analysis and recognition - Volume Part I
Bayesian learning of generalized gaussian mixture models on biomedical images
ANNPR'10 Proceedings of the 4th IAPR TC3 conference on Artificial Neural Networks in Pattern Recognition
Hi-index | 0.01 |
In this paper, a fast estimation method which is developed for estimating the parameters of the generalized Gaussian distribution (GGD) mixture model is presented. In practice, the frequency data observed from complex image intensity is modeled as a random variable, which could be approximated by a GGD mixture model. To seek the ''best-practice'' parameter estimates of the model, the new method intends to combine the merits of the estimation efficiency via statistical estimators and the computation efficiency via evolutionary algorithms, termed the EP2 method. The EP2 method is designed particularly for estimating widely ranged shape parameters that characterizes the Gaussian family densities, including sub- and super-Gaussian densities. Experimental results obtained by modeling both simulated data and complex image histogram data arising from non-Gaussian sources are employed to illustrate the estimation effectiveness and efficiency of the proposed method.