Segmenting motion capture data into distinct behaviors
GI '04 Proceedings of the 2004 Graphics Interface Conference
Blind spectral unmixing by local maximization of non-Gaussianity
Signal Processing
ICA mixture model algorithm for unsupervised classification of remote sensing imagery
International Journal of Remote Sensing
A general procedure for learning mixtures of independent component analyzers
Pattern Recognition
A Case Study of ICA with Multi-scale PCA of Simulated Traffic Data
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
Text detection in images using sparse representation with discriminative dictionaries
Image and Vision Computing
Separating pigment components of leaf color image using FastICA
ICIC'10 Proceedings of the 6th international conference on Advanced intelligent computing theories and applications: intelligent computing
IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
Target detection based on a dynamic subspace
Pattern Recognition
Hi-index | 0.01 |
An unsupervised classification algorithm is derived by modeling observed data as a mixture of several mutually exclusive classes that are each described by linear combinations of independent, non-Gaussian densities. The algorithm estimates the data density in each class by using parametric nonlinear functions that fit to the non-Gaussian structure of the data. This improves classification accuracy compared with standard Gaussian mixture models. When applied to images, the algorithm can learn efficient codes (basis functions) for images that capture the statistically significant structure intrinsic in the images. We apply this technique to the problem of unsupervised classification, segmentation, and denoising of images. We demonstrate that this method was effective in classifying complex image textures such as natural scenes and text. It was also useful for denoising and filling in missing pixels in images with complex structures. The advantage of this model is that image codes can be learned with increasing numbers of classes thus providing greater flexibility in modeling structure and in finding more image features than in either Gaussian mixture models or standard independent component analysis (ICA) algorithms