Binary Segmentation of Multiband Images

We present a method for binary segmentation of multiband images based on a combination of dimensionality reduction techniques (Weighted PCA and Quadratic Programming Feature Selection), classification methods (Gaussian Mixtures Models and Random Forest) and segmentation method (Quadratic Markov Measure Field Models). In this work, four pixels descriptors are presented: Color, Discrete Cosine Transform, Gradient Fields and Adjacency Matrix. Our method combines the outcome of several classifiers using an optimization criterion. That results in a robust method for image segmentation based on color, textures and orientation. We evaluate our method capabilities with different image types for example: color images in RGB format and satellite images. Experimental results demonstrated our method performance.