Segmentation method, image analysis

Segmentation method based on the analysis by Co-Occurrence Matrix is developed. We try to increase the quality of the obtained results by means of the application of two dimensional (2D) processing. We use Co-Occurrence Matrix for ultrasonic image segmentation. This tool, introduced by Haralick (1), was selected for the present study as several general considerations were favourable ... 

Gorretta, N. et al (2012) An iterative hyperspectral image segmentation method using a cross analysis of spectral and spatial information. Chemom. Intell. Lab. Syst, 117, 213-223. 

As mention in section 1, the Symmlet, ForwaRD and WaveD method have limitations. The orientation, scale and symmetry subband of the medical images decomposition present many advantages for medical image analysis and feature extraction. This is one of the reasons which our proposed performs better than the other methods. For example, an orientation map computed at the end of a line segment will produce a bimodal response. The filters are almost always either symmetric or antisymmetric. The... 

Recently, a method used for the analysis of frequency-domain data has been proposed for the analysis of time-domain images. The AB-plot or phasor plot provides a useful graphical representation of lifetime data that can be used for the segmentation of the images prior to data fitting [47, 48], With this method, data fitting may be avoided in many instances. 

---