No abstract

Obtaining the glottal space segmentation is essential to characterize morphological disorders of vocal folds. In this study, the tested images are been acquired by direct optical inspection of the glottis using an endoscope and most of them are very poor quality. The application of motion estimation is very useful to segment the vocal folds endoscopic videos without user interaction. This approach involves three process steps: 1) Wiener motion estimator--to shift the measurement the next frame regarding to the current frame, and look for similarities between them. The best matching will accurate a shift equal to the displacement vector of the object; 2) Segmentation using motion estimation results and applying Gabor filtering; 3) Experimental results to demonstrate that the proposed method is effective. Our proposal works correctly with 95% of database test videos and it shows a great advance in design, and in the nearby future, a complete method to diagnose vocal folds pathologies.

No abstract

In this paper, we explore a new correlation technique for cross-spectral image registration. The proposed technique matches the orientation feature of the second derivatives while making use of a statistical robust M estimator. Furthermore, it takes advantage of Fourier and multi-resolution techniques to reduce the complexity of spatial correlation. Simulation results show that our proposed approach gives more accurate results than the mutual information, and the normalized cross-correlation with prefiltering in terms of speed and accuracy.