Abstract

Abstract

Abstract
Important aspects of the implementation and calibration of a 3-D data acquisition system based on the ratio of two intensity images are described. These two images are obtained by illuminating the scene with a projector whose light is filtered, successively, by a graded and a constant neutral density filter. Calibration steps, involving the determination of camera and light projector geometric parameters and ratio calibration data, are analyzed. A new ratio calibration procedure is proposed. Results of two depth calculation methods are presented, and system accuracy is evaluated for several test scenes.

Abstract
In this paper, we present a new algorithm for motion flow field estimation using Cellular Neural Networks (CNN). We start from a mathematical viewpoint (i.e. statistical regularisation based on Markov Random Field (MRF) and proceed by mapping the algorithm onto a cellular neural network. Because of the temporal dynamics inherent in the cells of the CNN it is well suited to processing time-varying images. A robust motion estimation algorithm is achieved by using a spatio-temporal neighbourhood for modelling pixel interactions.

Abstract
In this paper we propose an image segmentation algorithm that combines region merging with spectral-based techniques. An initial partitioning of the image into primitive regions is produced by applying a region merging approach which produces a chunk graph that takes in attention the image gradient magnitude. This initial partition is the input to a computationally efficient region segmentation process that produces the final segmentation. The latter process uses a multi-class partition that minimizes the normalized cut value for the region graph. We have efficiently applied the proposed approach with good visual and objective segmentation quality results.

Abstract
A new approach is proposed for the automatic detection of the near-end and far-end intima and adventitia inner boundaries in ultrasound images of the common carotid artery. This method uses the instantaneous coefficient of variation edge detector, fuzzy classification of edges, several discriminating features of the carotid wall boundaries and dynamic programming. The carotid wall boundaries are detected both in healthy and in atherosclerotic arteries, with a wide range of plaque types and sizes. Manual and automatic results are significantly better for the far-end wall, where the automatic detection shows an accuracy similar to manual detections. The application of this approach in clinical practice is encouraged by the results for the far-end wall and the short computation time.