Ramón Rizo Aldeguer

Selection of an automated morphological gradient threshold for image segmentation

Segmentation is an essential part of practically any automated image recognition system, since it is necessary for further processing such as feature extraction or object recognition. There exist a variety of techniques for threshold selection, as it is a fast, simple and robust method. Threshold value will have considerable effects on the boundary position and overall size of the extracted objects. In this work, we propose an automated thresholding selection, which takes into account the local properties of a pixel. To do this, the algorithm calculates the morphological gradient and Laplacian and, afterwards, chooses a suitable threshold after estimating the lowest distance between the ideal segmentation and the morphological gradient thresholding segmentation.

A new artificial life formalization model: a worm with a Bayesian brain

This paper shows an application of Bayesian Programming to model a simple artificial life problem: that of a worm trying to live in a world full of poison. Any model of a real phenomenon is incomplete because there will always exist unknown, hidden variables that influence the phenomenon. To solve this problem we apply a new formalism, Bayesian programming, which has previously been used in autonomous robot programming. The proposed worm model has been used to train a population of worms using genetic algorithms. We will see the advantages of our method compared with a classical approach. Finally, we discuss the emergent behaviour patterns we observed in some of the worms and conclude by explaining the advantages of the applied method.

SBC-RX: Knowledge Based System for Raiodiagnosis and Training of Radiologists. The Teaching File Tool. A New Feature

We present a system based on A.I. techniques and oriented to radiologic diagnosis. SBC-RX uses expert knowledge which is displayed by a graphic interface. It allows queries and helps, explaining reasoning paths and interaction with basic images in order to show the features of each patology. In the new feature the system randomly selects a case problem from the teaching file, and presents it to the user. The diagnosis process is similar to aided diagnosis but the system does not accept incorrect answers from the user. When the diagnosis process ends, the system gives a list of mistakes made by the user and radiologic concepts that may have to be reviewed.