Intensive fruit and vegetable sorting is a common task in productive regions. In order to meet the market standards, produce is classified according to quality levels that depend on maturity degree, weight, size, density, skin defects, etc. Probably the most important of these tasks involve automatic visual inspection. A distributed and scalable system for sorting automation is presented, that addresses all aspects of the quality classification mentioned above. The main characteristics of the system are: it can control from 1 to 10 conveyor belts; its maximum performance is 15 fruits per second per belt; apart from weight sensors, it combines infrared, color and ultraviolet images; some fruit defect modules are available to take account of the presence of a given defect.

This paper describes a method for tracking regions in image sequences. Regions segmented from each frame by a motion segmentation technique are matched by using a relaxation procedure. Matching is based on measuring the similarity of the regions from the current frame and a list of regions corresponding to objects. A Kalman filter is used in order to estimate motion parameters. This filter uses a kinematic model which considers varying acceleration. This assumption allows the system to model the movement when objects are approaching the camera. The tracking method presented here has been successfully applied to traffic monitoring tasks, where it connects to other two computer vision based modules: motion segmentation and temporal integration.

We present a method for estimating the viewpoint from which a 3D image has been taken using a central-projection range sensor. We assume we have the 3D coordinates of the points, organized with a known topology, but considerable noise is present in the data. At points in the scene where there are surface discontinuities, we estimate step rays through a linear interpolation. The viewpoint is found as the point of minimum distance to the set of step rays. To cope with noise, we define an unbiased distance measure. The minimization of the sum of distances provides the viewpoint. We present results of several experiments carried out with 3D images of an old church.

A novel approach for dominant point detection in chain-coded contours is presented. Classical operations, such as computing a measurement of the curvature from the (x, y) co-ordinates of the contour points, finding curvature maxima, etc., are substituted by a neural network that traverses the contour, and gives a measurement of the relevance of every point. Further and straight-forward processing of the network output provides the dominant points. Two translations of the Freeman chain-code are presented, that easily provide the network input from the chain link values. Results with real and test images are presented that show the feasibility of the proposed algorithm. The simulation of the neural computations on a sequential machine makes the execution time of this algorithm of the same order as that of existing algorithms, but the cost can be significantly reduced by executing these computations on a neural-oriented hardware.

A new algorithm for dominant point detection in chain-coded contours is presented. The algorithm directly operates on the chain-code link values. No computation of the (x,y) co-ordinates of the contour points is done, nor any classical computation of the curvature or its derivative. Instead, a dynamic neural network traverses the contour giving a measurement of the relevance of each point, further and simple processing provides the dominant points. The network is trained with the result that a classical dominant point detection algorithm gives for the training contours, and using as training set a number of contours extracted from natural images. Results with real and test images are presented that show the reliability of the proposed algorithm. Since this algorithm is based on applying a neural network to the contour, it significantly reduces the execution time of existing dominant point detection algorithms. Computational time measurements are presented.