A. Oosterlinck

Range image acquisition with a single binary-encoded light pattern

The problem of strike identification in range image acquisition systems based on triangulation with periodically structured illumination is discussed. A coding scheme is presented based on a single fixed binary encoded illumination pattern, which contains all the information required to identify the individual strikes visible in the camera image. Every sample point indicated by the light pattern is made identifiable by means of a binary signature, which is locally shared among its closest neighbors. The applied code is derived from pseudonoise sequences, and it is optimized so that it can make the identification fault-tolerant to the largest extent. A prototype measurement system based on this coding principle is presented. Experimental results obtained with the measurement system are also presented. >

Vision and Lie's approach to invariance

The application of invariance theory has gained a renewed interest in the computer vision community. Recent results show that it offers a strong, unifying framework that helps in tackling problems such as calibration-less vision, efficient matching, shape-from-motion, grouping, and several other problems considered crucial to intelligent vision. Nonetheless, a systematic approach to the problem of extracting invariants is far from trivial. This paper describes one such approach, the theory of Lie groups. After a concise and non-rigorous account on the method itself, typical problems that arise in vision are discussed. For each of these problems, one or more relevant examples are given.

A knowledge-based system for the delineation of blood vessels on subtraction angiograms

Abstract A new approach to outline blood vessels on angiograms is described, based on a generic blood vessel model and four models for determining segment intersections. These models are generic in the sense that they only rely on the angiographic imaging technique and on the geometrical and topological properties of blood vessels. The models do not depend on specific anatomical knowledge. As a consequence, they can be used as an initial segmentation step to outline the coronary, cerebral as well as the carotid vessels. Results on clinical cerebral subtraction angiograms are presented.

Texture inspection with self-adaptive convolution filters

A resolution-independent method for detection of imperfections in quasi-periodic textures is described. After image standardization, the period is estimated in the horizontal and vertical directions. This determines the size of a sparse convolution mask. Mask coefficients are determined by the well-known technique of eigenfilter extraction. The method thus offers a completely automated generation of a bank of suitable filters, the form and the coefficients of which are made dependent on the texture type to be inspected. After feature extraction in the filtered images, a Mahalanobis classifier is applied.<<ETX>>

Stochastic predictive control of robot tracking systems with dynamic visual feedback

A vision-guided robot workstation is presented which picks up workpieces from a fast-moving conveyor belt. The role of computer vision as the feedback transducer strongly affects the closed-loop dynamics of the overall system, and a tracking controller with dynamic visual feedback is designed for achieving fast response and high control accuracy. In view of the long time delay and the heavy noise corruption embedded in visual data, the problem of visual controller design is posed in the framework of stochastic optimal control theory. The Kalman filter is chosen to estimate the state of the target motion and formulated as a joint detection and adaptive estimation method. The generalized predictive control strategy is utilized to compute the optimal path control data and implemented in a weighted version. Experimental results are given to show the effectiveness of the approach.<<ETX>>

Computer-assisted karyotyping with human interaction.

A system for machine assisted karyotyping and chromosome analysis has been developed. The system uses a drum- or TV-scanner as input device, runs provisionally in 32 K memory, and also allows human interaction on several stages. The accuracy with which banded chromosomes are karyotyped depends strongly on the type of classifier and varies from 40 up to 80%. The accuracy of the human assisted classifier (98%) comes close to that of a skilled technician (99.5%) using manual chromosomal analysis. Due to technical and memory limitations, the time necessary for the karyotyping of one cell is too long and depends on the interaction time; however karyotyping within 5 min, including human interaction, will be possible in the near future.

Chromosome Classification Using A Multi-layer Perceptron Neural Net

In this paper we present our recent study on using neural net systems for automated classification of human chromosomes. A multi-layer perceptron classifier was implemented and trained by a back-propagation algorithm. In comparison with traditional statistical pattern classification techniques, the neural net approach exhibits potential benefits of superior performance, adaptive learning capabilities, and high computation rates provided by massive parallelism. Results of the experiments carried out using both the perceptron and a Bayes classifier on a data set of chromosome feature measurements are given and compared.

A Knowledge-Based System For The 3D Reconstruction And Representation Of The Cerebral Blood Vessels From A Pair Of Stereoscopic Angiograms

This paper presents work in progress concerning an automatic system for the 3D reconstruction and representation of the cerebral vessels. It is based on a separate delineation of the blood vessels in two stereo images. First, we extract blood vessel segments from the image and subsequently we use those high level primitives to guide the stereoscopic matching process. Therefore, we make extensive use of domain specific knowledge like the orientation, thickness and intensity of blood vessels.

Motion-compensated interframe prediction

Motioncompensated interframe prediction has been applied widely in digital television signal coding specially in low bit-rate coding such as videotelephone and videoconference. A key element in motion-compensated interframe prediction is the motion estimation algorithm. In this paper a new motion estimation algorithm is presented. It is based on the block recursive (gradient) method and makes use of some of the advantages of the blockmatching method. Motion estimation with non-integer pd accuracy can be obtained with only a few iterations. In addition some techniques with respect to motion correlation and motion tendency estimation which we proposed before [1] are applied to the estimation algorithm which are efficient enough to improve the performance of the motion estimation and the homogeneity of the estimated motion vector field. The experiment shows that the proposed algorithm has a much higher estimation accuracy and a much better prediction performance than the conventional block motion estimation algorithms. Moreover a coding approach designed effectively to minimize the bit-rate necessary to present the motion vector field is proposed as well. A high compression rate for the transmission of the motion information has been achieved. Finally the simulation results of motioncompensated interframe prediction for low bit-rate coding based on the proposed algorithm and of the motion information encoding are presented.

Regularity Detection As A Strategy In Object Modelling And Recognition

Human subjects easily perceive and extensively use shape regularities such as symmetry or periodicity when they are confronted with the task of object description and recognition. A computer vision algorithm is presented which emulates such behaviour in that it similarly makes use of shape redundancies for the concise description and meaningful segmentation of object contours. This can be compared with the way in which designers proceed in using CAD/CAM. In order to make the problem more accessible to computer programming, the contours are analyzed in so-called arc length space. This novel mapping facilitates the detection and elimination of regularities under a broad range of viewing conditions and yields a natural basis for the formulation of the corresponding model compression rules. Several of the regularities which have traditionally been treated separately, are given a unified substrate.