Rolf P. Würtz

Distortion invariant object recognition in the dynamic link architecture

An object recognition system based on the dynamic link architecture, an extension to classical artificial neural networks (ANNs), is presented. The dynamic link architecture exploits correlations in the fine-scale temporal structure of cellular signals to group neurons dynamically into higher-order entities. These entities represent a rich structure and can code for high-level objects. To demonstrate the capabilities of the dynamic link architecture, a program was implemented that can recognize human faces and other objects from video images. Memorized objects are represented by sparse graphs, whose vertices are labeled by a multiresolution description in terms of a local power spectrum, and whose edges are labeled by geometrical distance vectors. Object recognition can be formulated as elastic graph matching, which is performed here by stochastic optimization of a matching cost function. The implementation on a transputer network achieved recognition of human faces and office objects from gray-level camera images. The performance of the program is evaluated by a statistical analysis of recognition results from a portrait gallery comprising images of 87 persons. >

Object recognition robust under translations, deformations, and changes in background

Recognition systems based on model matching using low level features often fail due to a variation in background. As a solution, I present a system for the recognition of human faces independent of hairstyle. Correspondence maps between an image and a model are established by coarse-fine matching in a Gabor pyramid. These are used for hierarchical recognition.

A sensor for dynamic tactile information with applications in human-robot interaction and object exploration

We present a novel tactile sensor, which is applied for dextrous grasping with a simple robot gripper. The hardware novelty consists of an array of capacitive sensors, which couple to the object by means of little brushes of fibers. These sensor elements are very sensitive (with a threshold of about 5 mN) but robust enough not to be damaged during grasping. They yield two types of dynamical tactile information corresponding roughly to two types of tactile sensor in the human skin. The complete sensor consists of a foil-based static force sensor, which yields the total force and the center of the two-dimensional force distribution and is surrounded by an array of the dynamical sensor elements. One such sensor has been mounted on each of the two gripper jaws of our humanoid robot and equipped with the necessary read-out electronics and a CAN bus interface. We describe applications to guiding a robot arm on a desired trajectory with negligible force, reflective grip improvement, and tactile exploration of objects to create a shape representation and find stable grips, which are applied autonomously on the basis of visual recognition.

Tracking Facial Feature Points with Gabor Wavelets and Shape Models

A feature-based approach to tracking rigid and non-rigid facial motion is described. Feature points are characterised using Gabor wavelets and can be individually tracked by phase-based displacement estimation. In order to achieve robust tracking a flexible shape model is used to impose global constraints upon the local feature points and to constrain the tracker. While there are many applications in facial analysis, the approach can be used for tracking other textured objects.

Genetic determination of human facial morphology: links between cleft-lips and normal variation

Recent genome-wide association studies have identified single nucleotide polymorphisms (SNPs) associated with non-syndromic cleft lip with or without cleft palate (NSCL/P), and other previous studies showed distinctly differing facial distance measurements when comparing unaffected relatives of NSCL/P patients with normal controls. Here, we test the hypothesis that genetic loci involved in NSCL/P also influence normal variation in facial morphology. We tested 11 SNPs from 10 genomic regions previously showing replicated evidence of association with NSCL/P for association with normal variation of nose width and bizygomatic distance in two cohorts from Germany (N=529) and the Netherlands (N=2497). The two most significant associations found were between nose width and SNP rs1258763 near the GREM1 gene in the German cohort (P=6 × 10−4), and between bizygomatic distance and SNP rs987525 at 8q24.21 near the CCDC26 gene (P=0.017) in the Dutch sample. A genetic prediction model explained 2% of phenotype variation in nose width in the German and 0.5% of bizygomatic distance variation in the Dutch cohort. Although preliminary, our data provide a first link between genetic loci involved in a pathological facial trait such as NSCL/P and variation of normal facial morphology. Moreover, we present a first approach for understanding the genetic basis of human facial appearance, a highly intriguing trait with implications on clinical practice, clinical genetics, forensic intelligence, social interactions and personal identity.

Corner detection in color images through a multiscale combination of end-stopped cortical cells

Abstract We assess the corner-detection capabilities of a model for end-stopped cells in the visual cortex (F. Heitger, L. Rosenthaler, R. von der Heydt, E. Peterhans, O. Kubler, Simulation of neural contour mechanisms: from simple to end-stopped cells, Vision Research 32(5) (1992) 963–981). The responses of one of these cells alone cannot account for the percept of a corner. This shortcoming can be greatly alleviated by a combination over several scales. The resulting corner detection method can deal with high frequency texture, low contrast, and rounded corners and is competitive in comparison with other corner detectors. Starting from known cortical cell types we hypothesize a color-sensitive equivalent of simple cells. This allows to extend corner detection to color-sensitive channels. The combination of grey-scale and color corner-detection yields a biologically plausible model of corner perception and may also be of interest for computer vision applications.

GripSee: A Gesture-Controlled Robot for Object Perception and Manipulation

We have designed a research platform for a perceptually guided robot, which also serves as a demonstrator for a coming generation of service robots. In order to operate semi-autonomously, these require a capacity for learning about their environment and tasks, and will have to interact directly with their human operators. Thus, they must be supplied with skills in the fields of human-computer interaction, vision, and manipulation. GripSee is able to autonomously grasp and manipulate objects on a table in front of it. The choice of object, the grip to be used, and the desired final position are indicated by an operator using hand gestures. Grasping is performed similar to human behavior: the object is first fixated, then its form, size, orientation, and position are determined, a grip is planned, and finally the object is grasped, moved to a new position, and released. As a final example for useful autonomous behavior we show how the calibration of the robots image-to-world coordinate transform can be learned from experience, thus making detailed and unstable calibration of this important subsystem superfluous. The integration concepts developed at our institute have led to a flexible library of robot skills that can be easily recombined for a variety of useful behaviors.

Computer-based recognition of dysmorphic faces

Genetic syndromes often involve craniofacial malformations. We have investigated whether a computer can recognize disease-specific facial patterns in unrelated individuals. For this, 55 photographs (256 × 256 pixel) of patients with mucopolysaccharidosis type III (n=6), Cornelia de Lange (n=12), fragile X (n=12), Prader–Willi (n=12), and Williams–Beuren (n=13) syndromes were preprocessed by a Gabor wavelet transformation. By comparing the feature vectors at 32 facial nodes, 42/55 (76%) of the patients were correctly classified. In another four patients (7%), the correct and an incorrect diagnosis scored equally well. Clinical geneticists who were shown the same photographs achieved a recognition rate of 62%. Our results prove that certain syndromes are associated with a specific facial pattern and that this pattern can be described in mathematical terms.

Corner Detection in Color Images by Multiscale Combination of End-Stopped Cortical Cells

We present a corner-detection algorithm based on a model for end-stopping cells in the visual cortex. Shortcomings of this model are overcome by a combination over several scales. The notion of an end-stopped cell and the resulting corner detector is generalized to color channels in a biologically plausible way. The resulting corner detection method yields good results in the presence of high frequency texture, noise, varying contrast, and rounded corners. This compares favorably with known corner detectors.

Syndrome identification based on 2D analysis software

Clinical evaluation of children with developmental delay continues to present a challenge to the clinicians. In many cases, the face provides important information to diagnose a condition. However, database support with respect to facial traits is limited at present. Computer-based analyses of 2D and 3D representations of faces have been developed, but it is unclear how well a larger number of conditions can be handled by such systems. We have therefore analysed 2D pictures of patients each being affected with one of 10 syndromes (fragile X syndrome; Cornelia de Lange syndrome; Williams–Beuren syndrome; Prader–Willi syndrome; Mucopolysaccharidosis type III; Cri-du-chat syndrome; Smith–Lemli–Opitz syndrome; Sotos syndrome; Microdeletion 22q11.2; Noonan syndrome). We can show that a classification accuracy of >75% can be achieved for a computer-based diagnosis among the 10 syndromes, which is about the same accuracy achieved for five syndromes in a previous study. Pairwise discrimination of syndromes ranges from 80 to 99%. Furthermore, we can demonstrate that the criteria used by the computer decisions match clinical observations in many cases. These findings indicate that computer-based picture analysis might be a helpful addition to existing database systems, which are meant to assist in syndrome diagnosis, especially as data acquisition is straightforward and involves off-the-shelf digital camera equipment.