Semi-automatic acquisition and labelling of image data using SOMs (2008)
Gunther Heidemann, Axel Saalbach, Helge Ritter
Abstract. Application of neural networks for real world object recognition suffers from the need to acquire large quantities of labelled image data. We propose a solution that acquires images from a...
Image and Vision Computing 23 (2005) 861–876 Unsupervised image categorization (2008)
Large image collections require efficient organization and visualization. This paper describes an approach to establish image categories automatically by unsupervised learning. The method works free...
Multimodal Interaction in an Augmented Reality Scenario ABSTRACT (2008)
Gunther Heidemann, Ingo Bax, Holger Bekel
We describe an augmented reality system designed for online acquisition of visual knowledge and retrieval of memorized objects. The system relies on a head mounted camera and display, which allow the...
Representing object manifolds by parametrized SOMs (2008)
Axel Saalbach, Gunther Heidemann, Helge Ritter
The recognition and pose estimation of threedimensional objects is a challenging task that requires suitable object representations. In this paper, we propose the “Parametrized Self-Organizing Map...
Learning to Recognise Objects and Situations to Control a Robot End-Effector (2008)
Gunther Heidemann, Helge Ritter
View based representations have become very popular for recognition tasks. In this contribution, we argue that the potential of the approach is not yet fully tapped: Tasks need not to be...
Interactive Image Data Labeling Using Self-Organizing Maps in an Augmented Reality Scenario (2008)
Holger Bekel, Gunther Heidemann, Helge Ritter
Abstract — We present an approach for the convenient labeling of image patches gathered from an unrestricted environment. The system is employed for a mobile Augmented Reality (AR) gear: While the...
Exploration based on Neural Networks with Applications in Manipulator Control (2007)
Ján Jockusch, Vollständiger Abdruck Der, Prof Dr, ...
ion . . . . . . . . . . . . . . . . . . . . . 25 4 The Controller Layer 29 4.1 The Controller Structure . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.2 Mechanisms for Safety and...
Combining spatial and colour information for content based image retrieval (2004)
Colour is one of the most important features in content based image retrieval. However, colour is rarely used as a feature that codes local spatial information, except for colour texture. This paper...
Efficient Vector Quantization using the WTA-rule with Activity Equalization (2001)
Gunther Heidemann, Gunther Heidemann, Helge Ritter, Helge Ritter
Abstract. We propose a new algorithm for vector quantization, the Activity Equalization Vector quantization (AEV). It is based on the winner takes all rule with an additional supervision of the...
Artificial Neural Networks for Automated Quality Control of Textile Seams (1999)
Claus Bahlmann, Gunther Heidemann, Helge Ritter, Ag Neuroinformatik
We present a method for an automated quality control of textile seams, which is aimed to establish a standardized quality measure and to lower costs in manufacturing. The system consists of a...
Combining Multiple Neural Nets for Visual Feature Selection and Classification (1999)
Gunther Heidemann, Helge Ritter
We present a system for object recognition in real images employing three dierent types of neural networks, which accomplish feature extraction and-classication. The main advantages of the method are...
Artificial Neural Networks for Automated Quality Control of Textile Seams (1999)
Claus Bahlmann, Gunther Heidemann, Helge Ritter, Ag Neuroinformatik, ...
We present a method for an automated quality control of textile seams, which is aimed to establish a standardized quality measure and to lower costs in manufacturing. The system consists of a...
Ein flexibel einsetzbares Objekterkennungssystem auf der Basis neuronaler Netze / (1998)
Zugl.: Bielefeld, Universiẗat, Diss., 1998.
A Hybrid Object Recognition Architecture (1996)
Gunther Heidemann, Franz Kummert, Helge Ritter, Gerhard Sagerer
. We present an architecture for 3D-object recognition based on the integration of neural and semantic networks. The architecture consists of mainly two components. A neural object recognition system...
A Neural Recognition Architecture for Composed Objects (1996)
Gunther Heidemann, Helge Ritter
We present an architecture for object recognition based on artificial neural networks (ANN). The system can be trained on the holistic recognition of wooden toy pieces and aggregates composed of...
A Neural 3-D Object Recognition Architecture Using Optimized Gabor Filters (1995)
Gunther Heidemann, Helge Ritter
We present an object recognition architecture based on feature extraction by Gabor filter kernels and feature classification by an artificial neural network. The parameters of the Gabor filters are...
Fronts between Hopf- and Turing-type domains in a two-component reaction-diffusion system (1993)
Heidemann, Gunther, Bode, Matthias, Purwins, Hans-Georg
Propagating and standing fronts between Hopf- and Turing-type domains are observed experimentally on a one-dimensional array of resistively coupled nonlinear LC-oscillators describable by a...