TY  - CHAP
A1  - Elsen, Ingo
A1  - Kraiss, Karl-Friedrich
A1  - Krumbiegel, Dirk
T1  - Pixel based 3D object recognition with bidirectional associative memories
T2  - International Conference on Neural Networks 1997
N2  - This paper addresses the pixel based recognition of 3D objects with bidirectional associative memories. Computational power and memory requirements for this approach are identified and compared to the performance of current computer architectures by benchmarking different processors. It is shown, that the performance of special purpose hardware, like neurocomputers, is between one and two orders of magnitude higher than the performance of mainstream hardware. On the other hand, the calculation of small neural networks is performed more efficiently on mainstream processors. Based on these results a novel concept is developed, which is tailored for the efficient calculation of bidirectional associative memories. The computational efficiency is further enhanced by the application of algorithms and storage techniques which are matched to characteristics of the application at hand.
Y1  - 1997
SN  - 0-7803-4122-8
N1  - June 9 - 12, 1997, Westin Galleria Hotel Houston, Texas, USA.
SP  - 1679
EP  - 1684
PB  - IEEE
CY  - New York
ER  - 
TY  - CHAP
A1  - Walter, Peter
A1  - Elsen, Ingo
A1  - Müller, Holger
A1  - Kraiss, Karl-Friedrich
T1  - 3D object recognition with a specialized mixtures of experts architecture
T2  - IJCNN'99. International Joint Conference on Neural Networks. Proceedings
N2  - Aim of the AXON2 project (Adaptive Expert System for Object Recogniton using Neuml Networks) is the development of an object recognition system (ORS) capable of recognizing isolated 3d objects from arbitrary views. Commonly, classification is based on a single feature extracted from the original image. Here we present an architecture adapted from the Mixtures of Eaqerts algorithm which uses multiple neuml networks to integmte different features. During tmining each neural network specializes in a subset of objects or object views appropriate to the properties of the corresponding feature space. In recognition mode the system dynamically chooses the most relevant features and combines them with maximum eficiency. The remaining less relevant features arz not computed and do therefore not decelerate the-recognition process. Thus, the algorithm is well suited for ml-time applications.
Y1  - 1999
SN  - 0-7803-5529-6
U6  - http://dx.doi.org/10.1109/IJCNN.1999.836243
SN  - 1098-7576
N1  - Washington, DC 10-16.07.1999
SP  - 3563
EP  - 3568
PB  - IEEE
CY  - New York
ER  -