| Abstract |
|
A three-stage recognition architecture that can be trained to different recognition or segmentation tasks is presented. It consists of an adaptive feature extraction based on vector quantization and local PCA. Neural expert networks classify the features. It will be shown that the system can be applied to object classification, segmentation of partially occluded objects and classification of object parts without modifications in the architecture.
|
 Additional Information
|
Citation:
Gunther Heidemann, Dirk Lucke, Helge Ritter,
"A System for Various Visual Classification Tasks Based on Neural Networks,"
icpr,
p. 1009,
15th International Conference on Pattern Recognition (ICPR'00) - Volume 1,
2000
|
