Share Email Print
cover

Optical Engineering

Hierarchical feed-forward network for object detection tasks
Author(s): Ingo Bax; Gunther Heidemann; Helge Ritter
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Recent research on neocognitron-like neural feed-forward architectures, which have formerly been successfully applied to the recognition of artificial stimuli such as paperclip objects, now also opens up application to more natural stimuli. Such networks exhibit high-recognition performance with respect to translation, rotation, scaling and cluttered surroundings. In this contribution, we introduce a new type of hierarchical model, which is trained using a non-negative matrix factorization algorithm. In contrast to previous work, our approach cannot only classify objects but is also capable of rapid object detection in natural scenes. Thus, the time-consuming and conceptually unsatisfying split-up into a localization stage (e.g., using segmentation) and a subsequent classification can be avoided. The network consists of alternating layers of simple and complex cell planes and incorporates nonlinear processing schemes that have been proposed in recent literature. Learning of receptive field profiles for the lower layers of the network takes place by unsupervised learning whereas a final classification layer is trained supervised. This final layer is then utilized for detection. We test the classification performance of the network on images of natural objects which are systematically distorted. To test the ability to detect objects, cluttered natural background is used.

Paper Details

Date Published: 1 June 2006
PDF: 10 pages
Opt. Eng. 45(6) 067203 doi: 10.1117/1.2209948
Published in: Optical Engineering Volume 45, Issue 6
Show Author Affiliations
Ingo Bax, Univ. Bielefeld (Germany)
Gunther Heidemann, Univ. Bielefeld (Germany)
Helge Ritter, Univ. Bielefeld (Germany)


© SPIE. Terms of Use
Back to Top