Share Email Print

Proceedings Paper

A hierarchical feed-forward network for object detection tasks
Author(s): Ingo Bax; Gunther Heidemann; Helge Ritter
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Recent research on Neocognitron-like neural feed-forward architectures, which have formerly been successfully applied to recognition of artifical stimuli like paperclip objects, is promising application to more natural stimuli. Several authors have shown high recognition performance of such networks with respect to translation, rotation, scaling and cluttered surroundings. In this contribution, we introduce a variation of existing hierarchical models, that is trained using a non-negative matrix factorization algorithm. In contrast to previous work, our approach can not 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. Though in principle an exhaustive search by classification of every sub-window of an image is performed, the process is nevertheless highly efficient. 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. Detection is achieved by attaching an additional network layer, whose simple cell profiles are learned from the final classification units that were acquired during the training phase. 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: 28 March 2005
PDF: 9 pages
Proc. SPIE 5818, Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks III, (28 March 2005); doi: 10.1117/12.605958
Show Author Affiliations
Ingo Bax, Bielefeld Univ. (Germany)
Gunther Heidemann, Bielefeld Univ. (Germany)
Helge Ritter, Bielefeld Univ. (Germany)

Published in SPIE Proceedings Vol. 5818:
Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks III
Harold H. Szu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?