An appearance based neural image processing algorithm for 3-D object recognition

We propose an appearance based neural image processing algorithm for the recognition of 3-D objects with arbitrary pose in a 2-D image. Instead of object segmentation we utilize the wavelet transform to extract compact features for object representation. Translational invariance is achieved by using...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101) Vol. 3; pp. 344 - 347 vol.3
Main Authors: Chunrong Yuan, Niemann, H.
Format: Conference Proceeding
Language:English
Published: IEEE 2000
Subjects:
Feature extraction
Image processing
Image recognition
Image segmentation
Lighting
Object recognition
Pattern recognition
Shape
Target recognition
Wavelet transforms
ISBN:0780362977, 9780780362970
ISSN:1522-4880
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose an appearance based neural image processing algorithm for the recognition of 3-D objects with arbitrary pose in a 2-D image. Instead of object segmentation we utilize the wavelet transform to extract compact features for object representation. Translational invariance is achieved by using two neural network based object pose estimators to translate objects automatically to the image center. Based on these translation-invariant features a neural model is built to identify objects taken at different viewpoint and under different illumination condition. Results for the recognition of real images under occlusions are shown.
ISBN:0780362977
9780780362970
ISSN:1522-4880
DOI:10.1109/ICIP.2000.899388