DMCA
Object Recognition in Image Sequences with Cellular Neural Networks
| Citations: | 1 - 0 self |
BibTeX
@MISC{Milanova_objectrecognition,
author = {Mariofanna Milanova and Ulrich Büker and Heinz Nixdorf},
title = {Object Recognition in Image Sequences with Cellular Neural Networks},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper, the application of CNN associative memories for 3D object recognition is presented. The main idea is to analyse the optical flow in an image sequence of an object. Several features of the optical flow between two succeeding images are calculated and merged to a time series of features for the whole image sequence. These features show several object specific characteristics and are used for a classification step in an object recognition system. Therefore, the feature vectors of an object set are learnt and recalled by an associative memory based on the paradigm of Cellular Neural Networks, CNN. 1 Introduction The question, how does the human visual system represent three-dimensional objects for recognition and how technical solutions can be found, has been the topic of many research, [2], [5], [14], [26]. A very common idea is the integration of several subsystems like attention windows, preprocessing, feature generation on the basis of intensity, colour or motion, etc....
Keyphrases
object recognition image sequence cellular neural network optical flow associative memory object recognition system common idea several subsystem feature vector technical solution whole image sequence feature generation time series several feature main idea many research cnn associative memory attention window several object specific characteristic classification step
