Title | Object recognition in image sequences with cellular neural networks |
Publication Type | Journal Article |
| 2000 |
Authors | Milanova, M, Büker, U |
Journal | NeurocomputingNeurocomputing |
Volume | 31 |
Issue | 1-4Amsterdam, Netherlands |
Pagination | 125 - 141 |
Date Published | 2000/// |
| 09252312 (ISSN) |
| algorithm, artificial neural network, Associative memory, Associative storage, Cellular neural networks, Computational methods, computer system, Image analysis, Image sequences, mathematical computing, Object recognition, Optical flow, Optical flows, Pattern recognition, Pattern recognition systems, priority journal, review, Three dimensional computer graphics, Time series analysis, Vectors |
| 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). (C) 2000 Elsevier Science B.V.In this paper, the application of CNN associative memories for 3D object recognition is presented. The main idea is to analyze 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).
|
| http://www.scopus.com/inward/record.url?eid=2-s2.0-0343852159&partnerID=40&md5=ecb858090fa38d7d39e6142515efac59 |