Abstract | ||
---|---|---|
In this paper, the a pplication 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 c lassification step in an object recognition system. Therefore, the feature vectors of an object set are learnt and recalled b y an associative memory. In our experiments we are successfully using an associative memory based o n the paradigm of Cellular Neural Networks, CNN. Like Liu and Michel showed, learning in an CNN can be done in a systematic manner by a synthesis procedure which stores all desired memory patterns as reachable memory vectors. |
Year | Venue | Keywords |
---|---|---|
1998 | NC | cellular neural network,feature vector,object recognition,associative memory,time series,optical flow |
Field | DocType | Citations |
3D single-object recognition,Pattern recognition,Time delay neural network,Feature (machine learning),Artificial intelligence,Cellular neural network,Mathematics,Machine learning,Neural gas,Cognitive neuroscience of visual object recognition | Conference | 0 |
PageRank | References | Authors |
0.34 | 8 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mariofanna G. Milanova | 1 | 155 | 20.19 |
Ulrich Büker | 2 | 22 | 7.27 |