We suggest using distributed associative memory (DAM) to integrate visual information from multiple cues or sources for performing invariant object recognition. We assume that the output of the sources vary consistently for a given input. We perform a series of experiments whose goal is to assess our approach to the data fusion problem. The database is made up of 15 classes of colored polyhedral objects. Each object in the database underwent a specific linear transformation and was correctly identified. The same applies to occlusion and noise. Our results show that for points close to the central locations of the objects being viewed the response is correct.
|Original language||English (US)|
|Number of pages||1|
|Issue number||1 SUPPL|
|State||Published - Jan 1 1988|
|Event||International Neural Network Society 1988 First Annual Meeting - Boston, MA, USA|
Duration: Sep 6 1988 → Sep 10 1988