Combining Feature- and Correspondence-Based Methods for Visual Object Recognition

Günter Westphal, Rolf P. Würtz
2009 Neural Computation  
We present an object recognition system built on a combination of feature-and correspondence-based pattern recognizers. The featurebased part, called preselection network, is a single-layer feedforward network weighted with the amount of information contributed by each feature to the decision at hand. For processing arbitrary objects, we employ small, regular graphs whose nodes are attributed with Gabor amplitudes, termed parquet graphs. The preselection network can quickly rule out most
more » ... ule out most irrelevant matches and leaves only the ambiguous cases, socalled model candidates, to be verified by a rudimentary version of elastic graph matching, a standard correspondence-based technique for face and object recognition. According to the model, graphs are constructed that describe the object in the input image well. We report the results of experiments on standard databases for object recognition. The method achieved high recognition rates on identity and pose. Unlike many other models, it can also cope with varying background, multiple objects, and partial occlusion.
doi:10.1162/neco.2009.12-07-675 pmid:19292649 fatcat:ldqzd7bqgjczvizxxxucmhilz4