Cue Integration by Similarity Rank List Coding - Application to Invariant Object Recognition
Autor: | Raul Grieben, Rolf P. Würtz |
---|---|
Rok vydání: | 2017 |
Předmět: |
business.industry
3D single-object recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Cue integration Cognitive neuroscience of visual object recognition Pattern recognition Single view Histogram Computer vision Artificial intelligence Invariant (mathematics) business Invariant object recognition Coding (social sciences) Mathematics |
Zdroj: | FAS*W@SASO/ICCAC |
Popis: | Similarity rank lists provide a method for learning generalization of classifiers from examples. Here, we apply it to invariant object recognition and demonstrate that it performs better than other approaches on view and illumination invariant recognition. Recognition from a single view reaches 87% success rate. To study its real world capabilities we introduce subsqare rank matching that works on image patches and RUBJECTS100, a database of 100 objects under varying pose and illumination, and a set of natural scenes containing these objects. |
Databáze: | OpenAIRE |
Externí odkaz: |