We consider the problem of identifying each of multiple objects in a scene with object distortions and background clutter present. A unified correlator architecture is used with inference filters that hierarchically process the input image scene to perform detection, enhancement, recognition, and finally identification. The different levels of the processor use various processing techniques: hit-miss rank-order and erosion/dilation morphological filtering, distortion-invariant filtering, feature extraction, and neural net classification.
Hierarchical scene analysis for object recognition
Signal Processing, Sensor Fusion, and Target Recognition ; 1992 ; Orlando,FL,United States
Proc. SPIE ; 1699
1992-07-09
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Learning Task-Specific Object Recognition and Scene Understanding
British Library Online Contents | 2000
|Improving scene attribute recognition using web-scale object detectors
British Library Online Contents | 2015
|A Local Color Descriptor for Efficient Scene-Object Recognition
British Library Conference Proceedings | 2001
|Special issue on 3D representation for object and scene recognition
British Library Online Contents | 2009
|