This paper describes techniques to perform efficient and accurate recognition in difficult domains by matching dense, oriented edge pixels. We model three-dimensional objects as the set of two-dimensional views of the object. Translation, rotation, and scaling of the views are allowed to approximate full three-dimensional motion. A modified Hausdorff measure is used to determine which transformations of each object model are reported as matches. The use of dense, oriented edge pixels allows us to achieve a low rate of false positives. Techniques to prune the search space are used to obtain a system that is efficient in practice. We give results of the system recognizing object views in intensity and infrared images.
Recognition by matching dense, oriented edge pixels
01.01.1995
684589 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Recognition by Matching Dense, Oriented Edge Pixels
British Library Conference Proceedings | 1995
|From Pixels to Edges in Medical Radiographs: A Pattern Recognition Approach to Edge Detection
British Library Conference Proceedings | 1994
|Quantitative steganalysis of least significant bit matching revisited for consecutive pixels
British Library Online Contents | 2014
|Recall or precision-oriented strategies for binary classification of skin pixels
British Library Online Contents | 2008
|IEEE | 1994