This paper presents a method for human action recognition based on patterns of motion. Previous approaches to action recognition use either local features describing small patches...
Due to noise, overlapped text/signature and multi-oriented nature, seal (stamp) object detection involves a difficult challenge. This paper deals with automatic detection of seal ...
This paper introduces an edge-based object recognition method that is robust with respect to clutter, occlusion and object deformations. The method combines the use of local featu...
Abstract. Robust object recognition is one of the most challenging topics in computer vision. In the last years promising results have been obtained using local regions and descrip...
This paper describes work done as part of the Oxford AGV (Autonomous Guided Vehicle) project [2] towards recognition of classes of objects to be encountered in a factory environme...