Combining Local and Global Image Features for Object Class Recognition

• Published in: IEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops p. 47
• Main Authors: Lisin, D.A., Mattar, M.A., Blaschko, M.B., Learned-Miller, E.G., Benfield, M.C.
• Format: Conference Proceeding
• Language: English; Japanese
• Published: IEEE 2005
• Subjects: Aquaculture; Computer science; Computer vision; Error analysis; Face detection; Image recognition; Laboratories; Object recognition; Robustness; Sea measurements

Object recognition is a central problem in computer vision research. Most object recognition systems have taken one of two approaches, using either global or local features exclusively. This may be in part due to the difficulty of combining a single global feature vector with a set of local features...