Abstract | ||
---|---|---|
Scene classification is a major open challenge in machine vision. Most solutions proposed so far such as those based on color histograms and local texture statistics cannot capture a scene's global configuration, which is critical in perceptual judgments of scene similarity. We present a novel approach, “configural recognition”, for encoding scene class structure. The approach's main feature is its use of qualitative spatial and photometric relationships within and across regions in low resolution images. The emphasis on qualitative measures leads to enhanced generalization abilities and the use of low-resolution images renders the scheme computationally efficient. We present results on a large database of natural scenes. We also describe how qualitative scene concepts may be learned from examples |
Year | DOI | Venue |
---|---|---|
1997 | 10.1109/CVPR.1997.609453 | San Juan |
Keywords | Field | DocType |
computer vision,encoding,image classification,natural scenes,object recognition,visual databases,color histograms,configural recognition,configuration based scene classification,image indexing,large database,learning from examples,local texture statistics,low resolution images,natural scenes,scene class structure | Histogram,Computer vision,Pattern recognition,Machine vision,Computer science,Search engine indexing,Scene statistics,Artificial intelligence,Contextual image classification,Perception,Encoding (memory),Cognitive neuroscience of visual object recognition | Conference |
Volume | Issue | ISSN |
1997 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
0-8186-7822-4 | 79 | 32.68 |
References | Authors | |
3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
P. Lipson | 1 | 79 | 33.01 |
W. E. L. Grimson | 2 | 11451 | 2002.95 |
Pawan Sinha | 3 | 686 | 176.04 |