Abstract | ||
---|---|---|
The success of any object recognition system, whether biological or artificial, lies in using appropriate representation schemes. The schemes should efficiently encode object concepts while being tolerant to appearance variations induced by changes in viewing geometry and illumination. Here, we present a biologically plausible representation scheme wherein objects are encoded as sets of qualitative image measurements. Our emphasis on the use of qualitative measurements renders the representations stable in the presence of sensor noise and significant changes in object appearance. We develop our ideas in the context of the task of face-detection under varying illumination. Our approach uses qualitative photometric measurements to construct a face signature ('ratio-template') that is largely invariant to illumination changes. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1007/3-540-36181-2_25 | Biologically Motivated Computer Vision |
Keywords | Field | DocType |
qualitative representations,qualitative measurement,biologically plausible representation scheme,appearance variation,varying illumination,qualitative image measurement,object recognition system,appropriate representation scheme,object appearance,encode object concept,qualitative photometric measurement,object recognition,face detection | Computer vision,ENCODE,Invariant (mathematics),Artificial intelligence,Face detection,Mathematics,Cognitive neuroscience of visual object recognition | Conference |
Volume | ISSN | ISBN |
2525 | 0302-9743 | 3-540-00174-3 |
Citations | PageRank | References |
16 | 1.17 | 31 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pawan Sinha | 1 | 686 | 176.04 |