Name
Abstract | ||
|---|---|---|
In this paper, we study a family of analytical probability models for images within the spectral representation framework. First the input image is decomposed using a bank of filters, and probability models are imposed on the filter outputs (or spectral components). A two-parameter analytical form, called a Bessel K form, derived based on a generator model, is used to model the marginal probabilities of these spectral components. The Bessel K parameters can be estimated efficiently from the filtered images and extensive simulations using video, infrared, and range images have demonstrated Bessel K form's fit to the observed histograms. The effectiveness of Bessel K forms is also demonstrated through texture modeling and synthesis. In contrast to numeric-based dimension reduction representations, which are derived purely based on numerical methods, the Bessel K representations are derived based on object representations and this enables us to establish relationships between the Bessel parameters and certain characteristics of the imaged objects. We have derived a pseudometric on the image space to quantify image similarities/differences using an analytical expression for L2-metric on the set of Bessel K forms. We have applied the Bessel K representation to texture modeling and synthesis, clutter classification, pruning of hypotheses for object recognition, and object classification. Results show that Bessel K representation captures important image features, suggesting its role in building efficient image understanding paradigms and systems. |
Year | DOI | Venue |
|---|---|---|
2002 | 10.1007/3-540-47969-4_3 | ECCV |
Keywords | Field | DocType |
bessel parameter,bessel k representation,image space,efficient image understanding paradigm,texture modeling,analytical image models,bessel k parameter,spectral component,bessel k form,image similarity,filtered image,object recognition,infrared,dimension reduction,numerical method,image features | Histogram,Computer vision,Dimensionality reduction,Pseudometric space,Feature (computer vision),Computer science,Clutter,Artificial intelligence,Numerical analysis,Cognitive neuroscience of visual object recognition,Bessel function | Conference |
Volume | ISSN | ISBN |
2350 | 0302-9743 | 3-540-43745-2 |
Citations | PageRank | References |
1 | 0.40 | 15 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Anuj Srivastava | 1 | 2853 | 199.47 |
| X. Liu | 2 | 1 | 0.40 |
| Ulf Grenander | 3 | 308 | 80.59 |