Name
Abstract | ||
|---|---|---|
In this paper, we introduce the progressive randomization (PR): a new image meta-description approach suitable for different image inference applications such as broad class Image Categorization, Forensics and Steganalysis. The main difference among PR and the state-of-the-art algorithms is that it is based on progressive perturbations on pixel values of images. With such perturbations, PR captures the image class separability allowing us to successfully infer high-level information about images. Even when only a limited number of training examples are available, the method still achieves good separability, and its accuracy increases with the size of the training set. We validate the method using two different inference scenarios and four image databases. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1016/j.cviu.2009.10.002 | Computer Vision and Image Understanding |
Keywords | Field | DocType |
training example,progressive randomization,image databases,different inference scenario,progressive perturbation,image forensics,image class separability,good separability,image categorization,image inference,broad class image,steganalysis,different image inference application,new image meta-description approach | Training set,Computer vision,Steganography,Categorization,Inference,Computer science,Cryptanalysis,Artificial intelligence,Pixel,Steganalysis,Class separability,Machine learning | Journal |
Volume | Issue | ISSN |
114 | 3 | Computer Vision and Image Understanding |
Citations | PageRank | References |
6 | 0.45 | 20 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Anderson Rocha | 1 | 913 | 69.11 |
| Siome Goldenstein | 2 | 618 | 47.43 |