Name
Abstract | ||
|---|---|---|
Since the large diffusion of digital camera and mobile devices with embedded camera and flashgun, the redeyes artifacts have de facto become a critical problem. The technique herein described makes use of three main steps to identify and remove red eyes. First, red-eye candidates are extracted from the input image by using an image filtering pipeline. A set of classifiers is then learned on gray code features extracted in the clustered patches space and hence employed to distinguish between eyes and noneyes patches. Specifically, for each cluster the gray code of the red-eyes candidate is computed and some discriminative gray code bits are selected employing a boosting approach. The selected gray code bits are used during the classification to discriminate between eye versus non-eye patches. Once red-eyes are detected, artifacts are removed through desaturation and brightness reduction. Experimental results on a large dataset of images demonstrate the effectiveness of the proposed pipeline that outperforms other existing solutions in terms of hit rates maximization, false positives reduction, and quality measure. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1155/2010/909043 | EURASIP J. Image and Video Processing |
Keywords | Field | DocType |
patches space,gray code,red-eyes removal,input image,selected gray code bit,false positives reduction,embedded camera,brightness reduction,discriminative gray code bit,large dataset,digital camera | Computer vision,Pattern recognition,Computer science,Filter (signal processing),Gray code,Digital camera,Boosting (machine learning),Artificial intelligence,Biometrics,Discriminative model,Maximization,False positive paradox | Journal |
Volume | Issue | ISSN |
2010, | 1 | 1687-5281 |
Citations | PageRank | References |
1 | 0.36 | 12 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sebastiano Battiato | 1 | 659 | 78.73 |
| Giovanni Maria Farinella | 2 | 412 | 57.13 |
| Mirko Guarnera | 3 | 53 | 6.59 |
| Messina, G. | 4 | 159 | 13.42 |
| Daniele Ravì | 5 | 232 | 12.31 |