Nudity detection in color images
The proliferation of nude images is a problem that affects families, the workplace, and society in general. To address this problem, many studies in visual content security are being done. However, the current state of technology is still crude, yielding inexact results at the cost of computing powe...
Saved in:
| Main Author: | |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Animo Repository
2004
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/etd_masteral/3227 https://animorepository.dlsu.edu.ph/context/etd_masteral/article/10065/viewcontent/CDTG003796_P.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Language: | English |
| Summary: | The proliferation of nude images is a problem that affects families, the workplace, and society in general. To address this problem, many studies in visual content security are being done. However, the current state of technology is still crude, yielding inexact results at the cost of computing power. Thus, new methods for nudity detection are being sought. In this study, a new algorithm for detecting nudity in color images is developed. A skin color distribution model is constructed using correlation and linear regression. This model is used to identify and locate skin regions in an image. These regions are analyzed for clues indicating nudity or non-nudity such as their sizes and relative distances from each other. Based on these clues and the percentage of skin in the image, an image is classified nude or non-nude. The skin color distribution model performs with 96.29% recall and 6.76% false positive rate on a test set consisting of 2,303,824 manually labeled skin pixels and 24,285,952 manually labeled non-skin pixels. The Nudity Detection Algorithm is able to detect nudity with a 94.77% recall and a false positive rate of 5.04% on a set of images consisting of 421 nude images and 635 non-nude images. |
|---|