Obscenity Detection Using Haar-Like Features and Gentle Adaboost Classifier
文献类型：期刊论文
| 作者 | Mustafa, Rashed; Min, Yang; Zhu, Dingju |
| 刊名 | SCIENTIFIC WORLD JOURNAL
 |
| 出版日期 | 2014 |
| 英文摘要 | Large exposure of skin area of an image is considered obscene. This only fact may lead to many false images having skin-like objects and may not detect those images which have partially exposed skin area but have exposed erotogenic human body parts. This paper presents a novel method for detecting nipples from pornographic image contents. Nipple is considered as an erotogenic organ to identify pornographic contents from images. In this research GentleAdaboost (GAB) haar-cascade classifier and haar-like features used for ensuring detection accuracy. Skin filter prior to detection made the system more robust. The experiment showed that, considering accuracy, haar-cascade classifier performs well, but in order to satisfy detection time, train-cascade classifieris suitable. To validate the results, we used 1198 positive samples containing nipple objects and 1995 negative images. The detection rates for haar-cascade and train-cascade classifiers are 0.9875 and 0.8429, respectively. The detection time for haar-cascade is 0.162 seconds and is 0.127 seconds for train-cascade classifier. |
| 收录类别 | SCI |
| 原文出处 | http://www.hindawi.com/journals/tswj/2014/753860/ |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/6018]  |
| 专题 | 深圳先进技术研究院_数字所 |
| 作者单位 | SCIENTIFIC WORLD JOURNAL |
| 推荐引用方式 GB/T 7714 | Mustafa, Rashed,Min, Yang,Zhu, Dingju. Obscenity Detection Using Haar-Like Features and Gentle Adaboost Classifier[J]. SCIENTIFIC WORLD JOURNAL,2014. |
| APA | Mustafa, Rashed,Min, Yang,&Zhu, Dingju.(2014).Obscenity Detection Using Haar-Like Features and Gentle Adaboost Classifier.SCIENTIFIC WORLD JOURNAL. |
| MLA | Mustafa, Rashed,et al."Obscenity Detection Using Haar-Like Features and Gentle Adaboost Classifier".SCIENTIFIC WORLD JOURNAL (2014). |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。