A new fast system for objectionable image identification based on shape features

摘要：

The paper introduces a new system for objectionable image identification based on shape feature extraction.The system targets 82％ of the objectionable nude pictures and wrongly classifies 6.98％ of the normal images.The processing speed is 0.115s per common image and 0.31s per pornographic image.The training and testing datasets of benign images are open libraries.The performance of the system is fairly good.

作者: SUN Yan-yan RUAN Qiu-qi

作者单位: Institute of Information Science,Beijing Jiaotong University,Beijing,China 100044

会议类型: 国际会议

会议名称: 9th International Conference on Signal Processing(第九届国际信号处理学术会议)(ICSP08)

会议地点: 北京

会议语种:英文

在线出版日期: 2008-10-26（万方平台首次上网日期，不代表论文的发表时间）