Information Audit Based on Image Content Filtering

At present, network information audit system is almost based on text information filtering, but badness information is embedded into image or image file directly by badness information provider, in order to avoid monitored by. The paper realizes an information audit system based on image content filtering. Taking the pornographic program identification for an example, the system can monitor the video including any abnormal human body information by matching the texture characters with those defined in advance, which consist of contrast, energy, correlation measure and entropy character measure and so on.

一种基于图像内容过滤的有线电视网信息审计系统

如何实现广播电视网节目内容的自动审计已成为目前广播电视网网络安全所面临的问题。笔者首先分析了目前有线电视网节目内容的审计,大多基于人工,不仅费时费力,且与先进的现代电视技术极不相匹配,接着对图像内容过滤的关键技术进行了分析,并用反差、能量、熵、相关4个特征量表示纹理特征,在此基础上用交互的动态规划法来进行图像对象分割然后利用相似度描述两个特征量的相似程度,最后以对黄色内容识别为实例,通过提取图像的纹理特征与定义好的特征库相匹配,监控包含不良人体图像信息的视频,实现对有线电视网节目内容的自动审计。