基于敏感图像识别预防水利灾害关键技术研究

Research on Key Technologies of Water Disaster Prevention Based on Pornographic Images Recognition

敏感图像信息多以压缩格式存在、表现形式多样、缺乏统一定义等诸多因素影响着敏感信息识别速度和准确率的提高。针对这个问题,从压缩域图像处理及基于数据挖掘探寻识别规则两个角度出发,采用数据挖掘的方法,在大量的样本数据中探寻隐含的判决规则,并用于进行敏感图像的识别。

The speed and accuracy of pornographic information detection are always affected by some issues, such as the compressed format in which pornographic image is usually stored and transmitted, the diversity of its manifestations and the lack of standard definitions. Considering these facts, a novel and yet effective pornographic image recognition method in compressed domain is proposed. Due to the fact that pornographic images have So many forms of existence and lack of unified ender-user definitions, to obtain the extracted features and the robust decision rules through experience could be a great challenge.