一种新型的基于内容的图像识别与过滤方法

A novel algorithm for content-based image recognition and filtering

实现了一种新型的网络敏感图像过滤系统。在此系统中,浏览模块和图像过滤模块协调通信、相互交换数据信息,可实时过滤网页中的敏感信息。在图像过滤模块中,通过肤色滤波器来获取图像中的肤色信息,并引入非线性Gamma矫正方法以弱化光照影响。接下来采用图像区域分割、块区域生长、点与区域的投票机制获取图像中的感兴趣区域,然后在这些区域内勾画出躯干的轮廓并获取局部信息。实验结果表明我们的算法能够实时准确地过滤网页中的敏感图像。

This paper presents a novel approach to blocking objection- able images. This system integrates an image filter module into a browser module. Blocking objectionable images is completed by the data interactions between the two modules. In the image filter module, a skin filter is designed to obtain the skin information, and a new Gamma correction method is introduced to reduce the illumination effect. To process an image quickly, we split it into several regions and a voting scheme is adopted to obtain some potential regions that can describe the attributes of the image. From the regions of interest, the contour of the body trunk is finally sketched and the local information is extracted from it. Experimental results show that our algorithm is capable of blocking objectionable images successfully with low computational cost.