arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.03771cs.CV
收藏

基于加权多示例学习的色情图像识别

Pornographic Image Recognition via Weighted Multiple Instance Learning

Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Megvii Inc. (Face++)(旷视科技(Face++))

Jin Xin, Wang Yuhui, Tan Xiaoyang

摘要:

在互联网时代,识别色情图像对于保护儿童身心健康具有重要意义。然而,这项任务是非常具有挑战性的,因为关键的色情内容(例如,乳房和私处)通常位于小尺寸的局部区域中。在本文中,我们将每个图像建模为一个区域袋,并遵循多实例学习(MIL)的方法来训练一个通用的基于区域的识别模型。具体来说,我们考虑到该地区的色情程度,并作出三个主要贡献。首先,我们表明,基于训练图像中的关键色情内容的很少的注释,我们可以生成一个适当大小的区域,其中潜在的积极区域通常包含有用的上下文,可以帮助识别。其次,我们提出了一个简单的定量测量一个地区的色情程度,它可以用来衡量不同地区的重要性,在一个积极的形象。第三,我们将识别任务表示为卷积神经网络框架下的加权MIL问题,并引入袋概率函数来结合不同区域的重要性。在我们新收集的大规模数据集上的实验证明了该方法的有效性,在10万张色情图像和10万张正常图像上的测试结果表明,该方法的正确率为97.52%,假阳性率为1%。

英文摘要:

In the era of Internet, recognizing pornographic images is of great significance for protecting children's physical and mental health. However, this task is very challenging as the key pornographic contents (e.g., breast and private part) in an image often lie in local regions of small size. In this paper, we model each image as a bag of regions, and follow a multiple instance learning (MIL) approach to train a generic region-based recognition model. Specifically, we take into account the region's degree of pornography, and make three main contributions. First, we show that based on very few annotations of the key pornographic contents in a training image, we can generate a bag of properly sized regions, among which the potential positive regions usually contain useful contexts that can aid recognition. Second, we present a simple quantitative measure of a region's degree of pornography, which can be used to weigh the importance of different regions in a positive image. Third, we formulate the recognition task as a weighted MIL problem under the convolutional neural network framework, with a bag probability function introduced to combine the importance of different regions. Experiments on our newly collected large scale dataset demonstrate the effectiveness of the proposed method, achieving an accuracy with 97.52% true positive rate at 1% false positive rate, tested on 100K pornographic images and 100K normal images.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑