###
计算机系统应用:2018,27(9):100-106
本文二维码信息
码上扫一扫!
基于多分类和ResNet的不良图片识别框架
王景中, 杨源, 何云华
(北方工业大学 计算机学院, 北京 100144)
Pornographic Images Recognition Framework Based on Multi-Classification and ResNet
WANG Jing-Zhong, YANG Yuan, HE Yun-Hua
(College of Computer, North China University of Technology, Beijing 100144, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 181次   下载 178
投稿时间:2018-01-14    修订日期:2018-02-09
中文摘要: 针对实际应用中色情图片的复杂多样性问题,提出一种基于多分类和深度残差网络(ResNet)的不良图片识别框架.不同于已有的方法将色情图片识别作为二分类问题,该方法基于多样性特征将色情图片分为7个更细粒度的类别,并将正常图片分为是否包含人物2个类别,通过50层ResNet模型进行分类,再按照阈值计算是否属于不良图片.为了减少训练时间和挖掘优质特征,采用一种反馈修正的训练策略.提出一种单边滑动窗口的预处理方法以解决图片不同尺度的影响问题.测试结果表明,该方法在时间效率和识别准确率上效果良好.
Abstract:To filter the variety of pornographic images in the reality Internet, the study proposed a Pornographic Images Recognition (PIR) framework based on multi-classification and deep Residual Network (ResNet). Traditional methods usually consider the PIR task as a binary classification, while the approach presented in this paper divides porno images into 7 detailed classes based on its variety features with 2 more benign image classes (with or without human in it). The approach relies on 50-ResNet to extract image features automatically, and then decides whether it belongs to porno images based on the highest score and gives threshold value. At training stage, a feedback-reconstruct training tactics is adopted for the network to collect better features. To deal with images in different scales, a monolateral sliding window method is taken to get better performance. After testing on the data set constructed with collected images from the Internet, the experimental result shows that the approach can reach high accuracy with lower time cost.
文章编号:     中图分类号:    文献标志码:
基金项目:国家自然科学基金(61371142)
引用文本:
王景中,杨源,何云华.基于多分类和ResNet的不良图片识别框架.计算机系统应用,2018,27(9):100-106
WANG Jing-Zhong,YANG Yuan,HE Yun-Hua.Pornographic Images Recognition Framework Based on Multi-Classification and ResNet.COMPUTER SYSTEMS APPLICATIONS,2018,27(9):100-106

用微信扫一扫

用微信扫一扫