基于零空间分析的计算机生成图像识别研究  

Computer Generated Image Recognition Based on Null Space Analysis

作　　者：李国贞 赵慧娜 林敏 LI Guo-zhen;ZHAO Hui-na;LIN Min(Henan University of Technology,Luohe Institute of Technology,Luohe Henan 462000,China;College of Computer Science and Technology,Inner Mongolia Normal University,Hohhot Inner Mongolia 010022,China)

机构地区：[1]河南工业大学漯河工学院,河南漯河462000 [2]内蒙古师范大学计算机科学技术学院,内蒙古呼和浩特010022

出　　处：《计算机仿真》2022年第1期162-165,185,共5页Computer Simulation

摘　　要：伴随着信息技术的发展,数字图像的真伪识别研究已成为热点,提出一种基于零空间分析的计算机生成图像识别方法。对计算机生成图像和真实图像的生成原理及特点进行研究,分析出可通过图像纹理、噪声和空间域特征上的差异对计算机生成图像和真实图像加以区分。为了解决小样本问题,采用零空间分析方法,建立新的样本矩阵,通过调整正则化因子选择出图片的最优化参数。在零空间算法的基础上,对类内散度矩阵进行正则化处理,结合指数正则化实现计算机生成图片的识别。通过仿真,确定最佳检测率对应的特征维数,并在特征维数基础上得到图片的识别率超过90%,说明基于零空间分析算法对图像的检测精度非常高,具有良好的计算机生成图像识别效果。With the development of information technology, the research of digital image authenticity recognition has become a hot spot. This paper proposes a computer-generated image recognition method based on null space analysis. Firstly, the generation principle and characteristics of computer-generated images and real images were studied It was analyzed that the difference of texture, noise and spatial domain features can be used to distinguish the computer-generated image from the real image. Secondly, in order to solve the problem of small samples, the null space analysis method was used to establish a new sample matrix, and the optimal parameters of the image were selected by adjusting the regularization factor. Finally, on the basis of the null space algorithm, the divergence matrix within the class was regularized and combined with exponential regularization to realize the recognition of computer-generated images. Through the simulation experiment, the feature dimension corresponding to the best detection rate is determined, and the recognition rate of the image is more than 90% based on the feature dimension. It shows that the detection accuracy of images based on zero space analysis algorithm is very high, and it has a good recognition effect of computer-generated images.

关 键 词：零空间分析 图像纹理 计算机生成图像 正则化处理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]