首页>
外国专利>
SYSTEM AND METHOD FOR DETECTING IMAGE FORGERY AND ALTERATION VIA CONVOLUTIONAL NEURAL NETWORK, AND METHOD FOR PROVIDING NON-CORRECTION DETECTION SERVICE USING THE SAME
SYSTEM AND METHOD FOR DETECTING IMAGE FORGERY AND ALTERATION VIA CONVOLUTIONAL NEURAL NETWORK, AND METHOD FOR PROVIDING NON-CORRECTION DETECTION SERVICE USING THE SAME
展开▼
机译:通过卷积神经网络检测图像伪造和篡改的系统和方法,以及使用该方法提供无缺陷检测服务的方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
To provide a correction detection system that accurately determines the presence or absence of correction of an image based on deep learning, and a service that detects the presence or absence of correction by using such a system.SOLUTION: The system that detects image forgery and alteration via a convolutional neural network according to an embodiment is a system that detects image forgery and alteration via the convolutional neural network for determining the presence or absence of forgery and alteration or fabrication of an image, and comprises: a correction feature pre-processing unit that passes the image through a high-pass filter to magnify the feature of forgery and alteration or fabrication; a correction feature extraction unit that extracts image correction feature information via a convolutional neural network learned in advance with the image with the magnified feature; a feature refining unit that refines the image correction feature information; and a correction distinguishing unit that determines the presence or absence of forgery and alteration or fabrication of the image based on the image correction feature information refined by the feature refining unit.SELECTED DRAWING: Figure 7
展开▼