检索结果-南通市图书馆

Geometric attack resistant image watermarking based on MSER

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2013年第1期7卷 145-156页

作者： Xuejuan ZHANG xiaochun cao Jingjie LI School of Computer Science and Technology Tianjin University Tianjin 300072 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing 100093 China

Geometric distortions are simple and effective at- tacks rendering many watermarking methods useless. They make detection and extraction of the embedded watermark difficult or even impossible by destroying the synchroniza- tion between the watermark reader and the embedded water- mark. In this paper, we propose a blind content-based image watermarking scheme against geometric distortions. Firstly, the MSER detector is adopted to extract a set of maximally stable extremal regions which are affine covariant and robust to geometric distortions and common signal processing. Sec- ondly, every original MSER is fitted into an elliptical region that was proved to be affine invariant. In order to achieve rota- tion invariance, an image normalization process is performed to transform the elliptical regions into circular ones. Finally, watermarks are repeatedly embedded into every circular disk by modifying the wavelet transform coefficients. Experimen- tal results on standard benchmark demonstrate that the pro- posed scheme is robust to geometric distortions as well as common signal processing.

关键词： image watermarking maximally stable ex- tremal region geometric distortions image normalization wavelet transform

Survey of recent progress in semantic image segmentation with CNNs

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2018年第5期61卷 107-124页

作者： Qichuan GENG Zhong ZHOU xiaochun cao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University State Key Laboratory of Information Security Institute of Information EngineeringChinese Academy of Sciences

In recent years, convolutional neural networks(CNNs) are leading the way in many computer vision tasks, such as image classification, object detection, and face recognition. In order to produce more refined semantic image segmentation, we survey the powerful CNNs and novel elaborate layers, structures and strategies, especially including those that have achieved the state-of-the-art results on the Pascal VOC 2012 semantic segmentation challenge. Moreover, we discuss their different working stages and various mechanisms to utilize the structural and contextual information in the image and feature spaces. Finally, combining some popular underlying referential methods in homologous problems, we propose several possible directions and approaches to incorporate existing effective methods as components to enhance CNNs for the segmentation of specific semantic objects.

关键词： semantic image segmentation CNN Pascal VOC 2012 challenge multi-granularity features construction of contextual relationships

Research on axial bearing capacity of rectangular concrete-filled steel tubular columns based on artificial neural networks

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2017年第5期11卷 863-873页

作者： Yansheng DU Zhihua CHEN Changqing ZHANG xiaochun cao School of Civil Engineering Tianjin University Tianjin 300072 China School of Computer Science and Technology Tianjin University Tianjin 300354 China SKL of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing 100093 China

Design of rectangular concrete-filled steel tubular （CFT） columns has been a big concern owing to their complex constraint mechanism. Generally, most existing methods are based on simplified mechanical model with limited experimental data, which is not reliable under many conditions, e.g., columns using high strength materials. Artificial neural network （ANN） models have shown the effectiveness to solve complex problems in many areas of civil engineering in recent years. In this paper, ANN models were employed to predict the axial bearing capacity of rectangular CFT columns based on the experimental data. 305 experimental data from articles were collected, and 275 experimental samples were chosen to train the ANN models while 30 experimental samples were used for testing. Based on the comparison among different models, artificial neural network modell （ANN1） and artificial neural network model2 （ANN2） with a 20- neuron hidden layer were chosen as the fit prediction models. ANN1 has five inputs： the length （D） and width （B） of cross section, the thickness of steel （t）, the yield strength of steel （fy）, the cylinder strength of concrete （fc＇）- ANN2 has ten inputs： D, B, t, fy, f′, the length to width ratio （D/B）, the length to thickness ratio （D/t）, the width to thickness ratio （B/t）, restraint coefficient （ξ）, the steel ratio （α）. The axial beating capacity is the output data for both *** outputs from ANN1 and ANN2 were verified and compared with those from EC4, ACI, GJB4142 and AISC360-10. The results show that the implemented models have good prediction and generalization capacity. Parametric study was conducted using ANN1 and ANN2 which indicates that effect law of basic parameters of columns on the axial bearing capacity of rectangular CFT columns differs from design *** results also provide convincing design reference to rectangular CFT columns.

关键词： rectangular CFT columns artificial neural net-work axial bearing capacity model prediction parametricstudy

Image composite authentication using a single shadow observation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2015年第9期58卷 122-134页

作者： cao xiaochun ZHAO HanDong WANG Chuan ZHANG Wei State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences

The paper presents a novel method for image composite authentication based on a single shadow in an outdoor image. Existing methods based on the shadow geometry consistency involve more than two shadow observations. We relax the requirement of two shadow observations in the same scene. As a trade-off,we use the information in EXIF(Exchangeable Image File) based on which the ground truth sun elevation is calculated. We also estimate the sun elevation based on geometric constraints the scene provides, whose consistency serves as the cue to authenticate image forgery. It is the first attempt, to our best knowledge, to make use of sun elevation with shadow of one object to authenticate outdoor images. Also, the novel use of GPS(Global Positioning System), and Date and Time data of captured image makes image forensics possible even in one image containing a single shadow. Experimental results on both the synthetic data and visually plausible images demonstrate the performance of the proposed method.

关键词： image forensics solar shadow sun elevation exchangeable image file geometry-based technique

A new encryption scheme for surveillance videos

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2015年第5期9卷 765-777页

作者： xiaochun cao Meili MA Xiaojie GUO Ling DU Dongdai LIN School of Computer Science and Technology Tianjin University Tianjin 300072 China SKL Of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing 100093 China

In this paper, we propose a novel framework to encrypt surveillance videos. Although a few encryption schemes have been proposed in the literature, they are not sufficiently efficient due to the lack of full consideration of the characteristics of surveillance videos, i.e., intensive global redundancy. By taking advantage of such redundancy, we design a novel method for encrypting such videos. We first train a background dictionary based on several frame observations. Then every single frame is parsed into the background and foreground components. Separation is the key to improve the efficiency of the proposed technique, since encryption is only carried out in the foreground, while the background is skillfully recorded by corresponding background recovery coefficients. Experimental results demonstrate that, compared to the state of the art, the proposed method is robust to known cryptanalytic attacks, and enhances the overall security due to the foreground and background separation. Additionally, our encryption method is faster than competing methods, which do not conduct foreground extraction.

关键词： surveillance videos video encryption background and foreground separation

维普期刊数据库

Video color conceptualization using optimization

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2014年第7期57卷 173-183页

作者： cao xiaochun ZHANG YuJie GUO XiaoJie CHEUNG Yiu-Ming School of Computer Science and Technology Tianjin University Department of Computer Science Hong Kong Baptist UniversityHong Kong SARHong Kong 999077China

Color conceptualization aims to propagate"color concepts"from a library of natural color images to the input image by changing the main ***,the existing method may lead to spatial discontinuities in images because of the absence of a spatial consistency *** this paper,to solve this problem,we present a novel method to force neighboring pixels with similar intensities to have similar *** this constraint,the color conceptualization is formalized as an optimization problem with a quadratic cost ***,we further expand two-dimensional(still image)color conceptualization to three-dimensional(video),and use the information of neighboring pixels in both space and time to improve the consistency between neighboring *** performance of our proposed method is demonstrated for a variety of images and video sequences.

关键词： color conceptualization color discontinuity optimization color correspondence video sequence

Semi-fragile watermarking for image authentication based on compressive sensing

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2016年第5期59卷 248-250页

作者： Ling DU xiaochun cao Wei ZHANG Xinpeng ZHANG Na LIU Jianguo WEI School of Computer Science and Technology Tianjin University School of Computer Shenyang Aerospace University State Key Laboratory of Information Security Institute of Information EngineeringChinese Academy of Sciences School of Communication and Information Engineering Shanghai University

Dear editor,With the aid of sophisticated photoediting software,multimedia content security is becoming increasingly prominent[1,2].The problems of verifying the integrity and recovering the alterations have been a major research topic for information security and multimedia[3–6].Semi-fragile watermarking techniques are more powerful in dealing with such cases,which are fragile to malicious modifications meanwhile robust to incidental

关键词： DCT Semi-fragile watermarking for image authentication based on compressive sensing

Photochemical Degradation of Triadimefon in Seawater

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Ocean University of China 2008年第2期7卷 171-176页

作者： SUN xiaochun YANG Guipeng cao Xiaoyan LIN Zhifeng Key Laboratory of Marine Chemistry Theory and Technology Ministry of Education Ocean University of China Qingdao 266100 P. R. China

The photochemical degradation of triadimefon in seawater was investigated under different reaction conditions in this study. The results showed that triadimefon could be effectively degraded by the irradiation of a high-pressure mercury lamp and the photodegradation rates were influenced by aquatic media, heavy metal ions and photosensitizers. The photochemical degradation of triadimefon followed the first-order reaction kinetic behavior, with the rate constants ranging from 0.0027 to 0.0128 min-1 under the studied conditions. The photolysis of triadimefon was slower in natural seawater than in distilled water or synthetic seawater. All the heavy metal ions studied in this paper had inhibition effects on the photolysis of triadimefon. Acetone, as a common photosensitizer, could accelerate the photolysis of triadimefon. Three photoproducts were identified by GC-MS analysis. Our study confirmed that photochemical degradation is an effective pathway to remove triadimefon in seawater.

关键词： triadimefon photochemical degradation seawater photoproducts kinetics

维普期刊数据库

在线全文

学校读者我要写书评

暂无评论

基于后门水印的联邦模型授权方案

网络空间安全科学学报

网络空间安全科学学报 2024年第1期2卷 113-122页

作者：张准李佳睿岳鹏杨文元操晓春中山大学网络空间安全学院深圳 518107

随着分布式机器学习技术在众多领域的深入应用,其模型安全性问题日益凸显。联邦学习作为一种创新的分布式机器学习方法,在保护数据隐私的同时,允许多方参与者共同训练模型。然而,训练得到的模型存在被滥用和难以实现版权保护等方面的问... 详细信息

随着分布式机器学习技术在众多领域的深入应用,其模型安全性问题日益凸显。联邦学习作为一种创新的分布式机器学习方法,在保护数据隐私的同时,允许多方参与者共同训练模型。然而,训练得到的模型存在被滥用和难以实现版权保护等方面的问题,导致恶意用户可能在未经允许的情况下使用模型并谋取经济利益,侵犯参与方的模型版权和知识产权。对于分布式机器学习中存在的模型滥用及版权难以保护的问题,针对联邦学习场景,提出了一种基于后门水印的联邦模型授权方案。该方案在模型训练完成后,通过中心服务器端嵌入后门水印和发放访问令牌,实现对模型使用权的管理。在这一方案下,仅当收集到多数参与方的访问令牌,即获得他们的授权时,用户才能恢复出后门信息,获得模型的使用权;否则,用户在缺乏后门信息的情况下,不能通过模型的验证,无法正常使用模型。在多种数据集上的实验表明,嵌入后门水印的模型与原联邦学习模型相比仅存在可以忽略的精度损失,且能准确验证授权信息,高效识别用户。该方案不仅有效地解决了联邦学习模型的版权保护问题,也大幅提升了联邦学习模型应用的安全性和可靠性。

关键词：分布式机器学习联邦学习模型授权隐私保护后门水印

维普期刊数据库