MiFor '10最新文献_第2页

Bags of phrases with codebooks alignment for near duplicate image detection 短语袋与码本对齐近重复图像检测

MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877991

S. Battiato, G. Farinella, G. Guarnera, Tony Meccio, G. Puglisi, D. Ravì, Rosetta Rizzo

引用次数: 17

Semi-interactive tracing of persons in real-life surveillance data 半交互式跟踪人在现实生活中的监控数据

MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877985

Michael J. Metternich, M. Worring

{"title":"Semi-interactive tracing of persons in real-life surveillance data","authors":"Michael J. Metternich, M. Worring","doi":"10.1145/1877972.1877985","DOIUrl":"https://doi.org/10.1145/1877972.1877985","url":null,"abstract":"To increase public safety, more and more surveillance cameras have been placed over the years. To deal with the resulting information overload many methods have been deployed, focusing either on real-time crime detection or post-incident investigation. In this paper we concentrate on post-incident investigation i.e. crime reconstruction using video data. For a complete crime reconstruction, the location of all persons of interest should be known before and during the incident. To do so, we follow persons within the field of view of a single camera (tracking) and between different cameras (tracing).\u0000 We present a semi-interactive approach to post-incident investigation. This method is specifically capable of tracking and tracing persons of interest. Our system supports the analytical reasoning process of the investigator with automatic analysis, visualization methods, and interaction processing. We show that the automatic tracing method significantly speeds up tracing of persons with clear visual characteristics. Tracing of persons without obvious characteristics is an inherently difficult task, but we show that intelligent use of interactive methods greatly improves the tracing performance of our system.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130651428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

On the influence of denoising in PRNU based forgery detection 去噪对基于PRNU的伪造检测的影响

MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1878002

G. Chierchia, S. Parrilli, G. Poggi, Carlo Sansone, L. Verdoliva

引用次数: 76

Building fingerprints with information from three color bands for source camera identification 利用三种颜色波段的信息构建指纹，用于源相机识别

MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1878001

Yongjian Hu, Chang-Tsun Li, Chao Jian

引用次数: 8

Videntifier" Forensic: large-scale video identification in practice “取证”:大规模视频识别的实践

MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877973

Herwig Lejsek, Hrönn Þormóðsdóttir, F. Ásmundsson, Kristleifur Daðason, Á. Jóhannsson, B. Jónsson, L. Amsaleg

引用次数: 8

A videosurveillance data browsing software architecture for forensics: from trajectories similarities to video fragments 一种用于取证的视频监控数据浏览软件架构:从轨迹相似性到视频片段

MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877984

Manuel Aravecchia, S. Calderara, Sara Chiossi, R. Cucchiara

引用次数: 5

Imputing human descriptions in semantic biometrics 语义生物识别中人类描述的输入

MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877982

D. Reid, M. Nixon

引用次数: 27

A visual tool for forensic analysis of mobile phone traffic 一个可视化工具，用于对移动电话流量进行法医分析

MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877992

Salvatore Catanese, G. Fiumara

{"title":"A visual tool for forensic analysis of mobile phone traffic","authors":"Salvatore Catanese, G. Fiumara","doi":"10.1145/1877972.1877992","DOIUrl":"https://doi.org/10.1145/1877972.1877992","url":null,"abstract":"In this paper we present our tool LogAnalysis for forensic visual statistical analysis of mobile phone traffic. LogAnalysis graphically represents the relationships among mobile phone users with a node-link layout. Its aim is to explore the structure of a large graph, measure connectivity among users and give support to visual search and automatic identification of organizations. To do so, LogAnalysis integrates graphical representation of network elements with measures typical of Social Network Analysis (SNA) in order to help detectives or forensic analysts to systematically examine relationships. The analysis of data extracted from mobile phone traffic logs has a fundamental relevance in forensic investigations since it allows to unveil the structure of relationships among individuals suspected to be part of criminal organizations together with the role they play inside the organization itself. To this purpose, the Social Network Analysis (SNA) methods were heavily employed in order to understand the importance of relationships. Interpretation and visual exploration of graphs representing phone contacts over a given time interval may become demanding, due to the presence of numerous nodes and edges. Our main contribution is an interface that enables systematic analysis of social relationships using visual different techniques and statistical information. LogAnalysis allows a deeper and clearer understanding of criminal associations while evidencing key members inside the criminal ring, and/or those working as link among different associations","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"516 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133633682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 24

An automatic transcription system of hearings in Italian courtrooms 意大利法庭听证会的自动转录系统

MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877998

D. Falavigna, M. Gerosa, D. Giuliani, R. Gretter

引用次数: 2

A game-theoretic system security design for the visible watermarking 基于博弈论的可见水印系统安全设计

MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877980

Min-Jen Tsai, Jung Liu

{"title":"A game-theoretic system security design for the visible watermarking","authors":"Min-Jen Tsai, Jung Liu","doi":"10.1145/1877972.1877980","DOIUrl":"https://doi.org/10.1145/1877972.1877980","url":null,"abstract":"Digital watermarking has been widely studied and regarded as a potentially effective means for protecting copyright of digital media in recent years. Among different categories of researches for digital watermarking, visible watermarking protect copyrights in a more active way since the approach not only prevents pirates but also visually recognizes the copyrights of multimedia data. However, how to determine the equilibrium of optimal security strategies between encoder and attacker and the optimal tradeoff between the intensity of embedded watermark and the perceptual translucence for visible watermark is becoming a subject of importance. Therefore, in order to achieve the best tradeoff between the embedding energy of watermark, the quality of perceptual watermark translucence and the image fidelity after attacks, a novel game-theoretic system security design for visible watermarking is proposed in this study. The watermark embedding problem is formulated as a dynamic non-cooperative game with complete information while the optimal strategy is defined by the Nash equilibrium of the game. The experimental results demonstrate the feasibility of the proposed approach which allows the watermark encoder to obtain the best watermarking strategy under attacks. Accordingly, our research could help to resolve security issue of visual communication.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116651461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4