发布求助
文献互助 智能选刊 最新文献

MiFor '10最新文献

筛选
英文 中文
Combining dynamic texture and structural features for speaker identification 结合动态纹理和结构特征进行说话人识别
MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877996
Guoying Zhao, Xiaohua Huang, Y. Gizatdinova, M. Pietikäinen
{"title":"Combining dynamic texture and structural features for speaker identification","authors":"Guoying Zhao, Xiaohua Huang, Y. Gizatdinova, M. Pietikäinen","doi":"10.1145/1877972.1877996","DOIUrl":"https://doi.org/10.1145/1877972.1877996","url":null,"abstract":"Visual information from captured video is important for speaker identification under noisy conditions that have background noise or cross talk among speakers. In this paper, we propose local spatiotemporal descriptors to represent and recognize speakers based solely on visual features. Spatiotemporal dynamic texture features of local binary patterns extracted from localized mouth regions are used for describing motion information in utterances, which can capture the spatial and temporal transition characteristics. Structural edge map features are extracted from the image frames for representing appearance characteristics. Combination of dynamic texture and structural features takes both motion and appearance together into account, providing the description ability for spatiotemporal development in speech. In our experiments on BANCA and XM2VTS databases the proposed method obtained promising recognition results comparing to the other features.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"163 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":"122618400","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: 15
Measuring sample distortions in face recognition 人脸识别中样本畸变的测量
MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877994
M. De Marsico, M. Nappi, D. Riccio
{"title":"Measuring sample distortions in face recognition","authors":"M. De Marsico, M. Nappi, D. Riccio","doi":"10.1145/1877972.1877994","DOIUrl":"https://doi.org/10.1145/1877972.1877994","url":null,"abstract":"In this paper we describe FACE (Face Analysis for Commercial Entities), a framework for face recognition, and show how the approach is made robust to both pose and light variations, thanks to suitable correction strategies. Furthermore, two separate indices are devised for the quantitative assessment of these two kinds of distortions, which allow evaluating the quality of the sample at hand before submitting it to the classifier. Moreover, FACE implements two reliability margins, which, differently from the preceding two, estimate the 'acceptability' of the single response from the classifier. Experimental results show that the overall FACE implementation is able to provide an accuracy (in terms of Recognition Rate) which is better, in some respect, than the present state of art.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"145 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":"122341288","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: 10
Further improvements on secret image sharing scheme 对秘密图像共享方案的进一步改进
MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877989
Saeed Alharthi, P. Atrey
{"title":"Further improvements on secret image sharing scheme","authors":"Saeed Alharthi, P. Atrey","doi":"10.1145/1877972.1877989","DOIUrl":"https://doi.org/10.1145/1877972.1877989","url":null,"abstract":"Secret image sharing technique has been widely researched in the past decade. This technique allows us to create the share images from a secret image in such a way that an individual share does not reveal any information about the secret image, however when a specified number of shares are brought together, they can be used to reconstruct the secret image. In this paper, we first point out the weaknesses of the existing secret image sharing methods proposed by Thien and Lin [8] and Alharthi and Atrey [1], and then propose a new method that overcomes these weaknesses. Thien and Lin [8] use a permutation step which leads to disclosure of the secret image if the permutation key is revealed. Alharthi and Atrey [1] suggested an improvement over Thien and Lin's method by removing the permutation step. However, their method has a limitation that the first few shares are not usable because of its similarity with the secret image. We propose further improvement over these two methods by repeatedly changing the value of share number using a modulo prime function. To show the superiority of our method over others, we present the security analysis and experimental results.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"80 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":"130888957","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: 16
Copy detection of immersed content in video databases 视频数据库中浸入式内容的复制检测
MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877993
Marzia Corvaglia, Fabrizio Guerrini, R. Leonardi, P. Migliorati, E. Rossi
{"title":"Copy detection of immersed content in video databases","authors":"Marzia Corvaglia, Fabrizio Guerrini, R. Leonardi, P. Migliorati, E. Rossi","doi":"10.1145/1877972.1877993","DOIUrl":"https://doi.org/10.1145/1877972.1877993","url":null,"abstract":"Content-Based Copy Detection techniques aim at the identification of modified copies of an original clip in a given database or on the Internet. Usually, a digital fingerprint is computed from the media itself by extracting some features which are later used for the copy detection task. In this paper we propose a system for Video Copy Detection which makes use of several low-level features. In particular we investigate the problem of the detection of copies immersed in dummy multimedia contents. By analyzing the temporal evolution of the selected features, the proposed method detects the relevant part of the query useful for the detection of the original content the query has been extracted from.\u0000 Experiments conducted on the data set provided by MPEG indicate that a combined use of different features can be useful for isolating immersed copies. Moreover we can see that the various features act differently with respect to the type of modification the video query suffered.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"16 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":"126820440","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: 1
Augmented crime scenes: virtual annotation of physical environments for forensic investigation 增强犯罪现场:用于法医调查的物理环境的虚拟注释
MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877999
A. P. Gee, P. J. Escamilla-Ambrosio, Matthew Webb, W. Mayol-Cuevas, A. Calway
{"title":"Augmented crime scenes: virtual annotation of physical environments for forensic investigation","authors":"A. P. Gee, P. J. Escamilla-Ambrosio, Matthew Webb, W. Mayol-Cuevas, A. Calway","doi":"10.1145/1877972.1877999","DOIUrl":"https://doi.org/10.1145/1877972.1877999","url":null,"abstract":"We describe a system aimed at the in-situ 3D annotation of physical objects and environments by the use of augmented reality. The system integrates absolute positioning technology, in the form of GPS and UWB positioning, with real-time computer vision to create a virtual 'incident map'. The virtual map is constructed collaboratively by multiple operatives and a remote control centre. We demonstrate the system operating in a test environment that covers indoor and outdoor areas and explain how the technology may be used to assist forensic investigators as they collect and process evidence in a crime scene.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"29 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":"133159863","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: 18
Semantic object watermark re-synchronization based on skeleton vertex corresponds 基于骨架顶点对应的语义对象水印重同步
MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877979
P. Tzouveli, Konstantinos A. Raftopoulos, K. Ntalianis, S. Kollias
{"title":"Semantic object watermark re-synchronization based on skeleton vertex corresponds","authors":"P. Tzouveli, Konstantinos A. Raftopoulos, K. Ntalianis, S. Kollias","doi":"10.1145/1877972.1877979","DOIUrl":"https://doi.org/10.1145/1877972.1877979","url":null,"abstract":"Plain rotation, scaling, and/or translation of an image can lead to loss of watermark synchronization and thus authentication failure. The block based approaches in particular are sensitive to geometric distortions due to the need for repositioning the block's rectangular grid. In this paper, we propose a novel block based approach for watermarking image objects in a way that is invariant to RST distortions. With the term \"image object\" we refer to semantically contiguous parts of images that have a specific contour boundary. The proposed approach is based on shape information since the watermark is embedded in image blocks, the location and orientation of which is defined by Eulerian tours that are appropriately arranged in layers, around the object's skeleton. The skeleton of the object (MAT transform) is defined by the shape of its boundary and not only is invariant to RST transformations but is also robust to cropping, clipping and other common deformation attacks. Results on the Caltech database are reported, showing the advantages of the proposed scheme","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"1 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":"129349929","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: 1
Estimating QP and motion vectors in H.264/AVC video from decoded pixels 从解码像素估计H.264/AVC视频的QP和运动向量
MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877995
G. Valenzise, M. Tagliasacchi, S. Tubaro
{"title":"Estimating QP and motion vectors in H.264/AVC video from decoded pixels","authors":"G. Valenzise, M. Tagliasacchi, S. Tubaro","doi":"10.1145/1877972.1877995","DOIUrl":"https://doi.org/10.1145/1877972.1877995","url":null,"abstract":"In this paper we present a method for blindly estimating the quantization parameter (QP) and the motion-vectors in H.264/AVC decoded video. We assume that only the decoded pixel values are available. This models pretty well the dissemination over the Internet of user-generated contents, where a video may pass through several coding/processing stages from acquisition to publication and download.\u0000 The proposed technique may be a relevant tool in the forensics field, as it can help to reconstruct the previous history of the digital content, or to provide evidence of tampering.\u0000 Most of the previous work in this direction simply adapts still image forensic approaches to video, but their applicability is in general limited (e.g. they can deal with Intra frames only).\u0000 Conversely, we explicitly take into consideration motion-compensated prediction used by state-of-the-art video codecs such as H.264/AVC to find the QP also for P frames. We show that the so-obtained QPs can be used to estimate the original motion field of the encoder.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"61 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":"121686549","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: 22
Copy-move forgery detection via texture description 通过纹理描述的复制-移动伪造检测
MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877990
E. Ardizzone, A. Bruno, G. Mazzola
{"title":"Copy-move forgery detection via texture description","authors":"E. Ardizzone, A. Bruno, G. Mazzola","doi":"10.1145/1877972.1877990","DOIUrl":"https://doi.org/10.1145/1877972.1877990","url":null,"abstract":"Copy-move forgery is one of the most common type of tampering in digital images. Copy-moves are parts of the image that are copied and pasted onto another part of the same image. Detection methods in general use block-matching methods, which first divide the image into overlapping blocks and then extract features from each block, assuming similar blocks will yield similar features. In this paper we present a block-based approach which exploits texture as feature to be extracted from blocks. Our goal is to study if texture is well suited for the specific application, and to compare performance of several texture descriptors. Tests have been made on both uncompressed and JPEG compressed images.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"1 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":"121183946","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: 64
Privacy preserving video surveillance using pedestrian tracking mechanism 利用行人跟踪机制保护隐私的视频监控
MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877983
Peng Zhang, Tony Thomas, S. Emmanuel, M. Kankanhalli
{"title":"Privacy preserving video surveillance using pedestrian tracking mechanism","authors":"Peng Zhang, Tony Thomas, S. Emmanuel, M. Kankanhalli","doi":"10.1145/1877972.1877983","DOIUrl":"https://doi.org/10.1145/1877972.1877983","url":null,"abstract":"Video surveillance has become a ubiquitous feature of the modern day life. However, the widespread use of video surveillance has raised concerns about the privacy of people. In this paper, we propose a novel video surveillance with a privacy preserving mechanism. We achieve this by combining the techniques of pedestrian tracking based on a Markov chain with two hidden states, elliptical head contour detection and encryption. The detected pedestrian face/head is obscured by encrypting with a unique key derived from a master key for the privacy preservation purpose. The surveillance video can be viewed with complete privacy or by revoking the privacy of any subset of pedestrians while ensuring complete privacy of the remaining pedestrians.The performance evaluation on many challenging surveillance scenarios shows that the proposed mechanism can effectively and robustly track multiple pedestrians and obscure their faces/head in real time.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"34 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":"115973518","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: 14
Video and image identification: tools for supporting forensic investigations 视频和图像识别:支持法医调查的工具
MiFor '10 Pub Date : 2010-10-29 DOI: 10.1145/1877972.1877975
Herwig Lejsek
{"title":"Video and image identification: tools for supporting forensic investigations","authors":"Herwig Lejsek","doi":"10.1145/1877972.1877975","DOIUrl":"https://doi.org/10.1145/1877972.1877975","url":null,"abstract":"The world's law enforcement agencies are increasingly tracking down producers and distributors of offensive multimedia content such as child abuse material. The challenge lies in the vast amount of easily accessible images and videos on the Internet, as well as the large capacities of today's hard drives. Inspecting each and every file is infeasible in practice, given police investigators' limited resources and time. Additionally, such inspection work is repetitive and slow, and in the case of deeply offensive images even psychologically harmful.\u0000 In the presentation we will first review the standard process and challenges that police investigators currently go through when investigating the contents of common storage devices and the challenges connected with this work. Second, we will present the currently available technical toolkits that can assist police investigators and save significant time during this tedious research process. We will focus especially on tools capable of extracting and classifying the content from large collections of multimedia files as this is the most time consuming task for investigators.\u0000 Finally we will look at the problem in a larger context, as not only police departments can benefit from the development of tools helping to automatically identify and/or classify multimedia content. Several other organizations are also involved in the fight against the distribution of offensive multimedia content on the internet, e.g. INHOPE (Internet Hotline Providers in Europe) and NGOs fighting for childrens' rights, as well as associations of internet service providers such as EUROISPA.","PeriodicalId":355677,"journal":{"name":"MiFor '10","volume":"49 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":"133343898","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: 1
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信