V. Chatzis, Fotios K. Panagiotopoulos, V. Mardiris
{"title":"Face to Iris Area Ratio as a feature for children detection in digital forensics applications","authors":"V. Chatzis, Fotios K. Panagiotopoulos, V. Mardiris","doi":"10.1109/DMIAF.2016.7574915","DOIUrl":"https://doi.org/10.1109/DMIAF.2016.7574915","url":null,"abstract":"This paper presents a new geometrical feature based on iris geometry for automatic children detection in digital images. The proposed feature is based on simple geometrical measures of face elements and especially iris. Iris outer boundary is approximated as a circle and the proposed feature is defined using the iris area and the distance of iris from mouth line. This approach is compared with two similar geometrical features. Experimental results show the superiority of the proposed feature over the existing ones. The proposed feature is more robust compared to the existing features that use geometrical information from human faces and gives better classification results, useful to digital forensics applications.","PeriodicalId":404025,"journal":{"name":"2016 Digital Media Industry & Academic Forum (DMIAF)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131463676","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}
Efstratios Kakaletsis, O. Zoidi, A. Tefas, N. Nikolaidis, I. Pitas
{"title":"Fast label propagation on facial images using a pruned similarity matrix","authors":"Efstratios Kakaletsis, O. Zoidi, A. Tefas, N. Nikolaidis, I. Pitas","doi":"10.1109/DMIAF.2016.7574911","DOIUrl":"https://doi.org/10.1109/DMIAF.2016.7574911","url":null,"abstract":"The label propagation process, which is often used to semantically annotate (tag) large amounts of multimedia data assets must be fast, in order to be efficient. In this paper, a novel facial images fast labeling method that is essentially a semi-supervised face recognition approach, is presented. The proposed method is based on the acceleration of a state of the art facial identity label propagation technique. The new method is called pruned label propagation due to the fact that the facial label inference is conducted using a similarity matrix containing fewer entries, namely the pairwise similarities that reside in the main and the off-diagonals of this matrix. Experiments conducted on facial image labeling in three stereoscopic movies, confirm the increased labeling accuracy and the reduced computational complexity of the proposed method.","PeriodicalId":404025,"journal":{"name":"2016 Digital Media Industry & Academic Forum (DMIAF)","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134300393","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}
{"title":"An expert subjective evaluation of a Reshaper model vs HDR10 for HDR coding","authors":"V. Baroncini, P. Topiwala","doi":"10.1109/DMIAF.2016.7574901","DOIUrl":"https://doi.org/10.1109/DMIAF.2016.7574901","url":null,"abstract":"This paper presents the results of a subjective evaluation experiment, made to compare different HDR coding technologies, conducted at the recent ITU/ISO/IEC VCEG/ MPEG/JPEG Meeting in San Diego, CA, February 2016. A set of “anchor” streams, conforming to the HDR10 spec, was compared to a similar rate-matched set obtained using a method called “Reshaper”, which requires normative changes to the underlying HEVC Main10 Profile. The subjective evaluation experiment was done involving sixteen “video coding expert” subjects, sitting two-at-a-time in front of a 4000-nit capable SIM2 monitor, at a distance equal to 2.5 times the screen height. The test itself followed the Expert Viewing Protocol (EVP) developed by one of the authors (V. B.). EVP involves the sequential viewing of (a) uncompressed original, (b) codec A, (c) codec B. To minimize as much as possible judgment biases, several randomizations in the presentation order were used. Performance results are presented in a graphical form for ease of analysis. It is noted that the Reshaper model provides some visual benefits in a minority of cases, notably at a mid-rate setting, while differences at lower and higher rates were within a margin of error. This paper focuses on the test methodology and results more than the specifics of the technology under test.","PeriodicalId":404025,"journal":{"name":"2016 Digital Media Industry & Academic Forum (DMIAF)","volume":"392 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124285493","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}
{"title":"Restoration of missing data in Greek folk music by interpolation techniques","authors":"P. Medentzidou, Constantine Kotropoulos","doi":"10.1109/DMIAF.2016.7574912","DOIUrl":"https://doi.org/10.1109/DMIAF.2016.7574912","url":null,"abstract":"Music recordings often suffer from noise. The noisy segments may be treated as missing data. To restore them, one may employ interpolation techniques. A music signal is modeled as an autoregressive process, and three interpolation methods are developed that are based on maximum likelihood, Gibbs sampling, and Expectation Maximization. The aforementioned techniques are tested for restoration of missing data in vocal and instrumental Greek folk songs. Experimental results show that interpolation techniques based on maximum likelihood and Gibbs sampling offer better restoration results than Expectation Maximization.","PeriodicalId":404025,"journal":{"name":"2016 Digital Media Industry & Academic Forum (DMIAF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116803269","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}
{"title":"Securing big data in the Cloud by protected mapping over multiple providers","authors":"Chunming Rong, Hongbing Cheng, M. Jaatun","doi":"10.1109/DMIAF.2016.7574925","DOIUrl":"https://doi.org/10.1109/DMIAF.2016.7574925","url":null,"abstract":"The Cloud is increasingly being used to store and process big data, and conventional security mechanisms using encryption are either not sufficiently efficient or not suited to the task of protecting big data in the Cloud. In this paper we present an alternative approach which divides big data among multiple Cloud providers, and instead of protecting the data itself, protects the mapping of the various data elements to each provider using a trapdoor function. Our initial analysis indicates that this is an efficient and secure approach for securing big data.","PeriodicalId":404025,"journal":{"name":"2016 Digital Media Industry & Academic Forum (DMIAF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125924411","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}
{"title":"Direct encoding for sampled color image sensors with localized inverse","authors":"Chulhee Lee, S. Baek","doi":"10.1109/DMIAF.2016.7574930","DOIUrl":"https://doi.org/10.1109/DMIAF.2016.7574930","url":null,"abstract":"The sampled filter array sensor is widely used in image capturing devices. For example, the color filter array image sensor is used in digital still cameras, mobile phones, etc. Traditionally, sampled RGB images are first interpolated to produce full-resolution RGB images and then converted to the Yuv format. These Yuv images or videos are encoded. In this paper, we propose a directing encoding method, which first converts sampled RGB images to Yuv images without increasing the image size. We propose to use interpolation methods that have localized inverse filters. Experimental results along with some analyses will be presented.","PeriodicalId":404025,"journal":{"name":"2016 Digital Media Industry & Academic Forum (DMIAF)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129268019","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}
Yuliyan Velchev, S. Radeva, Strahil Sokolov, D. Radev
{"title":"Automated estimation of human emotion from EEG using statistical features and SVM","authors":"Yuliyan Velchev, S. Radeva, Strahil Sokolov, D. Radev","doi":"10.1109/DMIAF.2016.7574899","DOIUrl":"https://doi.org/10.1109/DMIAF.2016.7574899","url":null,"abstract":"This paper presents an approach for automated estimation of human emotions from electroencephalogram data. The used features are principally the Hjorth parameters calculated for theta, alpha, beta and gamma bands taken from certain channels. The classification stage is support vector machine. Since the human emotions are modelled as combinations from physiological elements such as arousal, valence, dominance, liking, etc., these quantities are the classifier's outputs. The best achieved correct classification performance is about 80%.","PeriodicalId":404025,"journal":{"name":"2016 Digital Media Industry & Academic Forum (DMIAF)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125976037","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}
Toinon Vigier, Lukáš Krasula, Aurélien Milliat, Matthieu Perreira Da Silva, P. Callet
{"title":"Performance and robustness of HDR objective quality metrics in the context of recent compression scenarios","authors":"Toinon Vigier, Lukáš Krasula, Aurélien Milliat, Matthieu Perreira Da Silva, P. Callet","doi":"10.1109/DMIAF.2016.7574903","DOIUrl":"https://doi.org/10.1109/DMIAF.2016.7574903","url":null,"abstract":"The new High Dynamic Range (HDR) technologies intend to increase the immersiveness and quality of experience of the observers thanks to much larger luminance and contrast characteristics. This increase of the amount of information requires the development of new sophisticated compression algorithms. Moreover, well-known objective quality metrics designed for Low Dynamic Range (LDR) systems may not be directly used for assessing HDR videos. To address this issue, several different ways have been proposed. However, their performance and robustness in the context of the most recent HDR compression software solutions need to be assessed and validated on various types of content. In this paper, four objective metrics are benchmarked from data obtained in a new subjective test conducted on various HDR video sequences.","PeriodicalId":404025,"journal":{"name":"2016 Digital Media Industry & Academic Forum (DMIAF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128976626","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}
Cong Zhang, Jiangchuan Liu, Fei Chen, Yong Cui, E. Ngai
{"title":"Dependency-aware caching for HTTP Adaptive Streaming","authors":"Cong Zhang, Jiangchuan Liu, Fei Chen, Yong Cui, E. Ngai","doi":"10.1109/DMIAF.2016.7574908","DOIUrl":"https://doi.org/10.1109/DMIAF.2016.7574908","url":null,"abstract":"There has been significant interest in the use of HTTP adaptive streaming for live or on-demand video over the Internet in recent years. To mitigate the streaming transmission delay and reduce the networking overhead, an effective and critical approach is to utilize cache servers between the origin servers and the heterogeneous clients. As the underlying protocol for web transactions, HTTP has great potentials to explore the resources within state-of-the-art CDNs for caching; yet distinct challenges arise in the HTTP adaptive streaming context. After examining a long-term and large-scale adaptive streaming dataset as well as statistical analysis, we demonstrate that the switching requests among the different qualities frequently emerge and constitute a significant portion in a per-day view. Consequently, they have substantially affected the performance of cache servers and Quality-of-Experience (QoE) of viewers. In this paper, we propose a novel cache model that captures the dependency among the segments in the cache server for adaptive HTTP streaming. Our work does not assume any specific selection algorithm on the client's side and hence can be easily incorporated into existing streaming cache system. Its centralized nature is also well accommodated by the latest DASH specification. The performance evaluation shows our dependency-aware strategy can significantly improved the cache hit-ratio and QoE of HTTP streaming as compared to previous methods.","PeriodicalId":404025,"journal":{"name":"2016 Digital Media Industry & Academic Forum (DMIAF)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132260717","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}
{"title":"Social-aware peer discovery and resource allocation for device-to-device communication","authors":"Zhiyuan Tan, Xi Li, Hong Ji, Ke Wang, Heli Zhang","doi":"10.1109/DMIAF.2016.7574907","DOIUrl":"https://doi.org/10.1109/DMIAF.2016.7574907","url":null,"abstract":"Device-to-device (D2D) communication has been regarded as a major technology to improve spectrum utilization and to offload the traffic from cellular base station. D2D peer discovery, as a critical procedure, attracts a lot of attentions. Furthermore, combination with the mobile social network (MSN) is an efficient solution to improve the establishment of D2D pairs. However, limited work has been considered about the D2D peer discovery based on MSN. In this paper, we propose an efficient D2D communication scheme for jointly considering D2D peer discovery and resource allocation. Firstly, D2D peer discovery and match mechanism is studied under a D2D communication scenario with MSN. Particularly, residual energy of nodes is taken into account from the concept of green communication. Then based on the matched results, a resource allocation problem is formulated where sub-carries and power resource are jointly allocated. Finally, simulation results are presented to verify effectiveness of our studies.","PeriodicalId":404025,"journal":{"name":"2016 Digital Media Industry & Academic Forum (DMIAF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130409376","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}