ORCID Profile
0000-0003-4735-6138
Current Organisation
Deakin University
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: IET
Date: 2011
DOI: 10.1049/IC.2011.0134
Publisher: IEEE
Date: 12-2014
Publisher: Springer Science and Business Media LLC
Date: 22-05-2014
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: IEEE
Date: 12-2017
DOI: 10.1109/ISM.2017.67
Publisher: CSIRO Publishing
Date: 2019
DOI: 10.1071/AN17346
Abstract: Milk production responses were measured in grazing cows offered mixed rations with or without canola meal. Experiments were conducted in spring (Experiment 1 early lactation) and autumn (Experiment 2 late lactation). The experiments used 140 (Experiment 1) or 96 (Experiment 2) Holstein-Friesian multiparous dairy cows that had calved in late winter/early spring. Each experiment lasted 28 days including a 14-day adjustment period and a 14-day measurement period during which intake and milk production was measured. In each experiment, there were two dietary treatments: PMR: cows grazed a restricted pasture allowance (10–15 kg DM/cow per day, measured to ground level) supplemented with a PMR comprising wheat grain (60%, DM basis), lucerne hay (21%) and maize grain (19%) and PMR+C: cows were fed the same as the PMR cows, but some wheat grain in the PMR was replaced with solvent-extracted canola meal so that it comprised wheat grain (39%, DM basis), lucerne hay (21%), maize grain (19%) and canola meal (21%). The two treatments were randomly allocated to half the cows in each experiment. Cows were then further allocated into 10 groups of 7 cows (Experiment 1) or 8 groups of 6 cows (Experiment 2). Two groups of cows were assigned to receive a different amount of each ration: 8, 10, 12, 14 or 16 kg DM total supplement/cow per day for Experiment 1 and 6, 8, 10 or 12 kg DM total supplement/cow per day for Experiment 2. In Experiment 1, yields of energy corrected milk (ECM), milk fat, and milk protein were greater for PMR+C cows than PMR cows when 12 kg/cow per day of supplement or more was offered. Milk protein concentration was greater in PMR+C cows than PMR cows but only when 16 kg DM supplement/cow per day was offered. These changes in milk yield and composition were associated with increases in the intakes of pasture, supplement and total DM intake in the PMR+C cows compared with the PMR cows. In Experiment 2 there were no differences in milk yield or composition between PMR and PMR+C cows at any amount of supplement offered, nor were there any differences in intakes of pasture, supplement or total DM intake. It is concluded that replacing some of the wheat in a well-formulated PMR with canola meal can stimulate DMI and increase per-cow production of ECM when high amounts of supplement are fed in early lactation, but not late lactation.
Publisher: IEEE
Date: 06-2009
DOI: 10.1109/BIBE.2009.8
Publisher: IEEE
Date: 05-2012
Publisher: ACM
Date: 09-04-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2009
Publisher: Elsevier BV
Date: 12-2010
Publisher: IGI Global
Date: 07-2012
Abstract: Frame duplication is a common way of digital video forgeries. State-of-the-art approaches of duplication detection usually suffer from heavy computational load. In this paper, the authors propose a new algorithm to detect duplicated frames based on video sub-sequence fingerprints. The fingerprints employed are extracted from the DCT coefficients of the temporally informative representative images (TIRIs) of the sub-sequences. Compared with other similar algorithms, this study focuses on improving fingerprints representing video sub-sequences and introducing a simple metric for the matching of video sub-sequences. Experimental results show that the proposed algorithm overall outperforms three related duplication forgery detection algorithms in terms of computational efficiency, detection accuracy and robustness against common video operations like compression and brightness change.
Publisher: SPIE-Intl Soc Optical Eng
Date: 12-2006
DOI: 10.1117/1.2402932
Publisher: IGI Global
Date: 2008
DOI: 10.4018/978-1-59904-953-3.CH110
Abstract: This chapter is intended to disseminate the concept of digital signature-based image authentication. Capabilities of digital signature-based image authentication and its superiority over watermarking-based approaches are described first. Subsequently, general models of this technique — strict authentication and non-strict authentication are introduced. Specific schemes of the two general models are also reviewed and compared. Finally, based on the review, design issues faced by the researchers and developers are outlined.
Publisher: IGI Global
Date: 2009
DOI: 10.4018/978-1-60566-174-2.CH014
Abstract: As distributed mammogram databases at hospitals and breast screening centers are connected together through PACS, a mammogram retrieval system is needed to help medical professionals locate the mammograms they want to aid in medical diagnosis. This chapter presents a complete content-based mammogram retrieval system, seeking images that are pathologically similar to a given ex le. In the mammogram retrieval system, the pathological characteristics that have been defined in Breast Imaging Reporting and Data System (BI-RADSTM) are used as criteria to measure the similarity of the mammograms. A detailed description of those mammographic features is provided in this chapter. Since the user’s subjective perception should be taken into account in the image retrieval task, a relevance feedback function is also developed to learn in idual users’ knowledge to improve the system performance.
Publisher: IGI Global
Date: 2006
DOI: 10.4018/978-1-59140-563-4.CH012
Abstract: Although the development of multimedia processing techniques has facilitated the enrichment of information content, and the never-ending expansion of interconnected networks has constructed a solid infrastructure for information exchanges, meanwhile, the infrastructure and techniques have also smoothed the way for copyright piracy in virtual communities. As a result, the demand for intellectual property protection becomes apparent and exigent. In response to this challenge, digital watermarking has been proposed to serve this purpose. The idea of digital watermarking is to embed a small amount of secret information—the watermark—into the host digital productions, such as image and audio, so that it can be extracted later for the purposes of copyright assertion, authentication and content integrity verification, and so forth. Unlike traditional watermarks printed on paper, which are visible to human eyes, digital watermarks are usually invisible and can only be detected with the aid of a specially designed detector. One characteristic distinguishing digital watermarking from cryptography, which separates the digital signature from the raw data/content, is that digital watermarking embeds the signature in the content to be protected. The superiority of this characteristic is that while cryptography provides no protection after the content is decrypted, digital watermarking provides “intimate” protection, because the digital signature/secret information has become an inseparable constituent part of the content itself after embedding. Because of the very characteristic, digital watermarking requires no secret channel for communicating the digital signature that cryptography does. So in the last decade, digital watermarking has attracted numerous attention from researchers and is regarded as a promising technique in the field of information security. Various types of watermarking schemes have been developed for different applications. According to their natures, digital watermarking schemes could be classified into three categories: fragile watermarking, semi-fragile watermarking and robust watermarking. The schemes of the first two categories are developed for the purposes of multimedia authentication and content integrity verification, in which we expect the embedded watermark to be destroyed when attacks are mounted on its host media. More emphases of these schemes are placed on the capability of detecting and localizing forgeries and impersonations. The main difference between the two is that semi-fragile watermarking is tolerant to non-malicious operations, such as lossy compression within a certain compression ratio, while fragile watermarking is intolerant to any manipulations. Robust watermarking, on the other hand, is intended for the applications of copyright protection, wherein the watermarks should survive attacks aiming at weakening or erasing them provided the quality of the attacked content is still worth protecting. Therefore, the emphasis of robust watermarking schemes is placed on their survivability against attacks. This article is intended to focus on robust watermarking schemes for the application of copyright protection. See Li and Yang (2003) and Lin and Chang (2001) for more details about fragile and semi-fragile schemes.
Publisher: Springer Singapore
Date: 2019
Publisher: IGI Global
Date: 2009
DOI: 10.4018/978-1-60566-174-2.CH010
Abstract: An image is a symbolic representation people interpret an image and associate semantics with it based on their subjective perceptions, which involves the user’s knowledge, cultural background, personal feelings and so on. Content-based image retrieval (CBIR) systems must be able to interact with users and discover the current user’s information needs. An interactive search paradigm that has been developed for image retrieval is machine learning with a user-in-the-loop, guided by relevance feedback, which refers to the notion of relevance of the in idual image based on the current user’s subjective judgment. Relevance feedback serves as an information carrier to convey the user’s information needs / preferences to the retrieval system. This chapter not only provides the fundamentals of CBIR systems and relevance feedback for understanding and incorporating relevance feedback into CBIR systems, but also discusses several approaches to analyzing and learning relevance feedback.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2015
Publisher: IEEE
Date: 11-2013
Publisher: IEEE
Date: 11-2019
Publisher: Institution of Engineering and Technology (IET)
Date: 2004
Publisher: IEEE
Date: 07-2011
Publisher: Springer International Publishing
Date: 11-11-2018
Publisher: IEEE
Date: 12-2012
Publisher: IEEE
Date: 05-2010
Publisher: IEEE
Date: 08-2012
Publisher: IEEE
Date: 04-2015
Publisher: IEEE
Date: 07-2012
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Institution of Engineering and Technology (IET)
Date: 2005
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: IEEE
Date: 11-2016
Publisher: IGI Global
Date: 2006
DOI: 10.4018/978-1-59140-684-6.CH009
Abstract: Content-based image retrieval (CBIR) makes use of image features, such as color and texture, to index images with minimal human intervention. Content-based image retrieval can be used to locate medical images in large databases. This chapter introduces a content-based approach to medical image retrieval. Fundamentals of the key components of content-based image retrieval systems are introduced first to give an overview of this area. A case study, which describes the methodology of a CBIR system for retrieving digital mammogram database, is then presented. This chapter is intended to disseminate the knowledge of the CBIR approach to the applications of medical image management and to attract greater interest from various research communities to rapidly advance research in this field.
Publisher: IEEE
Date: 12-2010
Publisher: ACM
Date: 06-09-2012
Publisher: IGI Global
Date: 2008
DOI: 10.4018/978-1-59904-777-5.CH014
Abstract: Content-based image retrieval (CBIR) makes use of image features, such as color and texture, to index images with minimal human intervention. Content-based image retrieval can be used to locate medical images in large databases. This chapter introduces a content-based approach to medical image retrieval. Fundamentals of the key components of content-based image retrieval systems are introduced first to give an overview of this area. A case study, which describes the methodology of a CBIR system for retrieving digital mammogram database, is then presented. This chapter is intended to disseminate the knowledge of the CBIR approach to the applications of medical image management and to attract greater interest from various research communities to rapidly advance research in this field.
Publisher: IEEE
Date: 09-2015
Publisher: IEEE
Date: 04-2017
Publisher: IEEE
Date: 08-2007
DOI: 10.1109/IAS.2007.62
Publisher: IGI Global
Date: 2006
DOI: 10.4018/978-1-59140-563-4.CH001
Abstract: Pervasive services of virtual communities and digital governments are achievable only if trust, privacy and security can be secured and strengthened. To meet these requirements, mechanisms, which provide secure management of information and facilities without compromising privacy and civil rights, have to be devised. The success of such mechanisms relies on effective identity authentication. While traditional security measures such as PINs and passwords may be forgotten, stolen or cracked, biometrics provides authentication mechanisms based on unique human physiological and behavioral characteristics that can be used to identify an in idual or authenticate the claimed identity of an in idual, but cannot be easily duplicated or forged. Typical characteristics include but are not limited to fingerprint, face, iris, hand geometry, palm, voice pattern, signature, keystroke dynamics and so forth. Moreover, in the light of homeland security, biometrics has become a powerful measure in the government’s fight against identity fraud, illegal immigration, illegal workers and terrorism. Biometrics is also useful in preventing abuses of public health services and other government entitlement.
Publisher: IEEE
Date: 04-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2016
Publisher: Science Alert
Date: 05-2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: IEEE
Date: 2004
Publisher: Elsevier BV
Date: 09-2018
Publisher: Elsevier BV
Date: 02-2018
Publisher: IEEE
Date: 11-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: SPIE-Intl Soc Optical Eng
Date: 07-2008
DOI: 10.1117/1.2952843
Publisher: Springer Science and Business Media LLC
Date: 18-06-2008
Abstract: Tight clustering arose recently from a desire to obtain tighter and potentially more informative clusters in gene expression studies. Scattered genes with relatively loose correlations should be excluded from the clusters. However, in the literature there is little work dedicated to this area of research. On the other hand, there has been extensive use of maximum likelihood techniques for model parameter estimation. By contrast, the minimum distance estimator has been largely ignored. In this paper we show the inherent robustness of the minimum distance estimator that makes it a powerful tool for parameter estimation in model-based time-course clustering. To apply minimum distance estimation, a partial mixture model that can naturally incorporate replicate information and allow scattered genes is formulated. We provide experimental results of simulated data fitting, where the minimum distance estimator demonstrates superior performance to the maximum likelihood estimator. Both biological and statistical validations are conducted on a simulated dataset and two real gene expression datasets. Our proposed partial regression clustering algorithm scores top in Gene Ontology driven evaluation, in comparison with four other popular clustering algorithms. For the first time partial mixture model is successfully extended to time-course data analysis. The robustness of our partial regression clustering algorithm proves the suitability of the combination of both partial mixture model and minimum distance estimator in this field. We show that tight clustering not only is capable to generate more profound understanding of the dataset under study well in accordance to established biological knowledge, but also presents interesting new hypotheses during interpretation of clustering results. In particular, we provide biological evidences that scattered genes can be relevant and are interesting subjects for study, in contrast to prevailing opinion.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
Publisher: IEEE
Date: 08-2007
DOI: 10.1109/IAS.2007.46
Publisher: SPIE
Date: 19-02-2014
DOI: 10.1117/12.2038651
Publisher: IEEE
Date: 04-2013
Publisher: IET
Date: 2009
DOI: 10.1049/IC.2009.0232
Publisher: IEEE
Date: 05-2019
Publisher: IGI Global
Date: 2009
Publisher: IGI Global
Date: 2008
DOI: 10.4018/978-1-59904-953-3.CH054
Abstract: As the interconnected networks for instant transaction prevail and the power of digital multimedia processing tools for perfect duplication and manipulation increases, forgery and impersonation become major concerns of the information era. This chapter is intended to disseminate the concept of digital watermarking for multimedia authentication. Issues and challenges, such as security, resolution of t er localization, and embedding distortion, of this technical area are explained first. Three main categories of watermarking approaches, namely fragile, semi-fragile, and reversible schemes, to the issues and challenges are then presented. Merits and limitations of specific schemes of each category are also reviewed and compared.
Publisher: IEEE
Date: 04-2017
Publisher: SPIE
Date: 15-04-2005
DOI: 10.1117/12.594929
Publisher: Springer Berlin Heidelberg
Date: 2013
Publisher: IEEE
Date: 04-2018
Publisher: SPIE
Date: 19-02-2014
DOI: 10.1117/12.2038644
Publisher: IEEE
Date: 04-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2017
Publisher: IEEE
Date: 10-2013
DOI: 10.1109/SMC.2013.209
Publisher: Public Library of Science (PLoS)
Date: 06-04-2011
Publisher: Elsevier BV
Date: 02-2018
Publisher: SAGE Publications
Date: 16-11-2018
Abstract: Concussion in sport is a topic of growing interest in Australia and worldwide. To date, relatively few studies have examined the true incidence of concussion in cricket. Concussion in cricket is more common than current literature suggests. Descriptive epidemiology study. Level 4. This is a prospective registry and subsequent analysis of head impacts and concussions in elite-level male and female cricketers in Australia over 2 seasons (2015-2016 and 2016-2017). A total of 172 male and 106 female domestic and international players in 2015-2016 and 179 males and 98 females in 2016-2017 were included. There were 92 head impacts (29 concussions) in men’s matches and 15 head impacts (8 concussions) in women’s matches. Match incidence rates per 1000 player days were 7.2 head impacts (2.3 concussions) in elite male cricket and 3.7 head impacts (2.0 concussions) in elite female cricket. This equates to a head impact every 2000 balls and concussion every 9000 balls in male domestic cricket. Concussion rates per 1000 player-match hours were 0.4 for elite males and 0.5 for elite females 53% of head impacts in females were diagnosed as concussions compared with 32% in males, and 83% of concussions resulted in missing no more than 1 game. The rate of concussion in cricket is higher than previously appreciated however, the majority of patients recovered quickly, and players generally did not miss much playing time as a result. The institution of concussion policies after head impact, including player substitution, appears to have had an effect on increasing reporting of symptoms, resulting in an increase in diagnosis of concussion. Concussion in cricket is not as infrequent as previously assumed. Ongoing review of the rules and regulations is required to ensure that protection of player welfare lies in parallel with other sporting codes.
Publisher: IEEE
Date: 06-2009
DOI: 10.1109/BIBE.2009.28
Publisher: IEEE
Date: 09-2011
Publisher: Institution of Engineering and Technology (IET)
Date: 07-2018
Publisher: IEEE
Date: 10-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2017
Publisher: IEEE
Date: 07-2013
Publisher: Institution of Engineering and Technology
Date: 12-04-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2012
Publisher: Springer Science and Business Media LLC
Date: 30-01-2010
Abstract: Time-course microarray experiments can produce useful data which can help in understanding the underlying dynamics of the system. Clustering is an important stage in microarray data analysis where the data is grouped together according to certain characteristics. The majority of clustering techniques are based on distance or visual similarity measures which may not be suitable for clustering of temporal microarray data where the sequential nature of time is important. We present a Granger causality based technique to cluster temporal microarray gene expression data, which measures the interdependence between two time-series by statistically testing if one time-series can be used for forecasting the other time-series or not. A gene-association matrix is constructed by testing temporal relationships between pairs of genes using the Granger causality test. The association matrix is further analyzed using a graph-theoretic technique to detect highly connected components representing interesting biological modules. We test our approach on synthesized datasets and real biological datasets obtained for Arabidopsis thaliana. We show the effectiveness of our approach by analyzing the results using the existing biological literature. We also report interesting structural properties of the association network commonly desired in any biological system. Our experiments on synthesized and real microarray datasets show that our approach produces encouraging results. The method is simple in implementation and is statistically traceable at each step. The method can produce sets of functionally related genes which can be further used for reverse-engineering of gene circuits.
Publisher: Institution of Engineering and Technology (IET)
Date: 11-2012
Publisher: IEEE
Date: 11-2006
DOI: 10.1109/AVSS.2006.31
Publisher: IEEE
Date: 11-2009
Publisher: IEEE
Date: 02-2007
Publisher: IEEE
Date: 2009
Publisher: IGI Global
Date: 10-2009
Abstract: In this work we propose a Repetitive Index Modulation (RIM) based digital watermarking scheme for authentication and integrity verification of medical images. Exploiting the fact that many types of medical images have significant background areas and medically meaningful Regions Of Interest (ROI), which represent the actual contents of the images, the scheme uses the contents of the ROI to create a content-dependent watermark and embeds the watermark in the background areas. Therefore when any pixel of the ROI is attacked, the watermark embedded in the background areas will be different from the watermark calculated according to the attacked contents, thus raising alarm that the image in question is inauthentic. Because the creation of the watermark is content-dependent and the watermark is only embedded in the background areas, the proposed scheme can actually protect the content/ROI without distorting it.
Publisher: Institution of Engineering and Technology (IET)
Date: 08-05-2018
Publisher: IEEE
Date: 10-2014
Publisher: Elsevier BV
Date: 03-2001
Publisher: Institution of Engineering and Technology (IET)
Date: 06-2014
Publisher: IEEE
Date: 11-2017
Publisher: ACM
Date: 29-10-2010
Publisher: IEEE Comput. Soc
Date: 1999
Publisher: IEEE
Date: 12-2006
DOI: 10.1109/ISM.2006.101
Publisher: IEEE
Date: 09-2016
Publisher: Springer International Publishing
Date: 2016
Publisher: IEEE
Date: 09-2015
Publisher: IEEE
Date: 12-2012
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2017
Publisher: IEEE
Date: 12-2018
Publisher: IGI Global
Date: 10-2011
Abstract: Statistical image features play an important role in forensic identification. Current source camera identification schemes select image features mainly based on classification accuracy and computational efficiency. For forensic investigation purposes however, these selection criteria are not enough. Consider most real-world photos may have undergone common image processing due to various reasons, source camera classifiers must have the capability to deal with those processed photos. In this work, the authors first build a s le camera classifier using a combination of popular image features, and then reveal its deficiency. Based on the experiments, suggestions for the design of robust camera classifiers are given.
Publisher: IEEE
Date: 2005
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2023
Publisher: IEEE
Date: 03-2017
Publisher: IGI Global
Date: 2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: Springer International Publishing
Date: 2017
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: IEEE
Date: 04-2013
Publisher: IEEE
Date: 09-2014
Publisher: SPIE-Intl Soc Optical Eng
Date: 2007
DOI: 10.1117/1.2712445
Publisher: American Chemical Society (ACS)
Date: 18-01-2008
DOI: 10.1021/BI7020298
Abstract: Lignin degradation by fungal peroxidases is initiated by one-electron transfer to an exposed tryptophan radical, a reaction mediated by veratryl alcohol (VA) in lignin peroxidase (LiP). Versatile peroxidase (VP) differs not only in its oxidation of Mn2+ at a second catalytic site but also in its ability to directly oxidize different aromatic compounds. The catalytic tryptophan environment was compared in LiP and VP crystal structures, and six residues near VP Trp164 were modified by site-directed mutagenesis. Oxidation of Mn2+ was practically unaffected. However, several mutations modified the oxidation kinetics of the high-redox-potential substrates VA and Reactive Black 5 (RB5), demonstrating that other residues contribute to substrate oxidation by the Trp164 radical. Introducing acidic residues at the tryptophan environment did not increase the efficiency of VP oxidizing VA. On the contrary, all variants harboring the R257D mutation lost their activity on RB5. Interestingly, this activity was restored when VA was added as a mediator, revealing the LiP-type behavior of this variant. Moreover, combination of the A260F and R257A mutations strongly increased (20-50-fold) the apparent second-order rate constants for reduction of VP compounds I and II by VA to values similar to those found in LiP. Dissociation of the enzyme-product complex seemed to be the limiting step in the turnover of this improved variant. Nonexposed residues in the vicinity of Trp164 can also affect VP activity, as found with the M247F mutation. This was a direct effect since no modification of the surrounding residues was found in the crystal structure of this variant.
Publisher: IEEE
Date: 10-2007
Publisher: IEEE
Date: 02-2007
Publisher: IGI Global
Date: 2014
Abstract: Human face/gait-based gender recognition has been intensively studied in the previous literatures, yet most of them are based on the same database. Although nearly perfect gender recognition rates can be achieved in the same face/gait dataset, they assume a closed-world and neglect the problems caused by dataset bias. Real-world human gender recognition system should be dataset-independent, i.e., it can be trained on one face/gait dataset and tested on another. In this paper, the authors test several popular face/gait-based gender recognition algorithms in a cross-dataset manner. The recognition rates decrease significantly and some of them are only slightly better than random guess. These observations suggest that the generalization power of conventional algorithms is less satisfied, and highlight the need for further research on face/gait-based gender recognition for real-world applications.
Publisher: Springer Singapore
Date: 2019
Publisher: Elsevier BV
Date: 07-2019
Publisher: IEEE
Date: 08-2008
Publisher: IEEE
Date: 07-2014
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: MDPI AG
Date: 24-08-2023
DOI: 10.3390/S23177385
Abstract: With the increasing prevalence of digital multimedia content, the need for reliable and accurate source camera identification has become crucial in applications such as digital forensics. While effective techniques exist for identifying the source camera of images, video-based source identification presents unique challenges due to disruptive effects introduced during video processing, such as compression artifacts and pixel misalignment caused by techniques like video coding and stabilization. These effects render existing approaches, which rely on high-frequency camera fingerprints like Photo Response Non-Uniformity (PRNU), inadequate for video-based identification. To address this challenge, we propose a novel approach that builds upon the image-based source identification technique. Leveraging a global stochastic fingerprint residing in the low- and mid-frequency bands, we exploit its resilience to disruptive effects in the high-frequency bands, envisioning its potential for video-based source identification. Through comprehensive evaluation on recent smartphones dataset, we establish new benchmarks for source camera model and in idual device identification, surpassing state-of-the-art techniques. While conventional image-based methods struggle in video contexts, our approach unifies image and video source identification through a single framework powered by the novel non-PRNU device-specific fingerprint. This contribution expands the existing body of knowledge in the field of multimedia forensics.
Publisher: IEEE
Date: 07-2010
Publisher: IEEE
Date: 04-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: IEEE
Date: 07-2016
Publisher: Springer Science and Business Media LLC
Date: 16-10-2017
Publisher: Springer Science and Business Media LLC
Date: 12-10-2010
DOI: 10.1155/2010/212517
Publisher: Journal of Integrative Bioinformatics
Date: 2008
Publisher: IEEE
Date: 09-2015
Publisher: Springer Science and Business Media LLC
Date: 19-08-2016
Publisher: SPIE
Date: 19-11-2003
DOI: 10.1117/12.510574
Publisher: Elsevier BV
Date: 03-2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Springer Science and Business Media LLC
Date: 07-10-2010
DOI: 10.1155/2010/167942
Publisher: IEEE
Date: 07-2012
Publisher: IEEE
Date: 07-2012
Publisher: IET
Date: 2009
DOI: 10.1049/IC.2009.0274
Publisher: IEEE
Date: 07-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2014
Publisher: IEEE
Date: 11-2016
Publisher: IEEE
Date: 09-2013
Publisher: IEEE
Date: 03-2008
Publisher: Elsevier BV
Date: 10-2003
Publisher: IEEE
Date: 05-2010
Publisher: IEEE
Date: 09-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2003
Publisher: IEEE
Date: 06-2013
Publisher: IEEE
Date: 05-2002
Publisher: Springer Science and Business Media LLC
Date: 14-11-2017
Publisher: IEEE
Date: 11-2006
Publisher: IEEE
Date: 03-2014
Publisher: IGI Global
Date: 2005
DOI: 10.4018/978-1-59140-518-4.CH002
Abstract: As the interconnected networks for instant transaction prevail and the power of digital multimedia processing tools for perfect duplication and manipulation increases, forgery and impersonation become major concerns of the information era. This chapter is intended to disseminate the concept of digital watermarking for multimedia authentication. Issues and challenges, such as security, resolution of t er localization, and embedding distortion, of this technical area are explained first. Three main categories of watermarking approaches, namely fragile, semi-fragile, and reversible schemes, to the issues and challenges are then presented. Merits and limitations of specific schemes of each category are also reviewed and compared.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
Publisher: Springer Berlin Heidelberg
Date: 2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Springer Singapore
Date: 2019
Publisher: Springer International Publishing
Date: 2020
Publisher: Springer International Publishing
Date: 2020
Publisher: SPIE-Intl Soc Optical Eng
Date: 04-2003
DOI: 10.1117/1.1557156
Publisher: Springer International Publishing
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Wiley
Date: 06-07-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: IEEE
Date: 03-2014
Publisher: SPIE
Date: 06-2012
DOI: 10.1117/12.922492
Publisher: IEEE
Date: 11-2006
Publisher: IEEE
Date: 09-2012
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: IEEE
Date: 11-2015
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: Oxford University Press (OUP)
Date: 20-08-2008
DOI: 10.1093/BIOINFORMATICS/BTN375
Abstract: Motivation: There is a growing interest in extracting statistical patterns from gene expression time-series data, in which a key challenge is the development of stable and accurate probabilistic models. Currently popular models, however, would be computationally prohibitive unless some independence assumptions are made to describe large-scale data. We propose an unsupervised conditional random fields (CRF) model to overcome this problem by progressively infusing information into the labelling process through a small variable voting pool. Results: An unsupervised CRF model is proposed for efficient analysis of gene expression time series and is successfully applied to gene class discovery and class prediction. The proposed model treats each time series as a random field and assigns an optimal cluster label to each time series, so as to partition the time series into clusters without a priori knowledge about the number of clusters and the initial centroids. Another advantage of the proposed method is the relaxation of independence assumptions. Contact: ctli@dcs.warwick.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online.
Publisher: IEEE
Date: 03-2008
Publisher: IEEE
Date: 06-2013
Location: Taiwan, Province of China
Location: United Kingdom of Great Britain and Northern Ireland
Start Date: 2011
End Date: 2012
Funder: Technology Strategy Board
View Funded ActivityStart Date: 2010
End Date: 2014
Funder: European Commission
View Funded ActivityStart Date: 2018
End Date: 2018
Funder: Australian Department of Education and Training
View Funded ActivityStart Date: 2016
End Date: 2019
Funder: European Commission
View Funded Activity