#	Pagina
attuale pagina	/open-h2020/projects/200056/results.html

Report

Teaser, summary, work performed and final results

Periodic Reporting for period 1 - IDENTITY (Computer Vision Enabled Multimedia Forensics and People Identification)

Teaser

Summary

What is the problem/issue being addressed?
Forensics is mainly concerned with proving and investigating infringements, identifying perpetrators and describing modus operandi. Biometrics, on the other hand, is a relatively new science that aims at measuring and analysing a person\'s unique characteristics, both behavioural and physical. The potential of applying biometrics to forensics comes natural as several forensic questions rely on identifying, or verifying the identity, of people allegedly involved in crimes. Although these two scientific communities have operated in relative isolation over the past couple of decades, forensic biometrics have been successfully applied through the development automatic fingerprint identification systems (AFIS), and most recently, through the development of face recognition systems. The potential of forensics biometrics, however, can be extended to other biometric traits, such as iris and gait analysis.
This project aims at continuing supporting the development of the forensic biometric community. In the past five years, several improvements in the biometric community have resulted in more robust technologies for face, fingerprint, iris and gait recognition, which can now be applied to practical scenarios.
This project aims at consolidating the integration of multimedia forensics into the forensic science. Multimedia forensics is concerned with the development of scientific methods to extract, analyse and categorise digital evidence derived from multimedia sources, such as imaging devices. For example, developing technologies to identify, categorise and classify the source of images and video, as well as to authenticate and verify the integrity of their content. Since the enabling technologies in multimedia forensics are similar to those used for identification and verification purposes in biometric forensics, the integration of these areas is seamless. The proposed project will then support the integration of knowledge and expertise from the forensics, biometrics and multimedia forensics communities.

Why is it important for society?
Multimedia forensic and biometric techniques are useful in combating crime. For example multimedia forensic techniques can be used for source device identification, source device verification common source inference, content authentication and source-oriented image clustering. On the other hand, biometric techniques for identifying and recognising people find their use in access control border control, video surveillance, etc. From the scientific point of view, both sets of techniques are enabled by computer vision, image processing and machine learning. Therefore, experience gained from one domain is transferrable to the other and including the research agendas of both domain facilitate cross-fertilisation of ideas.

What are the overall objectives?
The main objective of IDENTITY is to enhance international and European collaborations in research, entrepreneurial development and innovation within the area of multimedia and biometric forensics. To this end, IDENTITY has the following specific objectives:
1. To promote knowledge transfer among research institutions and private companies about methodologies for identification within a forensic context. Two main lines of identification are considered, imaging device identification for multimedia forensics, and people identification, for biometric forensics.
2. To enhance research programs by incorporating experience of private companies and police investigators from real identification scenarios and forensic cases.
3. To disseminate knowledge and technologies internationally to ensure a wide impact and a continuing fostering of the multimedia forensics and biometric forensics communities.

Work performed

Impact on training and dissemination:
â€¢ Two summer schools listed below were organised by Massimo Tistarelli, with 10 scholarship made available to the Early Career Researchers of the IDENTITY Consortium.
- Int.l Summer school for advanced studies on biometrics: Biometrics, Forensic Science and the Quest for Identity (June 2016)
- Int.l Summer school for advanced studies on biometrics: Biometrics for Personalization and Forensic Identification (June 2017

â€¢ The consortium has organised a series of events listed below to deepen the impact on training and dissemination:
- October 2017: Jean-Luc Dugelay and Ling Wang contributed to the organisation of the International Joint Conference on Biometrics, USA.
- October 2017: Chang-Tsun Li, Andreas Uhl and Massimo Tistarelli organised the IJCB Special Session on Linking Biometrics with Forensic Science to disseminate the research outcomes.
- April 2017: 5th International Workshop on Biometrics and Forensics, held at The University of Warwick
- October 2016: Chang-Tsun Li, Massimo Tistarelli and Tieniu Tan organised the Biometrics and Multimedia Forensics Special Session on Biometrics and Multimedia Forensics for BTAS 2016.
- September 2016: Massimo Tistarelli organised the Panel Session on Relation/Implications of Forensic Biometrics and Multimedia Forensics for ICB 2016 in Sweden.

Impact on fight against crime:
â€¢ Chang-Tsun Li was invited to discuss his experience in developing a source-oriented image clustering method for integration into INTERPOLâ€™s International Child Sexual Exploitation Image Database at the 34th Meeting of the INTERPOL Specialists Group on Crimes against Children, Lyon, France, 14-18 November, 2016. The meeting was attended by more than 200 delegates from the law enforcement community around the world.
â€¢ Chang-Tsun Li acted as Expert Witness in June 2016 to analyse a set of voyeuristic video sets for Guildford Crown Court (UK). By using his multimedia forensics expertise he proved the defendant guilty, which the defendant admitted and was given a 10 monthsâ€™ imprisonment sentence.

Final results

Since the start of the project, in the multimedia forensics area, the consortium has developed a number of new methods for attenuating various sources of distortions to sensor pattern noise (a form of device fingerprint). This allows the quality of the device fingerprint to be enhanced so as to aide forensic investigations. We have also developed a new method for reducing the dimensionality of the sensor pattern noise (i.e. a more compact representation of the sensor pattern noise) so that forensic investigation can be performed in a more efficient manner. The consortium also developed a blind image clustering method using sensor pattern noise as feature, which is able to classify images into group so that each group contains images taken with the same camera. The significance of this clustering method is that the method allows investigators to establish the relationship of the images acquired at different times at different locations, hence enabling the investigators to narrow down the investigation.
In the biometrics domain, the main contribution has been the use of deep learning in people re-identification, which can be used for video surveillance. Our method is capable of learning the feature adaptively without the user providing specific features to guide the analysis and re-identification. Iris recognition is another sub-area the consortium has made significant improvement in terms of accuracy and efficiency (i.e. low computational complexity).