The 21st century society is universally recognized as the information and communication society. Information is continuously generated, acquired, and shared. A large part of this information is stored within multimedia documents generated in a number of different scenarios. It must be also considered that the availability of low-cost, high-capacity storage devices makes easy to quickly accumulate thousands of multimedia files.
Thus, the efficient management of large amounts of multimedia files is indeed a challenging task. In addition, it is common knowledge that digital assets are extremely volatile, in the sense that digital documents can be easily edited, intentionally or unintentionally, so that their content can be modified and the conveyed information can change its meaning. It is incontrovertibly true that digital documents are natively more prone than others to modifications and tampering: thus, in order to make this information valuable, it is fundamental to verify the integrity of the document for assuring the authenticity of the associated information. Governments, national and international associations are aware of the fact that the phenomena may also have legal, ethical, social, and cultural implications.
The MAVEN Project addresses these issues by using some of the latest technologies, powering integrity and authenticity verification tools with multimedia analysis algorithms that search for specific contents. In particular, the MAVEN capabilities range from face detection and recognition to image source verification. All the different modules are integrated within the same framework for application development. The following table describes the tools developed in the project.
|Tool for linking a digital photo to its corresponding camera device, in order to identify image origin.|
|Tool for verifying if a digital image suffered some local/global editing or manipulation (with original image available/not available).|
|Tool for assessing if a digital video suffered double encoding and insertion/ removal of frames.|
|Text Localization and Extraction||Tool for detection and recognition of text within unconstrained scene imagery.|
|Tool for the spotting of (previously known) keywords in audio tracks.|
|Face Detection and Recognition||Tool for the automatic detection and recognition of faces in image and video galleries.|
|Object and Scene
|Tool for detection of a set of company logos and categorization of scenes.|