2. Multimedia processing

The proliferation of user-generated content in the Web 2.0 era and the convergence of media delivery channels (Web, TV, mobile) shape the current multimedia area posing new challenges to the research community. Today’s devices are equipped with advanced functionalities and capabilities providing users unlimited access to a wealth of shared content. This content incorporates a rich set of media combinations encompassing text, graphics, animation, sound, sketches, speech, image and video. Multimedia collections need to be organized and analyzed in a structured manner in order to be valuable assets to enterprises, governmental services, community-based services and personal archives. Special concern should be given to representational issues of modeling and multimedia analysis and indexing processes.

Multimedia technology today allows the user to manipulate or interact with content in ways not possible in the past. The combination of PCs, mobile devices and networks allows the individual to create, edit, transmit, share, aggregate, personalize and interact with multimedia content in increasingly flexible ways across different platforms.

The group focuses on the development of methods and tools for content-based analysis and organization of multimedia collections. In particular, the research team currently focuses on the following topics:

• Handwriting recognition with application on mathematical expressions
• Document image analysis and indexing of historical manuscripts
• Scene text recognition and signs identification in video sequences
• Music Information Retrieval with emphasis in music similarity, searching and indexing of music
• Fusion techniques of visual and audio features for speaker identification in broadcast videos

Two topics in the area of that are of particular interest to the group and in which it needs to expand its current competencies are:

• Handwriting recognition and document image analysis, where the focus is on automatically analysing, processing, indexing and reusing the now-digitized handwritten information and/or textual information in video sequences.
• Music transcription technology. Despite the fact that the research team is developing efficient and robust algorithms to some of the subtasks involved in music transcription , there is a need to emphasize on the unexplored ones. At the same time, the integration of these subtasks to a single Transcription System requires advanced knowledge and experience in music systems integration. The focus is on converting any type of acoustic signal (sound or music) to a musical notation (score), similar to that of “written” music.

Related news