Novel Methods for Forensic Multimedia Data Analysis: Part II
Author:
Open Access
- 30 September 2020
- book chapter
- Published by IntechOpen
Abstract
We are proposing a new concept for new multimedia data processing techniques for varied multimedia sources. We address our work toward speech, video and images, handwriting and text documents. The methods and techniques will form a toolkit that can be used for different cases in a court of law in order to extract information from different multimedia sources. In addition to the data mentioned above, social media (e.g., Facebook and Twitter) provide multimedia data in new formats. Such data allow the investigator to identify and compare objects, events or persons based on data properties, including biometric features or more symbolic features that point to coincidences and anomalies. We continue our work of novel methods for forensic multimedia data analysis Part I by a description of related work and a proposal of the methods and techniques we are developing beyond the state of the art for handwriting, multimedia feature extraction, novelty detection, legal aspects and cloud computing. Then, we describe the tasks that should be solved by the system and the different multimedia data. We describe expected results of our proposed toolkit. Finally, we summarize the objective of our work.Keywords
This publication has 34 references indexed in Scilit:
- Scenario-based query processing for video-surveillance archivesEngineering Applications of Artificial Intelligence, 2010
- Handwritten word-spotting using hidden Markov models and universal vocabulariesPattern Recognition, 2009
- Text search for medieval manuscript imagesPattern Recognition, 2007
- Extraction and analysis of forensic document examiner features used for writer identificationPattern Recognition, 2007
- Word spotting for historical documentsInternational Journal on Document Analysis and Recognition (IJDAR), 2006
- The Shazam music recognition serviceCommunications of the ACM, 2006
- Word matching using single closed contours for indexing handwritten historical documentsInternational Journal on Document Analysis and Recognition (IJDAR), 2006
- Shape matching and object recognition using shape contextsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Estimating the Support of a High-Dimensional DistributionNeural Computation, 2001
- Online and off-line handwriting recognition: a comprehensive surveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000