About

Welcome to IAPR-TC6, a Technical Committee on Computational Forensics under the auspices of the International Association for Pattern Recognition (IAPR).

 

Computational Forensics (CF) is an emerging research domain. It concerns the investigation of forensic problems using computational methods. The primary goal is the discovery and the advancement of forensic knowledge. CF involves modeling, computer simulation, computer-based analysis and recognition in studying and solving forensic problems.

 

This group aims to further promote research, development and education in CF, and to provide a platform for cooperation and exchange of researchers, practitioners and teachers from the various disciplines of computational and forensic sciences.

 
Aim & Scope

The group promotes exchange and research in the field of Computational Forensics, mainly through the provision of:

  • International forum, the IWCF workshops, to peer-review and exchange research results
  • Performance evaluation, benchmarking and standardization of algorithms and computational procedures
  • Resources in forms of data sets, software tools, and specifications e.g. data formats and system interfaces 
  • Education and training to prepare current and future researchers and practitioners
  • Sources of information on events, related activities and financing opportunities

Forensic methods are widespread in the scientific disciplines: biology, chemistry, physics and medicine. One can categorize them into:

  • Classical forensic identification sciences based on individualization (to identify a finger, a writer, a weapon, a shoe that left the mark)
  • Practical-oriented disciplines based on classification and quantization (chemical, biological, medical, or physical methods) like forensic toxicology
 

Computational methods for application in the forensic sciences are studied under three perspectives:

  • Providing tools to support the forensic examiner in his / her daily casework
  • Establishing the scientific basis for a forensic discipline
  • Representing human expert knowledge and for implementing recognition and reasoning abilities in machines

Algorithms and methods from several areas of pattern recognition and machine intelligence are involved:

  • Signal processing / Image processing
  • Computer vision 
  • Computer graphics
  • Pattern recognition
  • Data mining
  • Robotics
  • Machine learning
  • Statistical Methods
Forensic sciences pose exceptional challenges for current pattern-recognition approaches
  • Tiny pieces of evidence that are hidden in a chaotic environment, crime scene or scene of accident
  • Study of specific properties (abnormalities)
  • Demand of a (somehow) sufficient quality of trace evidence found
  • Never identical traces, the limit/lack of appropriate reference samples
  • Partial knowledge, required approximation
  • Decision making under uncertainties & conjectures