Writer Identification Using Inexpensive Signal Processing Techniques

Abstract

We propose to use novel and classical audio and text signal-processing and otherwise techniques for "inexpensive" fast writer identification tasks of scanned hand-written documents "visually". The "inexpensive" refers to the efficiency of the identification process in terms of CPU cycles while preserving decent accuracy for preliminary identification. This is a comparative study of multiple algorithm combinations in a pattern recognition pipeline implemented in Java around an open-source Modular Audio Recognition Framework (MARF) that can do a lot more beyond audio. We present our preliminary experimental findings in such an identification task. We simulate "visual" identification by "looking" at the hand-written document as a whole rather than trying to extract fine-grained features out of it prior classification.

9 pages; 1 figure; presented at CISSE'09 at http://conference.cisse2009.org/proceedings.aspx ; includes the the application source code; based on MARF described in arXiv:0905.1235

References in corpus (3)

• The Modular Audio Recognition Framework (MARF) and its Applications: Scientific and Software Engineering Notes
• Managing Distributed MARF with SNMP
• A Java Data Security Framework (JDSF) and its Case Studies

Cited by in corpus (5)

• The use of machine learning with signal- and NLP processing of source code to fingerprint, detect, and classify vulnerabilities and weaknesses with MARFCAT
• Intensional Cyberforensics
• MARFCAT: Transitioning to Binary and Larger Data Sets of SATE IV
• Cryptolysis v.0.0.1 - A Framework for Automated Cryptanalysis of Classical Ciphers
• A Case Study on Quality Attribute Measurement using MARF and GIPSY