Date of Award

6-2018

Document Type

Open Access

Degree Name

Bachelor of Science

Department

Electrical Engineering

First Advisor

Luke Dosiek

Language

English

Keywords

Signal processing, image forensics, camera, machine learning, demosaicing, color filter array, co-occurrence matrix, IEEE Signal Processing Cup, Electrical Engineering, Computer Science

Abstract

The goal of this Senior Capstone Project was to lead Union College’s first ever Signal Processing Cup Team to compete in IEEE’s 2018 Signal Processing Cup Competition. This year’s competition was a forensic camera model identification challenge and was divided into two separate stages of competition: Open Competition and Final Competition. Participation in the Open Competition was open to any teams of undergraduate students, but the Final Competition was only open to the three finalists from Open Competition and is scheduled to be held at ICASSP 2018 in Calgary, Alberta, Canada. Teams that make it to the Final Competition will be competing to win a grand prize of $5,000. The goal of this year’s competition required teams to build a classification system that used a combination of various signal processing, machine learning, and image forensic techniques in order to determine the make and model of the camera used to capture a digital image both before and after that image has been post processed. IEEE provided competing teams with an image database consisting of ten different camera models and 275 images accompanying each camera for teams with which to use to train their classification systems. This senior project design report focused on the proposed classification system design that was implemented and submitted on behalf of Union’s Signal Processing Cup Team. The chosen classification system design used methods of re-sampling and re-interpolating in order to build feature spaces based on the relative differences of the original and reconstructed images from the provided image database. These feature spaces were then used to train machine learning classifiers in order to develop an ensemble-based decision fusion to identify camera source. Through the completion of this project, students competing in the IEEE Signal Processing Cup gained experience using signal processing, machine learning, and image forensic techniques to solve challenging information security problems.

Share

COinS