Conference proceeding
Image filter identification using demosaicing residual features
2017 IEEE International Conference on Image Processing (ICIP), v 2017-, pp 4103-4107
Sep 2017
Abstract
Image filters have become a popular feature of photo editing software and camera phones. Filter identification can provide useful information for us to determine source and processing history of images. Currently, there is no forensic work done to perform filter identification. In this paper, we propose a framework to search for color correlations left by different filters in a set of interpolation residuals obtained from various demosaicing algorithms. To effectively capture the structures of color correlations, we design a diverse set of geometric co-occurrence patterns and gather both intra-channel and inter-channel color dependencies using co-occurrence matrices. Experiments conducted on two large image databases full demonstrate the ability of our framework to identify a wide range of filters provided by both cameras and third-party software.
Metrics
Details
- Title
- Image filter identification using demosaicing residual features
- Creators
- Chen Chen - Drexel UniversityMatthew C. Stamm - Drexel University, Electrical and Computer Engineering
- Publication Details
- 2017 IEEE International Conference on Image Processing (ICIP), v 2017-, pp 4103-4107
- Publisher
- IEEE
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000428410704047
- Scopus ID
- 2-s2.0-85045311762
- Other Identifier
- 991019170557704721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Imaging Science & Photographic Technology