13 April 2018 Non-parametric adaptative JPEG fragments carving
Author Affiliations +
Proceedings Volume 10696, Tenth International Conference on Machine Vision (ICMV 2017); 106962D (2018) https://doi.org/10.1117/12.2310079
Event: Tenth International Conference on Machine Vision, 2017, Vienna, Austria
Abstract
The most challenging JPEG recovery tasks arise when the file header is missing. In this paper we propose to use a two layer machine learning model to restore headerless JPEG images. We first build a classifier able to identify the structural properties of the images/fragments and then use an AutoEncoder (AE) to learn the fragment features for the header prediction. We define a JPEG universal header and the remaining free image parameters (Height, Width) are predicted with a Gradient Boosting Classifier. Our approach resulted in 90% accuracy using the manually defined features and 78% accuracy using the AE features.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Sabrina Cherifa Amrouche, Sabrina Cherifa Amrouche, Dalila Salamani, Dalila Salamani, } "Non-parametric adaptative JPEG fragments carving", Proc. SPIE 10696, Tenth International Conference on Machine Vision (ICMV 2017), 106962D (13 April 2018); doi: 10.1117/12.2310079; https://doi.org/10.1117/12.2310079
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

Fast classification scheme for VQ
Proceedings of SPIE (November 21 2002)
Bit map reconstruction for document image compression
Proceedings of SPIE (November 01 1996)
Fractal image compression based on visual perception
Proceedings of SPIE (April 20 1995)

Back to Top