English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Convolutional Neural Networks (CNNs) have proved very accurate in multiplecomputer vision image classification tasks that required visual inspection inthe past (e.g., object recognition, face detection, etc.). Motivated by theseastonishing results, researchers have also started using CNNs to cope withimage forensic problems (e.g., camera model identification, tamperingdetection, etc.). However, in computer vision, image classification methodstypically rely on visual cues easily detectable by human eyes. Conversely,forensic solutions rely on almost invisible traces that are often very subtleand lie in the fine details of the image under analysis. For this reason,training a CNN to solve a forensic task requires some special care, as commonprocessing operations (e.g., resampling, compression, etc.) can strongly hinderforensic traces. In this work, we focus on the effect that JPEG has on CNNtraining considering different computer vision and forensic imageclassification problems. Specifically, we consider the issues that rise fromJPEG compression and misalignment of the JPEG grid. We show that it isnecessary to consider these effects when generating a training dataset in orderto properly train a forensic detector not losing generalization capability,whereas it is almost possible to ignore these effects for computer visiontasks.

Training CNNs in Presence of JPEG Compression: Multimedia Forensics vs Computer Vision