Image Processing

ViFoDAC is a collection of Authentic videos and Forged videos. The dataset has a total of 16 Authentic videos and 16 Forged videos. The Authentic videos are camera recorded whereas the Forged videos are edited using Adobe Premiere Pro and Wondershare Filmora software. The dataset can be used to train and optimise video identification models. This dataset can be used for the Research and Development of fake video classification. 

Re-curated Breast Imaging Subset DDSM Dataset (RBIS-DDSM) is a curated version of 849 images from the CBIS-DDSM dataset available online with a permissive copyright license (CC-BY-SA 3.0). The  CBIS-DDSM dataset is an improved version of the DDSM dataset. The authors of the CBIS-DDSM dataset attempted to improve the ground truth by applying simple image processing based methods to enhance the edges without any manual intervention from medical experts in order to segment and annotate masses. However, these annotations (segmentation maps) are inaccurate in most of the images. 

This dataset consists of 2 types of images i.e Authentic and Tampered. There are a total of 1,389 Authentic images and 597 Tampered images. Authentic images are camera clicked images in raw form & tampered images are the one being edited by Adobe Photoshop and few mobile applications. Different types of forgery techniques like copy-move, splicing, color enhancement, resizing etc have been applied on the tampered images. 

This publication contains three new datasets for scene-level sketch semantic segmentation task, namely SKY-Scene, TUB-Scene, and Freehand-Scene. SKY-Scene and TUB-Scene are synthetic datasets, where the scene layout templates were extracted from dataset SketchyScene, and the object components were adopted from dataset Sketchy. They are composed to include more sketch-specific characteristics, e.g., sparsity, abstractness, and diversity, to truly evaluate segmentation performance. Freehand-Scene are fifty real human-drawn scene sketches for practical test.