All Projects → namtpham → casia1groundtruth

namtpham / casia1groundtruth

Licence: other
Groundtruth images of tampering dataset CASIA 1.0

Projects that are alternatives of or similar to casia1groundtruth

casia2groundtruth
Groundtruth images of tampering dataset CASIA 2.0
Stars: ✭ 97 (+259.26%)
Mutual labels:  image-manipulation, casia, forgery, forgery-detection, groundtruth, splicing-detection, groundtruth-dataset
ManTraNet-pytorch
Implementation of the famous Image Manipulation\Forgery Detector "ManTraNet" in Pytorch
Stars: ✭ 47 (+74.07%)
Mutual labels:  image-manipulation, forgery, forgery-detection
ImagerJs
A JavaScript library for uploading images using drag & drop. Crop, rotate, resize, or shrink your image before uploading.
Stars: ✭ 101 (+274.07%)
Mutual labels:  image-manipulation
PerceptualGAN
Pytorch implementation of Image Manipulation with Perceptual Discriminators paper
Stars: ✭ 119 (+340.74%)
Mutual labels:  image-manipulation
sic
🦜 Accessible image processing and conversion from the terminal. Front-end for image-rs/image.
Stars: ✭ 96 (+255.56%)
Mutual labels:  image-manipulation
AODA
Official implementation of "Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis"(WACV 2022/CVPRW 2021)
Stars: ✭ 44 (+62.96%)
Mutual labels:  image-manipulation
Binarify
Convert Images to Binary Art!
Stars: ✭ 15 (-44.44%)
Mutual labels:  image-manipulation
wp-intervention
On-demand image manipulation for WordPress via the Intervention Library.
Stars: ✭ 21 (-22.22%)
Mutual labels:  image-manipulation
neural-imaging
[CVPR'19, ICLR'20] A Python toolbox for modeling and optimization of photo acquisition & distribution pipelines (camera ISP, compression, forensics, manipulation detection)
Stars: ✭ 109 (+303.7%)
Mutual labels:  forgery-detection
npm-sharper
📷 Automatic image processor middleware built on top of sharp and multer for express.
Stars: ✭ 17 (-37.04%)
Mutual labels:  image-manipulation
ZaneAPI
Image manipulation API for the layman.
Stars: ✭ 12 (-55.56%)
Mutual labels:  image-manipulation
imei
IMEI - ImageMagick Easy Install
Stars: ✭ 126 (+366.67%)
Mutual labels:  image-manipulation
coursera-ai-for-medicine-specialization
Programming assignments, labs and quizzes from all courses in the Coursera AI for Medicine Specialization offered by deeplearning.ai
Stars: ✭ 80 (+196.3%)
Mutual labels:  image-manipulation
auto-cloudinary
Super simple Cloudinary auto-upload implementation for WordPress.
Stars: ✭ 34 (+25.93%)
Mutual labels:  image-manipulation
inumon
A high-level image I/O and manipulation library for Nim
Stars: ✭ 30 (+11.11%)
Mutual labels:  image-manipulation
grafx2
Mirror of GrafX2. Official repo is on gitlab.
Stars: ✭ 108 (+300%)
Mutual labels:  image-manipulation
imaditor
Image Editor with a UI creatief with ImGui
Stars: ✭ 24 (-11.11%)
Mutual labels:  image-manipulation
imgx
A module to compress and optimize images
Stars: ✭ 13 (-51.85%)
Mutual labels:  image-manipulation
automatic-manga-colorization
Use keras.js and cyclegan-keras to colorize manga automatically. All computation in browser. Demo is online:
Stars: ✭ 20 (-25.93%)
Mutual labels:  image-manipulation
scikit-image-cheatsheet
See all scikit-image methods for image creation & manipulation and their output at a glance.
Stars: ✭ 16 (-40.74%)
Mutual labels:  image-manipulation

Groundtruth of spliced images in dataset CASIA 1.0

  • CASIA 2.0 groundtruth dataset is avaiable at: https://github.com/namtpham/casia2groundtruth

  • Please notice that the authors made mistakes in naming the files. If you already downloaded the dataset, I recommend you to rename the tampered images using the commands in the excel file. Otherwise, you can use the modified version of dataset.

  • Since the owners' server is no longer avaiable, I upload the dataset to my drive, including original dataset and the modified version (renaming dozens of images in tampering folder). Please visit one of the following links to download (~90 MB):

  • Google Drive: https://bit.ly/37TuHRx

  • One Drive: https://bit.ly/3nXyYJw

Due to the lack of manual file, I write up here the naming convention:

Authentic images: 800 images (8 categories, 100 images in each category).

Au_ani_0001.jpg

Au: Authentic

ani: animal category

Other categories: arc (architecture), art, cha (characters), nat (nature), pla (plants), sec, txt (texture)

Tampering images

a. Spliced image

    Sp_D_CND_A_pla0005_pla0023_0281.jpg
  • Sp: Splicing
  • D: Different (means the tampered region was copied from the different image)
  • Next 4 letters stand for the techniques they used to create the images. Unfortunately, I don't remember exactly.
  • pla0005: the source image
  • pla0023: the target image
  • 0281: tampered image ID

b. Copy-move images

    Sp_S_CND_A_pla0016_pla0016_0196.jpg
  • Sp: Tampering
  • S: Same (means the tampered region was copied from the same image)
  • And the rest is similar to case a.

If you use the groundtruth dataset for a scientific publication, please cite the following papers

  • CASIA dataset

      @inproceedings{Dong2013,
      doi = {10.1109/chinasip.2013.6625374},
      url = {https://doi.org/10.1109/chinasip.2013.6625374},
      year = {2013},
      month = jul,
      publisher = {{IEEE}},
      author = {Jing Dong and Wei Wang and Tieniu Tan},
      title = {{CASIA} Image Tampering Detection Evaluation Database},
      booktitle = {2013 {IEEE} China Summit and International Conference on Signal and Information Processing}
      }
    
  • CASIA groundtruth dataset

     @article{pham2019hybrid,
     title={Hybrid Image-Retrieval Method for Image-Splicing Validation},
     author={Pham, Nam Thanh and Lee, Jong-Weon and Kwon, Goo-Rak and Park, Chun-Su},
     journal={Symmetry},
     volume={11},
     number={1},
     pages={83},
     year={2019},
     publisher={Multidisciplinary Digital Publishing Institute}
     }
    
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].