“This is the 13th day of my participation in the First Challenge 2022. For details: First Challenge 2022”

  • πŸŽ‰ statement: as one of the bloggers in AI field, ❀️ lives up to your time and your ❀️

    • ❀️ column: AI field data resource collation ❀️ [Effectively reject fake data]

    πŸ‘‹ Follow me πŸ‘‹, Get more fun AI, charge πŸš€ πŸš€

    Basic information

    • The paper “Towards Photo-realistic Visible Watermark Removal with Conditional Generative Adversarial Networks” proposed based on U-NET + The CGAN model uses a large scale watermarking data set to remove watermarks.
    • The paper links

    Introduction to data set

    The LVW dataset consists of 60,000 watermarked images, including 80 watermarks from companies, organizations and individuals, including Chinese, English and logo styles, with 750 images for each watermark. To ensure the generality and usability of the image data, the images of the PASCAL VOC 2012 dataset were treated as original watermarked images. The above 80 watermarks were then stamped on the original image with random size, position and transparency, while the location information of the watermarks was recorded.

    Data set partitioning

    In order to meet the requirements of automatic processing of watermarks and images that have never been seen in real scenes, it is necessary to ensure that the watermarks and images in the training set will not appear in the test set, so that the application scenarios in real life can be well simulated. Specifically, 64 of the 80 watermarks are used as training watermarks, and the remaining 16 watermarks are used as test watermarks. Meanwhile, the training set images were selected from the PASCAL VOC 2012 training and validation images, while the test set images were selected from the PASCAL VOC 2012 test images.

    Sample dataset

    This dataset is used for academic purposes and is cited in the paper below

    ****** Citation ******

Please cite the following papers if you use this LVW dataset in your research:

[1] Danni Cheng, Xiang Li, Wei-Hong Li, Chan Lu, FakeLi, Hua Zhao and Wei-Shi Zheng. "Large-Scale Visible Watermark Detection and Removal with Deep Convolutional Networks", Chinese Conference on Pattern Recognition and Computer Vision (PRCV) , 2018.

[2] Xiang Li, Chan Lu, Danni Cheng, Wei-Hong Li, Mei Cao, Bo Liu, Jiechao Ma and Wei-Shi Zheng. "Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks", International Conference on Image and Graphics (ICIG), 2019.


Copy the code

    Notes (Data set production instructions in the paper)

    The data set can be obtained as follows

    Search for the same name of this blog public account, public account background, reply to large-scale watermarking to obtain the large-scale watermarking data set in this blog download link:

    Large scale watermarkingCopy the code

    πŸ’¬ to add a declaration

    Data resources are public, even open source, but sharing methods are personal

    It is not easy for the author to share and organize the data set. We all have the moment when we start to grow up from the small white, and there will be deficiencies in many places. Please believe that we will also make progress slowly

    πŸš€πŸš€ So far the gold digging platform has created the following classic blog post πŸš€πŸš€

    Computer vision field, classic blog post

    • 🍊 Use AI to convert photos of good friends into pencil sketches — 🍊2020 U2Net🍊

    • 🍊 NiceGAN environment to build, style migration (with source) | 【 2020 】 CVPR

    • 🍊 multi-stage progressive image restoration – go rain, denoising, fuzzy – effective tutorial (with source) | 【 2021 】 CVPR

    • 🍊 Image inpainting Based on Deep Learning – A Review

    • 🍊 graduation thesis, academic paper writing basic skills and experience – one read

    • 🍊 LaTeX2021 formula preparation, graphic installation, detailed tutorial, a read

    AI learning, deep learning environment building: an understanding

    • 🍊 # Ubuntu install CUDa11.2 for current users

    • 🍊 # Linux and Windows setup PIP image source – the most practical machine learning library download acceleration setup

    • 🍊 # Specify the GPU to run and train Python programs, deep learning single card, multi-card training GPU Settings

    • 🍊 # Install Pytorch and Torchvision in Cuda10.0 for Linux

    • 🍊 # Read SSH password login, public key authentication login

    • Install JDK 11: configure the JAVA_HOME environment variable

    πŸš€πŸš€ Mexic AI

  • πŸŽ‰ as one of the bloggers with the most dry goods in the field of AI, ❀️ lives up to his time and qing ❀️
  • ❀️ If the article is helpful to you, like, comment encourage bloggers every minute to seriously create