Kamino666 / watermark-tracerLinks
一个基于可视水印检测识别的数字媒体溯源应用系统，是我的大作业项目，包含这个系统以及一个开源的大规模常见水印图像数据集（Large-scale Common Watermark Dataset, LCWD）。 输入一个带有可视水印的图片或视频，系统会检测定位到水印所在的区域，然后将其提取出来，然后借助百度AI开放平台的OCR和logo识别以及Bing搜索引擎，溯源到这个图片或视频的源头。
☆129Updated 2 years ago
Alternatives and similar repositories for watermark-tracer
Users that are interested in watermark-tracer are comparing it to the libraries listed below
Sorting:
- [ACM MM 2021] Visible Watermark Removal via Self-calibrated Localization and Background Refinement☆231Updated last year
- ☆107Updated 2 years ago
- A self-supervised CNN for image watermark removal (IEEE Transactions on Circuits and Systems for Video 2024)☆57Updated 9 months ago
- 手写文字擦除第1名方案，水印智能消除赛第1名☆142Updated last year
- A simple image search engine using CLIP feature.☆65Updated 2 years ago
- A prize winning solution for Multimedia Deepfake Detection competition.☆159Updated 8 months ago
- Model for watermark classification implemented with PyTorch☆113Updated 8 months ago
- ☆79Updated 2 years ago
- 通用的图像分类项目，并以涉黄、涉政、涉恐和普通图片4分类为例。☆137Updated 5 years ago
- 检测透视图像中的矩形文档并对其进行矫正☆26Updated 2 years ago
- Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning☆28Updated last year
- This is an official pytorch implementation for "DENet: Disentangled Embedding Network for Visible Watermark Removal" (AAAI23).☆34Updated last year
- BSHM人像抠图ONNX版本☆24Updated last year
- 当下热门的模糊人脸修复模型的部署，分别是：Codeformer，GFPGAN，GPEN，Restoreformer☆33Updated last year
- 图片向量检索服务，包含Numpy、Faiss、ES、Milvus多种计算引擎☆133Updated 2 years ago
- 这是一个基于stable diffusion的扩展绘画工具（outpainting）☆36Updated last year
- 基于多模态特征融合的即时社交软件违规图片检测系统。通过结合图像和文本信息，系统支持对OCR后的文本进行高效的敏感词检测，并允许用户自定义敏感词词库。此外，系统能够自动识别图片中的二维码并提取域名进行安全检测，实现对图片的三分类，包括正常、涉黄和敏感信息，并支持建立图片黑白名…☆61Updated last year
- Chinese CLIP models with SOTA performance.☆55Updated last year
- 🔥Char detection base on crnn 字符（单字）检测基于CRNN☆82Updated 2 years ago
- Unofficial implementation of 《Towards Photo-Realistic VisibleWatermark Removal with Conditional Generative Adversarial Networks》☆10Updated 2 years ago
- An easy use face swap tool for images and tools only depend on onnxruntime.☆75Updated last year
- [AAAI 2021] Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal☆249Updated last year
- 轻量模型的图像分析web服务，包括倾斜矫正OCR，公章(印章)检测+识别，车牌识别。api方案使用FastAPI+Gunicorn，提供gradio展示。☆99Updated last year
- 数字图像课程大作业，实现图片中文档提取与矫正。整体思路是通过hough变换检测出直线，进而得到角点，最后经过投影变换，进行矫正。整个项目只用到了opencv的IO操作(包括手写卷积，hough哈夫变换，投影变换等等)☆76Updated 4 years ago
- 「ICLR 2025」 A Sanity Check for AI-generated Image Detection☆164Updated 3 weeks ago
- 🔥 [ICLR 2025] FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models☆244Updated this week
- 天池&ICDAR2023篡改图像检测比赛方案☆22Updated 2 years ago
- Chinese Stable Diffusion, zh SD,中文文生图，中文SD，中文Stable Diffusion☆49Updated last year
- ☆51Updated last year
- 2024.06.19 本项目使用Chinese-CLIP搭建文搜图/图搜图页面,旨在帮助用户快速使用跨模态检索任务。本项目代码针对MUGE数据集约19w(189585张)数据作为底库数据。本项目提供了提取特征, 检索, 以及uI代码。☆18Updated 11 months ago