该工作由电子科技大学陈昂、刘俊凯、夏子寒同学完成。我们提出可以使用深度学习的方案对中国车牌进行检测和识别。我们提出使用YOLOv3网络进行车牌检测，然后创新性地对检测后的车牌使用空间变换网络STN加以校正，最后使用LPRNet网络进行车牌的字符与数字识别。目前实测结果，在老师提供的45张数据集上，我们的YOLOv3网络检测准确率（IOU）达到98.2%，深度学习级联网络识别准确率为95.6%。我们采用大量测试集，最终我们的YOLOv3_STN_LPRNet级联网络识别准确率稳定在93.3%，不加空间变换网络STN的话，识别准确率在66%左右。 总体来说，使 用深度学习的方案比传统方案效果提升的非常好，而且我们加入空间变换网络STN的做法对于提升识别准确率很有效。
☆81Jul 22, 2020Updated 6 years ago
Alternatives and similar repositories for License_Plate_Recognition_pytorch
Users that are interested in License_Plate_Recognition_pytorch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Pytorch + STNet + LPRNet 进行车牌识别☆48Sep 24, 2020Updated 5 years ago
- 车牌识别，自然场景目标识别，使用中山大学智能交通重点实验室（ITS）开源数据集进行训练，tensorflow-ssd目标检测☆14Mar 31, 2021Updated 5 years ago
- 该工作的内容主要是面向中国车牌识别系统。车牌的检测系统通过YOLOv3网络来实现，检测后的车牌会通过空间变换网络进行倾斜校正。校正后的图片经由LPRNet进行识别。目前在1000张图片上测试的最终准确率可达93.3%。实现者电子科技大学刘俊凯、陈昂、夏子寒☆39Jul 18, 2020Updated 6 years ago
- 我们使用传统的数字图像处理的方法进行中国车牌的识别，与我们的深度学习方法进行对比。☆38Jul 18, 2020Updated 6 years ago
- License plate recognition 车牌识别☆29Feb 2, 2021Updated 5 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 使用retinaface完成车牌关键点检测，并在tensorRT下部署☆39Aug 5, 2021Updated 5 years ago
- 使用pytorch和opencv的简易识别车牌程序☆12Nov 3, 2020Updated 5 years ago
- License Plate Recognition☆33Dec 7, 2021Updated 4 years ago
- 基于yolov3的LPRnet车牌识别。以yolov3作为检测器、LPRnet作为识别模型，实现了实时车牌车牌识别模型。本项目直接使用LPRnet原始的网络作为车牌识别模型。☆16Feb 18, 2023Updated 3 years ago
- 使用 "Darknet yolov3-tiny" 进行车牌识别☆91May 21, 2019Updated 7 years ago
- Using GAN magic to generate more realistic license plates☆79Sep 6, 2019Updated 6 years ago
- OpenCV and Tesseract based python script to Recognise License Plate numbers☆11May 2, 2018Updated 8 years ago
- 使用YOLOv5和LPRNet进行车牌检测+识别（CCPD数据集）☆617Aug 10, 2024Updated 2 years ago
- A two stage lightweight and high performance license plate recognition in MTCNN and LPRNet☆683Jan 22, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- 深度学习车牌检测与识别，检测结果包含车牌矩形框和4个角点，基于pytorch框架运行☆116Jan 12, 2022Updated 4 years ago
- 基于Yolov5车牌检测,更快更准.☆1,288Feb 7, 2022Updated 4 years ago
- 基于深度学习的车牌识别GUI项目☆48Jun 15, 2022Updated 4 years ago
- 基于4种轻量级深度卷积网络的无场景约束全自动车牌识别，轻量级车牌检测，轻量级车牌识别，pyqt5可视化界面☆67Mar 24, 2020Updated 6 years ago
- Generate the fake Chinese license plate images for detection & recognition☆116Feb 5, 2020Updated 6 years ago
- [ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition☆2,644Feb 15, 2024Updated 2 years ago
- 基于Python的车牌检测和识别系统：☆881Jul 6, 2019Updated 7 years ago
- End to End Chinese License Plate Recognition☆80Jun 8, 2019Updated 7 years ago
- 基于QOpenGLWidget，实现点云载入，显示，鼠标键盘交互。点云的旋转，平移，放大缩小等功能☆11May 7, 2020Updated 6 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICML 2022] Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum☆12Jul 15, 2022Updated 4 years ago
- From pixels to symbolic rule learning☆13Nov 12, 2021Updated 4 years ago
- Unity project utilizing my "head-pose-estimation-opencv" DLL☆10Jan 8, 2020Updated 6 years ago
- RBM+BP神经网络识别手写数字和英文字符☆11Mar 25, 2023Updated 3 years ago
- 简单车牌识别-Mask_RCNN定位车牌+手写方法分割字符+CNN单个字符识别☆182Nov 21, 2020Updated 5 years ago
- XLPNet is a light-weight fully convolutional model for license plate detection and recognition.☆13Apr 1, 2022Updated 4 years ago
- 基于yoloV5-V6系列，train_palte添加多头检测。train_key添加关键点检测算法。☆44Nov 9, 2022Updated 3 years ago
- ☆11Jan 30, 2018Updated 8 years ago
- Python+OpenCV数字图像处理课程设计作业[车牌识别]☆219Feb 1, 2020Updated 6 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- 轻量级的车牌检测项目（支持车牌四角定位、矫正对齐）☆174Jun 4, 2024Updated 2 years ago
- 从0开始写一个操作系统——《操作系统真象还原》☆12Sep 21, 2020Updated 5 years ago
- ☆12Jan 8, 2020Updated 6 years ago
- chineres ocr from picture, 中英文本检测与文本识别，dense-ctc，dbnet，crnn，pse，unet等模型☆11Sep 23, 2020Updated 5 years ago
- 基于keras resnet34的车牌识别项目☆11Jan 19, 2019Updated 7 years ago
- 生成车牌识别数据集☆144Jun 1, 2023Updated 3 years ago
- MIDS Capstone Project, Duke University, 2021☆10Apr 28, 2021Updated 5 years ago