FantDing / Image-document-extract-and-correction
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)
☆74Updated 4 years ago
Alternatives and similar repositories for Image-document-extract-and-correction:
Users that are interested in Image-document-extract-and-correction are comparing it to the libraries listed below
- Document photo perspective transformation correction,利用unet网络进行 文档照片透视纠偏☆50Updated 4 years ago
- 参考眼底图像血管分割retina-unet实现的文档去噪、去水印☆96Updated 4 years ago
- ocr_torch是基于Torch1.8实现的DBNet(2.2M) + CRNN(3.8M)实现的轻量级文字检测识别项目(支持onnx推理).☆28Updated 3 years ago
- CTPN+CRNN bank card number identification(data/test pictures accuary ≈90%)☆69Updated 2 years ago
- 使用Pytorch实现了中文手写字符识别☆26Updated 6 years ago
- OCR Document image deformation correction.复现阿里OCR皱巴巴文档图像形变矫正☆93Updated 4 years ago
- 身份证全卡面文字识别:Faster-rcnn检测图片里的证件照,DBNet检测证件照里的文字,CRNN识别证件照里的文字☆41Updated 3 years ago
- 基于CTPN和CRNN实现的银行卡号识别系统☆13Updated 4 years ago
- A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization☆110Updated 3 years ago
- ocr with yolo3 as feature extractor, implemented by keras, and accelerated by tensorrt☆34Updated 4 years ago
- 基于pytorch卷积神经网络的中文手写汉字识别,使用HWDB数据库☆106Updated 5 years ago
- Using deep-leaning detect tables in the documet image☆25Updated 5 years ago
- 生成车牌识别数据集☆137Updated last year
- source codes for paper: DeepHSV: User-independent Offline Signature Verification Using Two-Channel CNN☆27Updated 5 years ago
- you can use dbnet to detect word or bar code,Knowledge Distillation is provided,also python tensorrt inference is provided.☆43Updated 4 years ago
- 检测条形码、运动目标、汉字识别等☆19Updated 5 years ago
- ☆35Updated 3 years ago
- 卡证和文档检测和矫正☆40Updated 4 months ago
- 表格结构解析新思路(表格识别新思路)☆124Updated 3 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☆12Updated 4 years ago
- 将原本Keras版本的AdvancedEAST改写成PyTorch版,将数据集由.npy文件改成一个LMDB文件,加入Precision,Recall, F1 score方便训练以及调试,底层网络仍然用VGG16。☆38Updated 4 years ago
- crnn实现水平和垂直方向中文文字识别, 提供在3w多个中文字符训练的水平识别和垂直识别的预训练模型; 欢迎关注,试用和反馈问题... ...☆248Updated 4 years ago
- 本项目旨在以CRAFT提供的预训练模型为基础,进行迁移学习以用于检测自己数据集中的文本。☆41Updated 5 years ago
- 使用GAN擦出文档印章 remove stamp by GAN☆155Updated 3 years ago
- python opencv 文档照片与证件照片的仿射变换的矫正☆11Updated 4 years ago
- ☆18Updated 3 years ago
- 图像矫正☆13Updated 7 years ago
- 表格线检测☆24Updated 5 years ago
- 基于keras的银行卡号识别☆69Updated 5 years ago
- Identifying numbers from bankcard, based on Deep Learning with Keras☆81Updated 3 years ago