AstarLight / my_scanner
my scanner 1.0
☆122Updated 7 years ago
Alternatives and similar repositories for my_scanner:
Users that are interested in my_scanner are comparing it to the libraries listed below
- Document Scanning With TensorFlow And OpenCV☆422Updated 5 years ago
- ☆103Updated 6 years ago
- iOS版本的手写汉字识别Demo,核心算法不到300行,参考博文//www.linyibin.cn/2016/11/10/technology-IME-HandWritingRecognization/☆124Updated 6 years ago
- haar + adboost, cnn,识别国内20多家银行的20多种银行卡,支持凸面和平面印刷字体☆112Updated 6 years ago
- Deep Learning on 身份证识别☆124Updated 5 years ago
- Image-process-libraries-like-photoshop☆162Updated 6 years ago
- A tools can generate samples for OCR trainning. 用于OCR的字符样本生成工具☆65Updated 7 years ago
- ☆51Updated 7 years ago
- ☆255Updated 8 months ago
- An implementation of CRNN (CNN+LSTM+warpCTC) on MxNet for chinese text recognition☆212Updated 2 years ago
- 使用mobilenet改造HED实现在手机端进行文档的边缘检测☆24Updated 6 years ago
- 端到端的针对身份证的文字识别☆24Updated 6 years ago
- 身份证复印件识别,CCF BDCI参赛项目☆62Updated 5 years ago
- 这是一个可以将任意人像照片转换为证件照的模块,使用grabcut和原创的matting算法,使用C++11标准编写,提供C++接口。☆42Updated 10 years ago
- 对任何文字图片来源进行预处理结合tesseract-ocr进行识别,主要模块有纸张边缘查找,四角定位,仿射变换,二值化,模糊处理,摩尔纹处理,噪点过滤,图片exif,jfif信息处理,表格线删除,图片阴影处理,傅里叶图片矫正处理等等。。本程序依赖于与图片exif,jfif信…☆89Updated 6 years ago
- Faster_RCNN for text detection 文本检测☆63Updated 3 years ago
- Document photo perspective transformation correction,利用unet网络进行 文档照片透视纠偏☆49Updated 4 years ago
- DFT-based text image rotation correction using OpenCV☆38Updated 11 years ago
- 公式图片ocr,输入图片输出对应的latex表达式☆291Updated 5 years ago
- BasicOCR是一个致力于解决自然场景文字识别算法研究的项目。该项目由长城数字大数据应用技术研究院佟派AI团队发起和维护。☆344Updated 4 years ago
- ☆56Updated 5 years ago
- Based on crnn add Chinese recognition☆134Updated 6 years ago
- Simple OCR service using deep learning☆59Updated 4 years ago
- 竖排书法汉字识别☆64Updated 5 years ago
- Script to train Hyperlpr(https://github.com/zeusees/HyperLPR)☆127Updated 5 years ago
- CNN models for CASIA-HWDB dataset recognition, Implementation of paper <Building Fast and Compact Convolutional Neural Networks for Offli…☆47Updated 6 years ago
- ☆70Updated 7 years ago
- 该脚本能够将用户指定的字符输出为不同字体的图像文件,用于训练文字识别的机器学习模型或用于其他文字识别OCR项目☆41Updated 6 years ago
- 使用CNN全卷积神经网络进行整行汉字识别,正确率90-94%,后来有朋友改成densenet做主网络,做到99%以上正确率☆31Updated 4 years ago
- 基于caffe的LSTM OCR案例,能够利用该案例完成序列的识别,包括验证码、车牌、身份证号码、地址等长序列动长的内容识别☆212Updated 7 years ago