livezingy / merged-characters-segmentation
Algorithm implementation of the "The Robustness of “Connecting Characters Together” CAPTCHAs". The test data set is the TAOBAO CAPTCHA that composed of blue character and white background.
☆27Updated 10 months ago
Related projects ⓘ
Alternatives and complementary repositories for merged-characters-segmentation
- Machine Learning 2016 final project☆45Updated 8 years ago
- Build an Optical Character Recognition service using deep learning method☆54Updated 7 years ago
- hack captcha with CNN☆37Updated 8 years ago
- 代码讲解部分请前往blog:http://lan2720.github.io/☆34Updated 8 years ago
- recaptcha with lstm and mxnet☆29Updated 7 years ago
- 验证码识别,该模型是基于xlvector模型上进行加工,验证码内容包含了大小字母以及数字,采用lstm+warp-ctc+cnn达到不分割字符而识别验证码内容~☆113Updated 7 years ago
- Caffe for CC4.0-Windows,简单的Caffe C++接口,方便简单☆162Updated 4 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
- chinese character generator and training using keras.☆40Updated 7 years ago
- object detection app based on tensorflow api☆51Updated 2 years ago
- A Simple Chinese OCR from tipdm contest☆63Updated 8 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