wxk2008

face_emotion_detection

using the libsvm, dlib to do face emotion detetction, if you want to improve the accuracy rate, you should tarin much more using much more data

remove-stamp

read_time-object-tracking-and-recognition

aster

Recognizing cropped text in natural images.

datasets

DBNet.pytorch

A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization

dbnet_tensorflow

DocProj

Document Rectification and Illumination Correction using a Patch-based CNN

gender_detection

using the svm,gabor,LBF to de gender detecttion

pytorch_crnnTOtf_crnn

research-charnet

CharNet: Convolutional Character Networks

STN_CNN_LSTM_CTC_TensorFlow

use STN+CNN+BLSTM+CTC to do OCR

tf-deeplabv3plus

this project is created based on the Google's tensorflow-project, the base net is mobilenetv2, if the model is trained base on the pre-train model, the Miou can be 84%

voc12

voc12augment is used to do object segmentation

crnn_pytorch

handpose_x

手部21个关键点检测，二维手势姿态，手势识别，pytorch,handpose

HDWT-data

models

Models and examples built with TensorFlow

opencv_extra

OpenCV extra data

PaddleOCR

基于飞桨的OCR工具库，包含总模型仅8.6M的超轻量级中文OCR，单模型支持中英文数字组合识别、竖排文本识别、长文本识别。同时支持多种文本检测、文本识别的训练算法。