flyinggh Goto Github PK

fots

OCR detection for ICDAR2015, which is based on FOTS, the precision is 80.6%.

fots_two_stage

EAST + Rotate + CRNN

frankenplus

Part of eMOP: Franken+ tool for creating font training for Tesseract OCR engine from page images.

frda

Face reconstruction and dense alignment

fvcore

Collection of common code that's shared among different research projects in FAIR computer vision team.

grabcut

Automatically exported from code.google.com/p/grabcut

grammarcnn

A CNN model for code generation.

grt

gesture recognition toolkit

halide

a language for fast, portable data-parallel computation

hdr-plus

HDR+ Implementation

hdrnet

An implementation of 'Deep Bilateral Learning for Real-Time Image Enhancements', SIGGRAPH 2017

homemade-machine-learning

🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained

horovod

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

hyperlpr

基于深度学习高性能中文车牌识别 High Performance Chinese License Plate Recognition Framework.

image-quality-assessment

Convolutional Neural Networks to predict the aesthetic and technical quality of images.

image-text-localization-recognition

A general list of resources to image text localization and recognition 场景文本位置感知与识别的论文资源与实现合集 シーンテキストの位置認識と識別のための論文リソースの要約

img2pose

The official PyTorch implementation of img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation

imgaug

Image augmentation for machine learning experiments.

impfacerecognition

A Matlab implementation of Face Recognition using Sparse Representation.

individual-project

My final year individual project, binocular 3D vision for Baxter robot.

insight

Computer Binocular Vision for Three-D Models' Reconstruction

jarvis

As the name suggests

jarvis-1

A very simple AI-based personal assistant written in Python.

javacnn

A Java implement of Convolutional Neural Network.

kaldi-lstm

C++ implementation of LSTM (Long Short Term Memory), in Kaldi's nnet1 framework. Used for automatic speech recognition, possibly language modeling etc, the training can be switched between CPU and GPU(CUDA). This repo is now merged into official Kaldi codebase(Karel's setup), so this repo is no longer maintained, please check out the Kaldi project instead.

kaze

KAZE Features

labeldoc

label tool for document analysis and OCR

lanyon

A content-first, sliding sidebar theme for Jekyll.

lbp-dbn-face-recognition

使用LBP特征提取算法提取人脸特征，DBN网络来实现人脸识别，测试数据库ORL数据库，识别率可达90%以上

learning-in-the-frequency-domain