brahimbellahcen Goto Github PK

mcs2018_challenge

Third place solution for Vision Labs Adversarial Attacks on Black Box Face Recognition System Challenge.

mediapipe

MediaPipe is a cross-platform framework for building multimodal applied machine learning pipelines

memory-augmented-neural-network

meshnet

MeshNet: Mesh Neural Network for 3D Shape Representation (AAAI 2019)

meshrcnn

code for Mesh R-CNN, ICCV 2019

metric_learning

Metric Learning TF 2.0+Keras Algorithm Implementations for Facial Recognition

midv500

Download and convert MIDV-500 annotations to COCO instance segmentation format

ml-python3-projects

ML-PYTHON3-PROJECTS

mocr

Meaningful Optical Character Recognition from identity cards with Deep Learning.

models

A collection of pre-trained, state-of-the-art models in the ONNX format

modular_tree

monk_v1

Monk is a low code Deep Learning tool and a unified wrapper for Computer Vision.

mtcnn-of-litong

离瞳的MTCNN

mtcnn-tensorflow

mtcnn-tf

mtcnn_pytorch

mtcnn_pytorch_zero_to_one

Tutorial about how to train MTCNN from zero to one.

mtcnnmaskdetection

Test the MTCNN face detector for people wearing masks

my_orc_keras_verification_code_identification

本项目实现了ocr主流算法gru/lstm+ctc+cnn架构，进行不定长度验证码识别，达到不分割字符而识别验证码内容的效果。验证码内容包含了大小字母以及数字，并增加点、线、颜色、位置、字体等干扰项。本项目对gru +ctc+cnn、lstm+ctc+cnn、cnn三种架构进行了对比，实践说明同等训练下gru/lstm+ctc+cnn架构准确率和速度均明显优于cnn架构，gru +ctc+cnn优于lstm+ctc+cnn，在实验2500个样本数据200轮训练时，gru +ctc+cnn架构在500样本测试准确率达90.2%。本项目技术能够训练长序列的ocr识别，更换数据集和相关调整，即可用于比如身份证号码、车牌、手机号、邮编等识别任务，也可用于汉字识别。

nd131-project-03

Project #3 for Intel's Nanodegree program on Udacity. Utilizing OpenVino toolkit, utilizing several models to controller a mouse pointer based on face and gaze

nvcaffe-converter

Convert NVCaffe model and weights into BVLC Caffe format

object_detection_and_face_identification

Object_detection with Face_Identification.

ocr_densenet

第一届西安交通大学人工智能实践大赛（2018AI实践大赛--图片文字识别）第一名；仅采用densenet识别图中文字

ocr_toolkit

I am trying to collect and combine resources and methods

odenet

This project implements a simple demo of ODENet

oneshot-audio

Experiment with "one-shot learning" techniques to recognize a voice signature

openseeface

Robust realtime face and facial landmark tracking on CPU with Unity integration

owndataset-face-calssification-withsvm

This is a fast implementation of a face classification system trained from scratch to your own dataset. The implementation is based on Facenet from keras, on MTCNN for face extraction and on an SVM for face identification/recognition/verification.

patch_based_cnn

the implement of Face Anti-Spoofing Using Patch and Depth-Based CNNs

pdftableextract

PDFTableExtract

preprocessing-images-for-face-recognition

preprocessing-images-for-Face-Recognition