This repository compare a selfie with images from identity documents and response if the selfie match.

Related tags

Deep Learningaws-rekognition-facecompare
Overview

aws-rekognition-facecompare

This repository compare a selfie with images from identity documents and response if the selfie match.

This code was made in a Python Notebook under SageMaker.

Set up:

  • Create a Notebook Instance in SageMaker
  • Notebook instance type : ml.t2.medium
  • Volume Size : 5GB EBS
  • Create a role for SageMaker with the following policies:
  • AmazonS3FullAccess
  • AmazonRekognitionFullAccess
  • AmazonSageMakerFullAccess
  1. Create a S3 Bucket
  2. Inside bucket create folder to insert the dataset images

Code Explanation

boto3 is needed to use the aws client of S3 and Rekognition. Just like what we do with variables, data can be kept as bytes in an in-memory buffer when we use the io module’s Byte IO operations, so we can load images froms S3. At least Pillow is needed for image plotting.

import boto3
import io
from PIL import Image, ImageDraw, ExifTags, ImageColor

rekognition_client=boto3.client('rekognition')
s3_resource = boto3.resource('s3')

In this notebook I use two functions of AWS Rekognition

  • detect_faces : Detect faces in the image. It also evaluate different metrics and create different landmarks for all elements of the face like eyes positions.
  • compare_faces : Evaluate the similarity of two faces.

Case of use

Here I explain how to compare two images

The compare function

IMG_SOURCE ="dataset-CI/imgsource.jpg"
IMG_TARGET ="dataset-CI/img20.jpg"
response = rekognition_client.compare_faces(
                SourceImage={
                    'S3Object': {
                        'Bucket': BUCKET,
                        'Name': IMG_SOURCE
                    }
                },
                TargetImage={
                    'S3Object': {
                        'Bucket': BUCKET,
                        'Name': IMG_TARGET                    
                    }
                }
)

response

{'SourceImageFace': {'BoundingBox': {'Width': 0.3676206171512604,
   'Height': 0.5122320055961609,
   'Left': 0.33957839012145996,
   'Top': 0.18869829177856445},
  'Confidence': 99.99957275390625},
 'FaceMatches': [{'Similarity': 99.99634552001953,
   'Face': {'BoundingBox': {'Width': 0.14619407057762146,
     'Height': 0.26241832971572876,
     'Left': 0.13103649020195007,
     'Top': 0.40437373518943787},
    'Confidence': 99.99955749511719,
    'Landmarks': [{'Type': 'eyeLeft',
      'X': 0.17260463535785675,
      'Y': 0.5030772089958191},
     {'Type': 'eyeRight', 'X': 0.23902645707130432, 'Y': 0.5023221969604492},
     {'Type': 'mouthLeft', 'X': 0.17937719821929932, 'Y': 0.5977044105529785},
     {'Type': 'mouthRight', 'X': 0.23477530479431152, 'Y': 0.5970458984375},
     {'Type': 'nose', 'X': 0.20820103585720062, 'Y': 0.5500822067260742}],
    'Pose': {'Roll': 0.4675966203212738,
     'Yaw': 1.592366099357605,
     'Pitch': 8.6331205368042},
    'Quality': {'Brightness': 85.35185241699219,
     'Sharpness': 89.85481262207031}}}],
 'UnmatchedFaces': [],
 'ResponseMetadata': {'RequestId': '3ae9032d-de8a-41ef-b22f-f95c70eed783',
  'HTTPStatusCode': 200,
  'HTTPHeaders': {'x-amzn-requestid': '3ae9032d-de8a-41ef-b22f-f95c70eed783',
   'content-type': 'application/x-amz-json-1.1',
   'content-length': '911',
   'date': 'Wed, 26 Jan 2022 17:21:53 GMT'},
  'RetryAttempts': 0}}

If the source image match with the target image, the json return a key "FaceMatches" with a non-empty, otherwise it returns a key "UnmatchedFaces" with a non-empty array.

# Analisis imagen source
s3_object = s3_resource.Object(BUCKET,IMG_SOURCE)
s3_response = s3_object.get()
stream = io.BytesIO(s3_response['Body'].read())
image=Image.open(stream)
imgWidth, imgHeight = image.size  
draw = ImageDraw.Draw(image)  

box = response['SourceImageFace']['BoundingBox']
left = imgWidth * box['Left']
top = imgHeight * box['Top']
width = imgWidth * box['Width']
height = imgHeight * box['Height']

print('Left: ' + '{0:.0f}'.format(left))
print('Top: ' + '{0:.0f}'.format(top))
print('Face Width: ' + "{0:.0f}".format(width))
print('Face Height: ' + "{0:.0f}".format(height))

points = (
    (left,top),
    (left + width, top),
    (left + width, top + height),
    (left , top + height),
    (left, top)

)
draw.line(points, fill='#00d400', width=2)

image.show()
Left: 217
Top: 121
Face Width: 235
Face Height: 328

png

0: for face in response['FaceMatches']: face_match = face['Face'] box = face_match['BoundingBox'] left = imgWidth * box['Left'] top = imgHeight * box['Top'] width = imgWidth * box['Width'] height = imgHeight * box['Height'] print('FaceMatches') print('Left: ' + '{0:.0f}'.format(left)) print('Top: ' + '{0:.0f}'.format(top)) print('Face Width: ' + "{0:.0f}".format(width)) print('Face Height: ' + "{0:.0f}".format(height)) points = ( (left,top), (left + width, top), (left + width, top + height), (left , top + height), (left, top) ) draw.line(points, fill='#00d400', width=2) image.show()"> 
# Analisis imagen target
s3_object = s3_resource.Object(BUCKET,IMG_TARGET)
s3_response = s3_object.get()
stream = io.BytesIO(s3_response['Body'].read())
image=Image.open(stream)
imgWidth, imgHeight = image.size  
draw = ImageDraw.Draw(image)
if len(response['UnmatchedFaces']) > 0:
    for face in response['UnmatchedFaces']:
        box = face['BoundingBox']
        left = imgWidth * box['Left']
        top = imgHeight * box['Top']
        width = imgWidth * box['Width']
        height = imgHeight * box['Height']
        print('UnmatchedFaces')
        print('Left: ' + '{0:.0f}'.format(left))
        print('Top: ' + '{0:.0f}'.format(top))
        print('Face Width: ' + "{0:.0f}".format(width))
        print('Face Height: ' + "{0:.0f}".format(height))

        points = (
            (left,top),
            (left + width, top),
            (left + width, top + height),
            (left , top + height),
            (left, top)

        )
        draw.line(points, fill='#ff0000', width=2)
        
if len(response['FaceMatches']) > 0:
    for face in response['FaceMatches']:
        face_match = face['Face']
        box = face_match['BoundingBox']
        left = imgWidth * box['Left']
        top = imgHeight * box['Top']
        width = imgWidth * box['Width']
        height = imgHeight * box['Height']
        print('FaceMatches')
        print('Left: ' + '{0:.0f}'.format(left))
        print('Top: ' + '{0:.0f}'.format(top))
        print('Face Width: ' + "{0:.0f}".format(width))
        print('Face Height: ' + "{0:.0f}".format(height))

        points = (
            (left,top),
            (left + width, top),
            (left + width, top + height),
            (left , top + height),
            (left, top)

        )
        draw.line(points, fill='#00d400', width=2)        
image.show()
FaceMatches
Left: 671
Top: 1553
Face Width: 749
Face Height: 1008

png

Owner
GitHub Repository
Molecular AutoEncoder in PyTorch

MolEncoder Molecular AutoEncoder in PyTorch Install $ git clone https://github.com/cxhernandez/molencoder.git && cd molencoder $ python setup.py insta

Carlos Hernández 80 Dec 05, 2022
MADE (Masked Autoencoder Density Estimation) implementation in PyTorch

pytorch-made This code is an implementation of "Masked AutoEncoder for Density Estimation" by Germain et al., 2015. The core idea is that you can turn

Andrej 498 Dec 30, 2022
This repo includes the CUB-GHA (Gaze-based Human Attention) dataset and code of the paper "Human Attention in Fine-grained Classification".

HA-in-Fine-Grained-Classification This repo includes the CUB-GHA (Gaze-based Human Attention) dataset and code of the paper "Human Attention in Fine-g

16 Oct 29, 2022
Training neural models with structured signals.

Neural Structured Learning in TensorFlow Neural Structured Learning (NSL) is a new learning paradigm to train neural networks by leveraging structured

955 Jan 02, 2023
SelfAugment extends MoCo to include automatic unsupervised augmentation selection.

SelfAugment extends MoCo to include automatic unsupervised augmentation selection. In addition, we've included the ability to pretrain on several new datasets and included a wandb integration.

Colorado Reed 24 Oct 26, 2022
Py-faster-rcnn - Faster R-CNN (Python implementation)

py-faster-rcnn has been deprecated. Please see Detectron, which includes an implementation of Mask R-CNN. Disclaimer The official Faster R-CNN code (w

Ross Girshick 7.8k Jan 03, 2023
Dilated RNNs in pytorch

PyTorch Dilated Recurrent Neural Networks PyTorch implementation of Dilated Recurrent Neural Networks (DilatedRNN). Getting Started Installation: $ pi

Zalando Research 200 Nov 17, 2022
Jaxtorch (a jax nn library)

Jaxtorch (a jax nn library) This is my jax based nn library. I created this because I was annoyed by the complexity and 'magic'-ness of the popular ja

nshepperd 17 Dec 08, 2022
Pytorch implementation of PCT: Point Cloud Transformer

PCT: Point Cloud Transformer This is a Pytorch implementation of PCT: Point Cloud Transformer.

Yi_Zhang 265 Dec 22, 2022
A scikit-learn compatible neural network library that wraps PyTorch

A scikit-learn compatible neural network library that wraps PyTorch. Resources Documentation Source Code Examples To see more elaborate examples, look

4.9k Dec 31, 2022
4th place solution for the SIGIR 2021 challenge.

SIGIR-2021 (Tinkoff.AI) How to start Download train and test data: https://sigir-ecom.github.io/data-task.html Place it under sigir-2021/data/. Run py

Tinkoff.AI 4 Jul 01, 2022
Linear algebra python - Number of operations and problems in Linear Algebra and Numerical Linear Algebra

Linear algebra in python Number of operations and problems in Linear Algebra and

Alireza 5 Oct 09, 2022
A custom DeepStack model that has been trained detecting ONLY the USPS logo

This repository provides a custom DeepStack model that has been trained detecting ONLY the USPS logo. This was created after I discovered that the Deepstack OpenLogo custom model I was using did not

Stephen Stratoti 9 Dec 27, 2022
Tensorflow implementation of Semi-supervised Sequence Learning (https://arxiv.org/abs/1511.01432)

Transfer Learning for Text Classification with Tensorflow Tensorflow implementation of Semi-supervised Sequence Learning(https://arxiv.org/abs/1511.01

DONGJUN LEE 82 Oct 22, 2022
PyTorch code for SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised DA

PyTorch Code for SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation Viraj Prabhu, Shivam Khare, Deeks

Viraj Prabhu 46 Dec 24, 2022
Colab notebook for openai/glide-text2im.

GLIDE text2im on Colab This repository provides a Colab notebook to produce images conditioned on text prompts with GLIDE [1]. Usage Run text2im.ipynb

Wok 19 Oct 19, 2022
Pre-training of Graph Augmented Transformers for Medication Recommendation

G-Bert Pre-training of Graph Augmented Transformers for Medication Recommendation Intro G-Bert combined the power of Graph Neural Networks and BERT (B

101 Dec 27, 2022
Motion and Shape Capture from Sparse Markers

MoSh++ This repository contains the official chumpy implementation of mocap body solver used for AMASS: AMASS: Archive of Motion Capture as Surface Sh

Nima Ghorbani 135 Dec 23, 2022
Locally Enhanced Self-Attention: Rethinking Self-Attention as Local and Context Terms

LESA Introduction This repository contains the official implementation of Locally Enhanced Self-Attention: Rethinking Self-Attention as Local and Cont

Chenglin Yang 20 Dec 31, 2021
Config files for my GitHub profile.

Canalyst Candas Data Science Library Name Canalyst Candas Description Built by a former PM / analyst to give anyone with a little bit of Python knowle

Canalyst Candas 13 Jun 24, 2022