Build Instructions

Collapse

• 1

  Setting up the Raspberry Pi

  Prepare your Raspberry Pi with latest Raspbian operating system and get ready to do some programming. If you are new in Raspberry Pi read this how to get started using Raspberry Pi guide. You can plug a mouse, keyboard, and monitor into your Pi or access it using SSH client like PuTTY. To know how to connect with PuTTY you may read this tutorial.

  Install python serial module using the command:

  sudo apt-get install python-serial
  

  Install AWS IoT SDK using following command:

  sudo pip install AWSIoTPythonSDK
  

  Details of AWSToTPythonSDK is here.

• 2

  Installing & Configuring AWS CLI

  The AWS Command Line Interface (CLI) is a unified tool that allows you to control AWS services from the command line. AWS CLI helps you creating an AWS object from the command line without using a GUI interface. If you already have pip and a supported version of Python (integrated with latest Raspbian OS), you can install the AWS CLI with the following command:

  pip install awscli --upgrade --user
  

  You need to configure AWS CLI with Access Key ID, Secret Access Key, AWS Region Name and Command Output format before getting started with it.

  Follow this tutorial for completing the whole process.

• 3

  Setting up Amazon S3 Bucket, Amazon Rekognition and Amazon DynamoDB

  Amazon Rekognition is a sophisticated deep learning-based service from Amazon Web Services (AWS) that makes it easy to add powerful visual search and discovery to your own applications. With Rekognition using simple APIs, you can quickly detect objects, scenes, faces, celebrities, and inappropriate content within images. Amazon Rekognition also provides highly accurate facial analysis and facial recognition. You can detect, analyze, and compare faces for a wide variety of user verification, cataloging, people counting, and public safety use cases.

  Amazon Rekognition is based on the same proven, highly scalable, deep learning technology developed by Amazon’s computer vision scientists to analyze billions of images and videos daily, and requires no machine learning expertise to use. Amazon Rekognition is a simple and easy-to-use API that can quickly analyze any image or video file stored in Amazon S3.

  Amazon Rekognition can store information about detected faces in server-side containers known as collections. You can use the facial information stored in a collection to search for known faces in images, stored videos, and streaming videos. Amazon Rekognition supports the IndexFaces operation, which you can use to detect faces in an image and persist information about facial features detected into a collection.

  The face collection is the primary Amazon Rekognition resource, each face collection you create has a unique Amazon Resource Name (ARN). You create each face collection in a specific AWS Region in your account.

  We start by creating a collection within Amazon Rekognition. A collection is a container for persisting faces detected by the IndexFaces API. You might choose to create one container to store all faces or create multiple containers to store faces in groups. You can use AWS CLI to create a collection or use the console. For AWS CLI, you can use the following command:

  aws rekognition create-collection --collection-id guest_collection --region eu-west-1
  

  The above command creates a collection named guest_collection.

  The user or role that executes the commands must have permissions in AWS Identity and Access Management (IAM) to perform those actions. AWS provides a set of managed policies that help you get started quickly. For our example, you need to apply the following minimum managed policies to your user or role:

  • AmazonRekognitionFullAccess

  • AmazonDynamoDBFullAccess

  • AmazonS3FullAccess

  • IAMFullAccess

  Next, we create an Amazon DynamoDB table. DynamoDB is a fully managed cloud database that supports both document and key-value store models. In our example, we’ll create a DynamoDB table and use it as a simple key-value store to maintain a reference of the FaceId returned from Amazon Rekognition and the full name of the person.

  You can use either the AWS Management Console, the API, or the AWS CLI to create the table. For the AWS CLI, use the following command:

  aws dynamodb create-table --table-name guest_collection \
  --attribute-definitions AttributeName=RekognitionId,AttributeType=S \
  --key-schema AttributeName=RekognitionId,KeyType=HASH \
  --provisioned-throughput ReadCapacityUnits=1,WriteCapacityUnits=1 \
  --region eu-west-1
  

  For the IndexFaces operation, you can provide the images as bytes or make them available to Amazon Rekognition inside an Amazon S3 bucket. In our example, we upload the images (images of the known guest) to an Amazon S3 bucket.

  Again, you can create a bucket either from the AWS Management Console or from the AWS CLI. Use the following command:

  aws s3 mb s3://guest-images --region eu-west-1
  

  Although all the preparation steps were performed from the AWS CLI, we need to create an IAM role that grants our function the rights to access the objects from Amazon S3, initiates the IndexFaces function of Amazon Rekognition, and create multiple entries within our Amazon DynamoDB key-value store for a mapping between the face and the person’s full name.

  To get the access use the file: access-policy.json

  { 
      "Version": "2012-10-17", 
      "Statement": [ 
          {
               "Effect": "Allow",
               "Action": [ 
                  "logs:CreateLogGroup", 
                  "logs:CreateLogStream", 
                  "logs:PutLogEvents" 
                  ], 
                  "Resource": "arn:aws:logs:*:*:*"
           }, 
           {
               "Effect": "Allow", 
               "Action": [ 
                  "s3:GetObject"
                   ], 
                  "Resource": [
                       "arn:aws:s3:::bucket-name/*" 
                        ]
            }, 
            { 
              "Effect": "Allow", 
              "Action": [
                   "dynamodb:PutItem" 
              ], 
              "Resource": [ 
                  "arn:aws:dynamodb:aws-region:account-id:table/family_collection"
              ] 
            }, 
            { 
              "Effect": "Allow", 
              "Action": [ 
                  "rekognition:IndexFaces"
               ],
              "Resource": "*"
                   }
               ]
          }
  

  For the access policy, ensure you replace aws-region, account-id, and the actual name of the resources (e.g., bucket-name and family_collection) with the name of the resources in your environment.

  Now, attach the access policy to the role using the following command.

  aws iam put-role-policy --role-name LambdaRekognitionRole --policy-name \ LambdaPermissions --policy-document file://access-policy.json
  

  We can almost configure our AWS environment. We can now upload our images to Amazon S3 to seed the face collection. For this example, we again use a small piece of Python code that iterates through a list of items that contain the file location and the name of the person within the image.

  Before running the code you need to install Boto3. Boto3 is the Amazon Web Services (AWS) Software Development Kit (SDK) for Python, which allows Python developers to write software that makes use of services like Amazon S3 and Amazon EC2. You can find the latest, most up to date, documentation at Read the Docs, including a list of services that are supported.

  Install the Boto3 library using the following command:

  sudo pip install boto3
  

  Now, run the following python code to upload the images into S3 Bucket. Before running the code be sure that you keep all the images and the python file in the same directory.

  import boto3
  s3 = boto3.resource('s3')
  # Get list of objects for indexing
  images=[('afridi.jpg','Shahid Afridi'),
         ('sakib.jpg','Sakib Al Hasan'),
         ('kohli.jpg','Birat Kohli'),
         ('masrafi.jpg','Mashrafe Bin Mortaza'),
         ('ganguli.jpg','Sourav Ganguly')
        ]
  # Iterate through list to upload objects to S3   
  for image in images:
     file = open(image[0],'rb')
     object = s3.Object('taifur12345bucket',image[0])
     ret = object.put(Body=file,
                     Metadata={'FullName':image[1]}
                     )
  #print(image[0])
  #print(image[1])
  

  Now, add the Face Index to AWS DynamoDB with full name for every image using the following python code.

  import boto3
  from decimal import Decimal
  import json
  import urllib
  BUCKET = "taifur12345bucket"
  KEY = "sample.jpg"
  IMAGE_ID = KEY  # S3 key as ImageId
  COLLECTION = "family_collection"
  dynamodb = boto3.client('dynamodb', "eu-west-1")
  s3 = boto3.client('s3')
  # Note: you have to create the collection first!
  # rekognition.create_collection(CollectionId=COLLECTION)
  def update_index(tableName,faceId, fullName):
      response = dynamodb.put_item(
      TableName=tableName,
      Item={
          'RekognitionId': {'S': faceId},
          'FullName': {'S': fullName}
          }
      )
      #print(response)
  def index_faces(bucket, key, collection_id, image_id=None, attributes=(), region="eu-west-1"):
      rekognition = boto3.client("rekognition", region)
      response = rekognition.index_faces(
          Image={
              "S3Object": {
                  "Bucket": bucket,
                  "Name": key,
              }
          },
          CollectionId=collection_id,
          ExternalImageId="taifur",
          DetectionAttributes=attributes,
      )
      if response['ResponseMetadata']['HTTPStatusCode'] == 200:
          faceId = response['FaceRecords'][0]['Face']['FaceId']
          print(faceId)
          ret = s3.head_object(Bucket=bucket,Key=key)
          personFullName = ret['Metadata']['fullname']
          #print(ret)
          print(personFullName)
          update_index('taifur12345table',faceId,personFullName)
      # Print response to console.
      #print(response)
      return response['FaceRecords']
  for record in index_faces(BUCKET, KEY, COLLECTION, IMAGE_ID):
      face = record['Face']
      # details = record['FaceDetail']
      print "Face ({}%)".format(face['Confidence'])
      print "  FaceId: {}".format(face['FaceId'])
      print "  ImageId: {}".format(face['ImageId'])
  

  Once the collection is populated, we can query it by passing in other images that contain faces. Using the SearchFacesByImage API, you need to provide at least two parameters: the name of the collection to query, and the reference to the image to analyze. You can provide a reference to the Amazon S3 bucket name and object key of the image, or provide the image itself as a byte stream.

  In the following example, I used the following code in the Lambda function to search face by taking the image from S3 Bucket. In response, Amazon Rekognition returns a JSON object containing the FaceIds of the matches. Using the face ID retrieves the full name.

View all 7 instructions