{"id":1425,"date":"2022-01-03T23:13:00","date_gmt":"2022-01-03T23:13:00","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2022\/01\/03\/identity-verification-using-amazon-rekognition\/"},"modified":"2022-01-03T23:13:00","modified_gmt":"2022-01-03T23:13:00","slug":"identity-verification-using-amazon-rekognition","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2022\/01\/03\/identity-verification-using-amazon-rekognition\/","title":{"rendered":"Identity verification using Amazon Rekognition"},"content":{"rendered":"
\n

In-person user identity verification is slow to scale, costly, and high friction for users. Machine learning (ML) powered facial recognition technology can enable online user identity verification. Amazon Rekognition<\/a> offers pre-trained facial recognition<\/a> capabilities that you can quickly add to your user onboarding and authentication workflows to verify opted-in users\u2019 identities online. No ML expertise is required. With Amazon Rekognition, you can onboard and authenticate users in seconds while detecting fraudulent or duplicate accounts. As a result, you can grow users faster, reduce fraud, and lower user verification costs.<\/p>\n

In this post, we describe a typical identity verification workflow and show how to build an identity verification solution using various Amazon Rekognition APIs. We provide a complete sample implementation in our GitHub repository<\/a>.<\/p>\n

User registration workflow<\/h2>\n

The following figure shows a sample workflow of a new user registration. Typical steps in this process are:<\/p>\n

    \n
  1. User captures selfie image and the image of a government-issued identity document.<\/li>\n
  2. Quality check of the selfie image and optional liveness detection<\/a> of the user face.<\/li>\n
  3. Comparison of the selfie image with the identity document face image.<\/li>\n
  4. Check of the selfie against a database of existing user faces.<\/li>\n<\/ol>\n

    \"\"<\/a><\/p>\n

    You can customize the flow according to the business process. It often contains some or all of the steps presented in the preceding diagram. You can choose to run all the steps synchronously (wait for one step to complete before moving on to the next step). Alternately, you can run some of the steps highlighted in orange asynchronously (don\u2019t wait for that step to complete) to speed up the user registration process and improve the customer experience. If the steps aren\u2019t successful, you must roll back the user registration.<\/p>\n

    In addition to new user registration, another common flow is an existing or returning user login. In this flow, a check of the user face (selfie) is performed against a previously registered face. Typical steps in this process include user face capture (selfie), check of the selfie image quality, and search and compare of the selfie against the faces database. The following diagram shows a possible flow.<\/p>\n

    \"\"<\/a><\/p>\n

    You can customize the steps of the process according to your business needs, and choose to include or exclude the liveness detection.<\/p>\n

    Solution overview<\/h2>\n

    The following reference architecture shows how you can use Amazon Rekognition, along with other AWS services, to implement identity verification.<\/p>\n

    \"\"<\/a><\/p>\n

    The architecture includes the following components:<\/p>\n

      \n
    1. Applications invoke Amazon API Gateway<\/a> to route requests to the correct AWS Lambda<\/a> function depending on the user flow. There are four major actions in this solution: authenticate, register, register with ID card, and update.<\/li>\n
    2. API Gateway uses a service integration to run the AWS Step Functions<\/a> express state machine corresponding to the specific path called from API Gateway. Within each step, Lambda functions are responsible for triggering the correct set of calls to and from Amazon DynamoDB<\/a> and Amazon Simple Storage Service<\/a> (Amazon S3), along with the relevant Amazon Rekognition APIs.<\/li>\n
    3. DynamoDB holds face IDs (face-id<\/code>), S3 path URIs, and unique IDs (for example employee ID number) for each face-id<\/code>. Amazon S3 stores all the face images.<\/li>\n
    4. The final major component of the solution is Amazon Rekognition. Each flow (authenticate, register, register with ID card, and update) calls different Amazon Rekognition APIs depending on the task.<\/li>\n<\/ol>\n

      Before we deploy the solution, it\u2019s important to know the following concepts and API descriptions:<\/p>\n