Performing 1:1 Face Match with Didit's JS SDK

Seamless IntegrationIntegrate Didit's 1:1 Face Match into your web applications using the intuitive JavaScript SDK, enabling quick and secure biometric verification workflows.

Robust Fraud PreventionLeverage AI-powered facial recognition, combined with passive and active liveness detection, to accurately compare a user's live selfie against their ID document photo, effectively deterring identity fraud.

Configurable WorkflowsCustomize verification thresholds for face match scores, allowing you to define when a session requires review or automatic decline, tailoring the process to your specific risk appetite.

Didit's AdvantageDidit provides an AI-native, modular identity platform with Free Core KYC, no setup fees, and clean APIs, making advanced biometric verification accessible and scalable for businesses of all sizes.

In today's digital landscape, verifying a user's identity is paramount for security, compliance, and building trust. One of the most effective methods is 1:1 Face Match, which compares a user's live biometric data (usually a selfie) against a trusted source, such as their identity document photo. Didit offers a cutting-edge, AI-native solution for this, and integrating it into your web applications is streamlined with the Didit JavaScript (JS) SDK.

Understanding 1:1 Face Match Verification

Didit's 1:1 Face Match is a critical component of robust identity verification, designed to ensure that the person presenting an identity document is indeed its legitimate owner. This process involves two primary steps:

1. Liveness Detection: Before any comparison, Didit employs both Passive & Active Liveness checks. This step is crucial for fraud prevention, as it verifies that a real, live person is present and not a deepfake, photo, or video spoof attempting to bypass the system.
2. Facial Comparison: Once liveness is confirmed, the system extracts the portrait from the user's ID document (using Didit's ID Verification capabilities like OCR, MRZ, and barcode scanning) and compares it against the live selfie. This comparison generates a similarity score, indicating the likelihood that the two faces belong to the same individual.

The result is a comprehensive report that includes the face match score, status (Approved, Rejected, In Review), and any relevant warnings. This ensures a high level of assurance that the person engaging with your service is who they claim to be.

Integrating Face Match with the Didit JS SDK

Integrating Didit's 1:1 Face Match into your web application is straightforward thanks to the developer-first approach and clean APIs offered by the Didit JS SDK. The SDK simplifies the process of capturing user biometrics, sending them to Didit's backend, and receiving verification results.

The core process typically involves:

1. Initializing the SDK: Set up the Didit SDK in your application, providing necessary API keys and configuration.
2. Capturing Biometrics: The SDK provides components or functions to guide users through the liveness detection and selfie capture process. This can include active challenges (e.g., head turns) or passive analysis, depending on your configured liveness method.
3. Submitting for Verification: The captured data is securely transmitted to Didit's platform.
4. Receiving Results: Your application receives a detailed response, including the face_match object, which contains the verification status, similarity score, and any warnings.

Didit's modular architecture means you can integrate Face Match as a standalone component or as part of a broader orchestrated workflow that includes ID Verification, AML Screening, and other checks.

Understanding Face Match Report and Warnings

The face_match object within the API response provides crucial details for decision-making. Key fields include:

• status: Indicates 'Approved', 'Rejected', 'In Review', or 'Not Finished'.
• score: A numerical value (0-100) representing the similarity between the two faces.
• source_image and target_image: Temporary URLs to the images used for comparison, expiring after 60 minutes for enhanced security.
• warnings: An array of objects detailing any issues encountered during the process.

Warnings are particularly important for understanding potential risks. For example, a LOW_FACE_MATCH_SIMILARITY warning indicates that the facial features do not closely match, suggesting a possible identity mismatch. Another critical warning is NO_REFERENCE_IMAGE, which means a comparison image was missing, preventing the face match from completing.

Didit allows you to configure thresholds for these warnings. You can set a 'Review threshold' where sessions with scores below this mark are flagged for manual review, and a 'Decline threshold' for automatic rejection. This level of control empowers businesses to balance user experience with their specific risk tolerance.

Security and Best Practices

When working with biometric data, security is paramount. Didit adheres to stringent security protocols, ensuring that temporary URLs for images expire quickly. As a best practice, your application should only store the verification status and similarity score, minimizing the retention of sensitive biometric data on your servers. This approach aligns with privacy regulations and reduces your data footprint.

By leveraging Didit's secure infrastructure and following recommended practices, you can deploy a highly secure and compliant identity verification system.

How Didit Helps

Didit is the AI-native, developer-first identity platform that makes advanced face matching accessible and robust. Our 1:1 Face Match and Passive & Active Liveness products are powered by cutting-edge AI and computer vision, ensuring fast, accurate, and secure identity verification. Didit's modular architecture allows you to easily plug-and-play our identity checks, including ID Verification and Face Match & Face Search, into your existing workflows via clean APIs or our no-code Business Console.

We stand out by offering Free Core KYC, meaning you can start verifying identities without upfront costs. There are no setup fees, and our pay-per-successful-check model ensures you only pay for what you use. Didit's comprehensive Biometric Authentication combines liveness detection and face matching into a single, seamless flow, providing a complete picture of the user's authentication attempt and significantly combating fraud. With Didit, you gain an open, modular, and globally designed identity solution that automates trust and scales with your business needs.

Ready to Get Started?

Ready to see Didit in action? Get a free demo today.

Start verifying identities for free with Didit's free tier.