> For the complete documentation index, see [llms.txt](https://docs.digit.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.digit.org/health/access/public-health-product-suite/health-campaign-management-hcm/facial-recognition.md). # Facial Recognition ## Overview Face ID Attendance replaces manual attendance marking with a biometric check-in. Instead of signing a register, a field worker scans their face on the mobile app. Every scan creates an attendance event that carries a timestamp, GPS coordinates, and a face match confidence score, so attendance can be verified after the fact rather than taken on trust. This release is a pilot. The Facial Recognition APK runs alongside the standard Digit app on the same backend. Pilot users receive the Facial Recognition APK; everyone else continues on the standard APK. No separate console setup is required. This manual is organised by task. Find the task you need below and go directly to that section. You do not need to read the whole document. ## Key features * Face enrollment with six guided angle captures and a liveness check, for both system users and helpers * Morning face scan login that creates an attendance event with timestamp, GPS, and confidence score * A four-digit backup PIN, issued automatically at the end of enrollment, for use when face verification will not pass * Multi-user support on one device: one system user is mapped to the device, and up to two helpers on the same team can be enrolled and verified on it * Random re-verification prompts during the day, shown as a non-blocking ticker that does not interrupt registration or delivery * Full offline operation: enrollment records and attendance events are stored on the device and sync automatically when the device reconnects * Verification History on the device, showing every enrollment and every verification with match score, time, and GPS * Supervisor view of anomaly flags, including missed re-verification windows ## User Roles

Role	What they do
Distributor(system user)	Enrols their own face, checks in daily by face scan, responds to re-verification prompts, and enrols helpers on their device.
Helper(non-system user)	Does not log in to the app. Is enrolled and verified by the Distributor on the Distributor’s device.
Team Supervisor	Reviews attendance and verification records. Note: In this release, the re-verification prompt is only intended for the Distributor role.
Attendance Supervisor	Reviews attendance records and anomaly flags, including missed re-verification windows, and manages duplicate enrollment by SOP.

{% hint style="info" %} **Before you begin:** Your first face enrolment requires an active internet connection. Everything after enrollment, including login and re-verification, works offline. Use your existing HCM campaign credentials. No new account is created for Facial Recognition. Location must be enabled on the device. Every enrollment and verification captures GPS coordinates. Find a spot with even light, remove glasses and anything covering your face, and hold the phone 30–40 cm away. {% endhint %} ### Overview: how Face ID attendance works A face scan happens at four moments. Understanding the sequence makes the rest of the manual easier to follow.

Stage	When it happens	What the system records
Enrolment	Once, the first time you open the app. Requires internet.	Six-angle capture plus a liveness check. The profile is stored on the device and synced to the backend. A four-digit backup PIN is generated.
Login check-in	Every morning, when you open the app.	An attendance event with timestamp, GPS coordinates, and the face match confidence score. Up to three attempts before the PIN fallback is offered.
Re-verification	At random points during the day, shown as a ticker.	A verification event, or a missed-window log entry if the countdown expires without a scan.
Helper verification	When the Distributor verifies a helper on their device.	A verification event tied to the helper’s user ID, stored under the Distributor’s device and profile.

{% hint style="info" %} **Key dependency:** The system user must verify their own face before any helper on that device can be verified. If the Distributor has not completed their scan, the helper’s Verify Face action will not proceed. {% endhint %} ### Role Mapping

Term	Description
System user	A worker with their own HCM login, mapped to the device. In this pilot, the Distributor role. Enrols their own face and can enrol helpers.
Non-system user (Helper)	A team member without an HCM login is listed under non-mobile users on the Distributor’s device. Up to two per device. Each gets their own face profile linked to their own user ID.

--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.digit.org/health/access/public-health-product-suite/health-campaign-management-hcm/facial-recognition.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.