What this shows: Identity verification concept that matches a live face against the authenticated photo from an electronic identity document chip.
My role / team role: Prepared the verification workflow, biometric/KYC positioning, architecture documentation, and showcase material for technical review.
Public proof: Architecture and README explain the chip-level identity workflow, verification use case, and implementation boundaries.
Tech and implementation areas:
- Face recognition
- eMRTD/e-passport workflow
- KYC verification
- Python backend concepts
- Secure verification architecture
Relevant roles this project supports:
- Computer Vision Developer
- KYC/Identity Verification Engineer
- AI Product Engineer
- Backend Automation Developer
This is a public case-study repository. The production source code is private because it may contain proprietary business logic, client workflows, credentials, deployment details, or reusable internal implementation patterns. The public repo is intentionally focused on the product, screenshots, workflow, architecture, and evaluation material.
For technical review, we can provide a live demo walkthrough, private repository access under NDA, a code screen-share, architecture review, or redacted implementation samples.
Prove a person is who their ID card says they are — verified against the card's own chip, not a printed photo.
AuthentID is an identity-verification system that reads the cardholder's authentic facial image directly from the secure chip of an electronic ID card (the ICAO 9303 eMRTD applet), cryptographically proves the chip and its data are genuine, and matches that trusted photo against a live camera feed.
flowchart LR
A[Electronic ID card<br/>inserted in reader] --> B[Establish secure channel<br/>BAC session keys]
B --> C[Read chip data files<br/>MRZ, facial image, security objects]
C --> D{Cryptographic checks}
D -->|Passive Authentication| E[Data signed by a<br/>trusted national authority]
D -->|Chip / Active Authentication| F[Chip is genuine,<br/>not a clone]
E --> G[Trusted reference photo<br/>extracted from chip]
F --> G
H[Live camera feed] --> I[Face detection +<br/>128-d face encoding]
G --> J[Compare faces<br/>euclidean distance]
I --> J
J --> K[Match / No-match<br/>+ confidence score]
The reference photo is never trusted blindly: it is only used after the chip and the data on it pass cryptographic verification against a store of trusted national signing certificates.
It is a chip-level identity-verification platform for electronic ID documents. Instead of comparing a face to a printed photo (which can be swapped, reprinted, or tampered with), AuthentID compares the face to the photo stored inside the document's tamper-resistant chip — and verifies that chip is authentic before trusting it.
It is built for organisations that must be certain an ID document is real and belongs to the person presenting it — onboarding, access control, regulated check-in, and identity desks.
- Chip-sourced reference photo — the comparison image comes from the eMRTD chip, not the printed card surface.
- Passive Authentication — verifies the chip's data was signed by a legitimate national document-signing authority.
- Chip & Active Authentication — proves the chip itself is genuine and has not been cloned.
- Secure messaging (BAC) — all communication with the chip runs over an encrypted, MAC-protected channel.
- Live face matching — deep-learning face detection plus a 128-dimension face-recognition model.
- Confidence scoring — every comparison returns a similarity score, not just a yes/no.
- Document expiry & integrity checks — flags expired documents and data-group mismatches.
- Standards-based — built around the ICAO 9303 eMRTD specification used by e-passports and modern eID cards.
| Audience | Why it helps |
|---|---|
| Banks & financial services | KYC onboarding that resists printed-photo fraud. |
| Border, travel & hospitality desks | Confirm a traveller matches their genuine document. |
| Telecom & regulated sign-up | Meet identity-assurance requirements at registration. |
| Secure facilities & access control | Tie physical access to a verified, genuine ID. |
| Government & public services | High-assurance identity checks at service counters. |
- Insert the card — the cardholder places their electronic ID card in a contact smart-card reader.
- Open a secure channel — AuthentID derives session keys and talks to the chip over encrypted secure messaging.
- Read the chip — it retrieves the data files: the machine-readable zone, the facial image, and the security objects.
- Verify authenticity — cryptographic checks confirm the data was signed by a trusted authority and the chip is genuine.
- Extract the trusted photo — only verified data is used; the authentic facial image is taken from the chip.
- Match against the camera — faces in the live camera feed are compared to the trusted photo, with a confidence score shown for each.
- Document layer: ICAO 9303 eMRTD — BAC secure messaging, Passive / Chip / Active Authentication
- Smart-card I/O: PC/SC contact reader communication
- Face detection: deep-learning SSD detector
- Face recognition: 128-dimension deep-metric face encoding with euclidean-distance matching
- Cryptography: national CSCA / document-signer certificate validation, CRL checks
- Platform: Python application, cross-platform camera capture
This repository is a public showcase. It documents the product — it does not contain the chip-communication code, the authentication logic, the certificate-validation pipeline, or any source code.
How is this different from normal face-match ID checks? Most systems compare a face to the printed photo on a card. AuthentID compares it to the photo stored in the card's secure chip — and cryptographically verifies that chip is genuine first.
What documents does it work with? Electronic ID cards and travel documents that implement the ICAO 9303 eMRTD chip standard (the same standard used by modern e-passports).
Does it need an internet connection? The core verification runs locally against a bundled store of trusted signing certificates.
What stops someone using a cloned or fake chip? Chip Authentication and Active Authentication cryptographically prove the chip is the genuine original and has not been copied.
What does the confidence score mean? It is the similarity between the live face and the chip photo — a higher score means a closer match.
Is this open source? No. This repository is a marketing showcase. The product is proprietary — see the license.
How do I get access or a demo? See the Contact & Demo section below.
- 🔐 Chip-level trust — verifies the document, not just the face.
- 🧾 Standards-based — built on the ICAO 9303 eMRTD specification.
- 🧠 Modern face recognition — deep-learning detection and encoding.
- 📊 Explainable — every check and every match comes with a clear result and score.
Built by Advenno — Full-Stack Brand Building. Get in touch with the development team.
| Developer | ||
|---|---|---|
| Muhammad Maaz | mazwaseem098@gmail.com | +92 323 7609712 |
| Muhammad Tanveer | mtanveertahir66@gmail.com | +92 320 6688665 |
- Company: Advenno
- Email: hello@advenno.com
- GitHub: @maaz-gobi
Need high-assurance identity verification built on real document security? Get in touch to discuss your use case.
This is a proprietary product by Advenno. This repository contains documentation and marketing materials only. See LICENSE for terms.
Keywords: eMRTD verification, ICAO 9303, electronic ID card, e-passport chip, biometric facial verification, face match, identity verification, KYC, chip authentication, passive authentication, active authentication, BAC secure messaging, NFC ID verification, document authenticity, anti-spoofing identity, face recognition, smart card identity, AuthentID, Advenno.