Master's project · 2019

ATM identity validation with face recognition

A cross-platform academic prototype exploring face recognition as a secondary identity-validation layer for ATMs.

01 · Context

The problem

Card-and-PIN authentication can benefit from an additional, non-contact identity signal when security risk is high.

02 · Role

Responsibility and scope

Designed, implemented, tested, and documented the prototype as the author of a California State University, Dominguez Hills master's project.

03 · Decision logic

Combined Haar Cascade face detection with Local Binary Pattern recognition, persistent training data, motion detection, and a desktop application workflow.

01Live image
02Face detection
03Pre-processing
04LBP recognition
05Identity match
JavaJavaCV / OpenCVHaar CascadeLocal Binary PatternRelational database

04 · Outcome

What changed

The project report states a recognition rate above 90% under its selected testing strategy; it recommends future work on speed and recognition performance.

05 · Learning

Lessons and next iteration

Biometric systems require careful attention to testing conditions, failure handling, privacy, and layered authentication—not accuracy alone.