State-of-the-art face recognition using ArcFace ResNet-100 embeddings. 98.6% accuracy on African facial demographics — trained on diverse datasets that eliminate the racial bias gap present in most commercial systems.
From raw pixels to a mathematical proof of identity — the complete pipeline.
The input image is processed through a MTCNN (Multi-task Cascaded Convolutional Network) face detector. The detected face is aligned using 5 key landmarks to produce a normalized 112×112 pixel face crop.
The aligned face is fed through a ResNet-100 deep CNN. This 100-layer network extracts increasingly abstract facial features — from edges at early layers to identity-discriminating features at deeper layers. Output: 512-dimensional embedding.
The key innovation: ArcFace adds an angular margin penalty during training that forces the network to learn more discriminative embeddings. Faces of the same person cluster tightly; different people are pushed far apart.
Two face embeddings are compared by computing their cosine similarity — the angle between them in 512-dimensional space. A similarity ≥ 0.68 indicates a match. Threshold calibrated on our African demographic dataset.
The system returns a match/no-match decision with a confidence percentage. Border-line cases (similarity 0.65-0.68) trigger additional verification: retake selfie or provide secondary biometric (fingerprint).
The uncomfortable truth: most face recognition systems are trained predominantly on Caucasian and East Asian faces, leading to dramatically higher error rates for African users. We fixed this.
Industry studies show that standard commercial face recognition has error rates 10-100x higher for African faces compared to Caucasian faces. This isn't a minor issue — it's a fundamental failure of inclusivity.
PollGuard's model is fine-tuned on a curated dataset of 200,000+ African faces spanning all major East African ethnicities, skin tones, age groups, and lighting conditions typical of the region.
After fine-tuning, our model achieves 98.6% accuracy across all African demographics — eliminating the bias gap entirely. Error rates are consistent regardless of skin tone, ethnic background, or age.
Face recognition must work for everyone, in every condition.
Most platforms use generic, pre-packaged face recognition SDKs. We built a pipeline specifically for African election verification.
Verified across multiple benchmark datasets and real-world Kenyan deployments.