POSE-AWARE FACE SELECTION FOR IMPROVING FACE IDENTIFICATION RELIABILITY

Begmatov, Shohruh

Муҳандислик ва Иқтисодиёт · 2026-yil

Annotatsiya

Face identification systems are widely used in access control, attendance monitoring, surveillance, and human–computer interaction applications. Although modern FaceID systems based on deep facial embeddings achieve high recognitionaccuracy under controlled conditions, their reliability decreases when faces are captured at non-frontal angles.In real-world environments, camera position and person movement often cause significant yaw and pitch variations,reducing the visibility of facial landmarks and distorting the extracted facial features. This paper investigates the influenceof face pose angles on FaceID matching performance. The effect of yaw and pitch angles on facial embedding similaritywas experimentally evaluated using cosine distance as the matching metric. A pose-dependent score matrix was constructedto analyze how the matching score changes under different horizontal and vertical face orientations. Based onthe obtained results, a pose-aware face image selection algorithm was proposed. According to this algorithm, face imagesare accepted for identification when the horizontal angle between the camera and the human face is within 0°–57°, andthe vertical angle is within −56.25° to +56.25°. The experimental results showed that excluding highly deviated faceimages before identification improves the reliability of the FaceID system. The proposed pose-aware filtering approachreduced false identification cases by an average of 22%. These results confirm that face pose control is an importantpreprocessing stage for improving the practical reliability of FaceID systems in real-world camera-based applications

Maqola ma’lumotlari
MualliflarBegmatov, Shohruh
JurnalМуҳандислик ва Иқтисодиёт
Nashr sanasi2026-06-01
Jild4
Son6
TilIngliz

Kalit so‘zlar

Face identification; FaceID; face pose; yaw angle; pitch angle; cosine distance; facial embedding; poseaware filtering; biometric recognition

Ilmiy soha

Муҳандислик ва Иқтисодиёт jurnalidan boshqa maqolalar

Муҳандислик ва Иқтисодиёт — barcha maqolalar