Abstract
Correlation filters have been applied successfully in pattern matching needed in face verification. In this paper, we propose a face verification technique based on half the lower face using the minimum average correlation energy (MACE) filter which has the ability to satisfy the correlation peak at the origin, and minimise the average correlation energy. Our experiments show that the application of the MACE filter for face verification using the lower‐left or ‐right parts of the face generates authentication with at least 80% accuracy. Authentication accuracy using the MACE filter based on the whole face increases to at least 88%, but requires approximately twice as much response time.