Human eyebrow recognition in the matching-recognizing framework

This paper studies the problem of automatically recognizing human eyebrows using a frontal view. In the matching-recognizing framework for image-based object classification, we design an automatic human eyebrow recognition system via fast template matching and Fourier spectrum distance. Fast template matching is used to locate the target subregion of a gallery template or a pure eyebrow image in a probe original eyebrow image, whereas Fourier spectrum distance is used to determine the final identity of the probe original eyebrow image. We conducted a number of experiments to demonstrate the efficacy of the proposed system and corroborate the validity of eyebrow recognition on the BJUT eyebrow database. Moreover, we also tested the system on the color FERET database. Experimental results show that our approach can be directly applied to face recognition by only replacing eyebrow templates with face templates, and may achieve higher accuracy in eyebrow recognition than in small face recognition. This is a strong argument for eyebrow recognition to replace face recognition as an independent biometric in certain scenarios, especially where relatively large eyebrows can be cropped.