Using the framework of quotient image model, this paper presented a median filtering-based method (MFQI) for the illumination normalization of facial images. The proposed method first uses adaptive median filtering to derive an estimation of the received light, and then uses the quotient image model for local illumination normalization. Compared with the other quotient image methods, MFQI does not require any assumptions on lighting conditions and shadows, and is easy to be implemented. Experimental results indicate that the proposed method is effective in face recognition with varying lighting conditions, and can achieve high recognition accuracy using the Yale face database B.

The median filtering-based method (MFQI) effectively normalizes facial images for face recognition with varying lighting conditions, achieving high recognition accuracy using the Yale face database B.

Median Filtering-Based Quotient Image Model for Face Recognition with Varying Lighting Conditions

Key Takeaway: The median filtering-based method (MFQI) effectively normalizes facial images for face recognition with varying lighting conditions, achieving high recognition accuracy using the Yale face database B.