Unsharp masking using quadratic filter for the enhancement of fingerprints in noisy background

• We designed and implemented a quadratic filter for enhancing noisy fingerprints.
• The filter is based on truncated Volterra series that can model polynomial nonlinearities.
• It is tested with fingerprints that are corrupted by Gaussian and impulsive noise of different variances.
• The performance parameters are observed to be better than conventional image filters.

The paper summarizes the design and implementation of a quadratic edge detection filter based on Volterra series. The filter is employed in an unsharp masking scheme for enhancing fingerprints in a dark and noisy background. The proposed filter can account for much of the polynomial nonlinearities inherent in the input image and can replace the conventional edge detectors like Laplacian, LoG, etc. The application of the new filter is in forensic investigation where enhancement and identification of latent fingerprints are key issues. The enhancement of images by the proposed method is superior to that with unsharp masking scheme employing conventional filters in terms of the visual quality, the noise performance and the computational complexity, making it an ideal candidate for latent fingerprint enhancement.