Sweat Gland Enhancement Method for Fingertip OCT Images Based on Generative Adversarial Network

Abstract

Sweat pores are gaining recognition as a secure, reliable, and identifiable third-level fingerprint feature. Challenges arise in collecting sweat pores when fingers are contaminated, dry, or damaged, leading to unclear or vanished surface sweat pores. Optical Coherence Tomography (OCT) has been applied in the collection of fingertip biometric features. The sweat pores mapped from the subcutaneous sweat glands collected by OCT possess higher security and stability. However, speckle noise in OCT images can blur sweat glands making segmentation and extraction difficult. Traditional denoising methods cause unclear sweat gland contours and structural loss due to smearing and excessive smoothing. Deep learning-based methods have not achieved good results due to the lack of clean images as ground-truth. This paper proposes a sweat gland enhancement method for fingertip OCT images based on Generative Adversarial Network (GAN). It can effectively remove speckle noise while eliminating irrelevant structures and repairing the lost structure of sweat glands, ultimately improving the accuracy of sweat gland segmentation and extraction. To the best knowledge, it is the first time that sweat gland enhancement is investigated and proposed. In this method, a paired dataset generation strategy is proposed, which can extend few manually enhanced ground-truth into a high-quality paired dataset. An improved Pix2Pix for sweat gland enhancement is proposed, with the addition of a perceptual loss to mitigate structural distortions during the image translation process. It’s worth noting that after obtaining the paired dataset, any advanced supervised image-to-image translation network can be adapted into our framework for enhancement. Experiments are carried out to verify the effectiveness of the proposed method.