SUPER-RESOLUTION AND DENOISE USING ARTIFICIAL INTELLIGENCE FOR IMAGE ENHANCEMENT IN FINGERPRINT RECOGNITION

  • Doãn Thanh Bình
Keywords: Fingerprint recognition, super-resolution and denoising.

Abstract

This paper presents a super-resolution and denoising solution using artificial
intelligence to solve the problem of improving the quality of input fingerprint
images for fingerprint recognition systems. Super resolution and image noise
reduction are two important tasks in image processing to improve image quality.
Image Super-Resolution is mapping a low-resolution image to a high-resolution
image while denoising takes care of restoring from noisy input images. By
analyzing and calculating the experimental image quality parameters, we will
prove that the proposed method is superior to some existing methods such as
Curvelet transform, discrete wavelet transform (DWT), very deep hyperresolution (VDSR), hyper-resolution convolution neural network (SRCNN).

điểm /   đánh giá
Published
2021-10-15
Section
RESEARCH AND DEVELOPMENT