Efficient hardware implementation of the Richardson-Lucy algorithm for restoring motion-blurred image on reconfigurable digital system

Carregando...
Imagem de Miniatura

Data

Título da Revista

ISSN da Revista

Título de Volume

Editor

Universidade Federal de Minas Gerais

Descrição

Tipo

Artigo de evento

Título alternativo

Primeiro orientador

Membros da banca

Resumo

This work presents the hardware implementation of the RLA (Richardson-Lucy Algorithm) for image restoration task, in which the images are blurred by relative motion between camera and the scene. In this case the RLA was implemented in an FPGA-based platform using the hardware description language VHDL, and assuming the absence of additive noise in the capturing image system. The overall architecture is scalable from 3×3 to 9×9 mask sizes for the convolution steps of the RLA. The quality evaluation of the collected images was achieved using the SR-SIM (Spectral Residual Based Similarity) metric as well as by a visual verification of the images. The synthesis results and respective testing with real images are also presented in order to give support to video applications.

Abstract

Assunto

Processamento de imagens -- Técnicas digitais, Engenharia elétrica

Palavras-chave

Image restoration , Convolution , Mathematical model , Hardware , Computer architecture , Deconvolution , Measurement, Richardson-Lucy Algorithm , Motion-Blurred Image Restoration , FPGA, Hardware Implementation , Scalable , Additive Noise , Distortion , Computer Vision , Input Image , Image Size , Convolution Operation , Singular Value Decomposition , Correction Process , Peak Signal-to-noise Ratio , Point Spread Function , Image Edge , Mathematical Operations , Inversion Process , Ordered Subset Expectation Maximization , Clock Cycles , Hardware Architecture , Convolution Process , Restoration Quality , Embedded System

Citação

Curso

Endereço externo

https://ieeexplore.ieee.org/document/7724056

Avaliação

Revisão

Suplementado Por

Referenciado Por