ETRI-Knowledge Sharing Plaform

KOREAN
특허 검색
Status Country
Year ~ Keyword

Detail

Registered METHOD AND APPARATUS FOR REMOVING COMPRESSED POISSON NOISE OF IMAGE BASED ON DEEP NEURAL NETWORK

Inventors
Yoo Seok Bong, Han Mi Kyong
Application No.
16987027 (2020.08.06)
Publication No.
20210042887 (2021.02.11)
Registration No.
11430090 (2022.08.30)
Country
UNITED STATES
Project Code
19MH1500, Development and Demonstration of Smart City Service over 5G Network, Han Mi Kyong
Abstract
A method for removing compressed Poisson noises in an image, based on deep neural networks, may comprise generating a plurality of block-aggregation images by performing block transform on low-frequency components of an input image; obtaining a plurality of restored block-aggregation images by inputting the plurality of block-aggregation images into a first deep neural network; generating a low-band output image from which noises for the low-frequency components are removed by performing inverse block transform on the plurality of restored block-aggregation images; and generating an output image from which compressed Poisson noises are removed by adding the low-band output image to a high-band output image from which noises for high-frequency components of the input image are removed.
KSP Keywords
Block Transform, Deep neural network(DNN), Frequency components, High Frequency(HF), Poisson Noise, high-band, high-frequency components, low-band, low-frequency, neural network