Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
IMAGE PROCESSING METHOD AND IMAGE RECEPTION DEVICE
Document Type and Number:
WIPO Patent Application WO/2018/193333
Kind Code:
A1
Abstract:
The present invention provides an image processing method for generating high-resolution image data from low-resolution image data, and an image reception device which operates using said image processing method. Specifically provided is an image processing method for generating high-resolution image data from low-resolution image data, wherein: a plurality of items of first image data are generated by dividing the low-resolution image data; one of two adjacent items from among the plurality of items of first image data is set as second image data and the other is set as third image data; fourth image data is generated by supplementing pixel data around the second image data; said pixel data includes a portion of the third image data; a convolutional neural network using the fourth image data as an input is applied; the convolutional neural network outputs fifth image data; and high-resolution image data is generated by combining a plurality of items of fifth image data. Also provided is an image reception device which operates using said image processing method.

Inventors:
SHIOKAWA MASATAKA (JP)
TAKAHASHI KEI (JP)
IWAKI YUJI (JP)
GODO HIROMICHI (JP)
Application Number:
PCT/IB2018/052435
Publication Date:
October 25, 2018
Filing Date:
April 09, 2018
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SEMICONDUCTOR ENERGY LAB (JP)
International Classes:
H04N7/01; G06T3/40
Domestic Patent References:
WO2009130820A12009-10-29
Foreign References:
JP2005346639A2005-12-15
Other References:
OHTANI, SHINYA ET AL.: "Super-Resolution with Four Output Convolutional Neural Networks", EARLY PUBLISHED THESIS OF IEICE TRANSACTIONS D, 15 January 2016 (2016-01-15), pages 1 - 6
DAI, AKIRA ET AL.: "Review on basic of improving visual texture of natural image in which super-resolution process is applied", IMPS IMAGE MEDIA PROCESSING SYMPOSIUM 2015, 18 November 2015 (2015-11-18), pages 130 - 131
Download PDF: