Processing

Please wait...

Settings

Settings

Goto Application

1. CN113228111 - IMAGE PROCESSING METHOD, IMAGE PROCESSING SYSTEM, AND PROGRAM

Office
China
Application Number 201980086315.3
Application Date 25.12.2019
Publication Number 113228111
Publication Date 06.08.2021
Publication Kind A
IPC
G06T 11/80
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
112D image generation
80Creating or modifying a manually drawn or painted image using a manual input device, e.g. mouse, light pen, direction keys on keyboard
G06T 1/00
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
1General purpose image data processing
G06T 1/40
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
1General purpose image data processing
20Processor architectures; Processor configuration, e.g. pipelining
40Neural networks
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
CPC
G06T 1/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
1General purpose image data processing
G06T 11/80
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
112D [Two Dimensional] image generation
80Creating or modifying a manually drawn or painted image using a manual input device, e.g. mouse, light pen, direction keys on keyboard
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 3/049
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
049Temporal neural nets, e.g. delay elements, oscillating neurons, pulsed inputs
G06T 11/001
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
112D [Two Dimensional] image generation
001Texturing; Colouring; Generation of texture or colour
G06T 11/203
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
112D [Two Dimensional] image generation
20Drawing from basic elements, e.g. lines or circles
203Drawing of straight lines or curves
Applicants CYGAMES INC.
CY游戏公司
Inventors KURABAYASHI SHUICHI
仓林修一
Agents 北京林达刘知识产权代理事务所(普通合伙) 11277
Priority Data 2018247800 28.12.2018 JP
Title
(EN) IMAGE PROCESSING METHOD, IMAGE PROCESSING SYSTEM, AND PROGRAM
(ZH) 图像处理方法、图像处理系统和程序
Abstract
(EN) The present invention provides an image processing method in which a computer stores, for each element, learning data having a pair comprising an outline image and a color image, generates, for each element, an estimation model for estimating the color image from the outline image by means of machine learning using the learning data of the elements, acquires the outline image to be colored (target outline image), identifies the element corresponding to the target outline image, generates the color image (target color image) paired with the target outline image on the basis of the target outline image and the estimation model corresponding to the identified element, uses the target color image to generate the color layer for an image file containing an outline layer and said color layer, inserts the generated color layer into the image file (target image file) containing the outline layer corresponding to the target outline image, corrects, on the basis of a user input, the color layer of the target image file into which said color layer was inserted, extracts the corrected color layer and corresponding outline layer as a learning image pair, and stores, as learning data, the pair of the outline image of the extracted outline layer and the color image of the color layer in association with the element corresponding to the estimation model used when generating the target color image.
(ZH) 提供图像处理方法,其中计算机:针对各元素存储包括成对的线条画图像和着色图像的学习数据;针对各元素通过使用元素的学习数据的机器学习来生成用于从线条画图像估计着色图像的估计模型;获得要着色的对象的线条画图像即对象线条画图像;识别与对象线条画图像相对应的元素;基于与所识别的元素相对应的估计模型和对象线条画图像来生成与对象线条画图像要配对的着色图像即对象着色图像;通过使用对象着色图像来生成包括线条画层和着色层的图像文件的着色层;将所生成的着色层插入到包括与对象线条画图像相对应的线条画层的图像文件即对象图像文件中;基于用户输入来修改被插入了着色层的对象图像文件的着色层;提取修改后的着色层和相应线条画层作为学习用的图像对;以及同与在生成对象着色图像时使用的估计模型相对应的元素相关联地存储成对的所提取的线条画层的线条画图像和所提取的着色层的着色图像作为学习数据。
Related patent documents