WO2019091181A8 - 图像处理方法、处理装置和处理设备 - Google Patents

图像处理方法、处理装置和处理设备 Download PDF

Info

Publication number
WO2019091181A8
WO2019091181A8 PCT/CN2018/101372 CN2018101372W WO2019091181A8 WO 2019091181 A8 WO2019091181 A8 WO 2019091181A8 CN 2018101372 W CN2018101372 W CN 2018101372W WO 2019091181 A8 WO2019091181 A8 WO 2019091181A8
Authority
WO
WIPO (PCT)
Prior art keywords
image
processing
neural network
input
generative neural
Prior art date
Application number
PCT/CN2018/101372
Other languages
English (en)
French (fr)
Other versions
WO2019091181A1 (zh
Inventor
刘瀚文
那彦波
Original Assignee
京东方科技集团股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 京东方科技集团股份有限公司 filed Critical 京东方科技集团股份有限公司
Priority to EP18876474.0A priority Critical patent/EP3709267A4/en
Priority to US16/338,830 priority patent/US11138466B2/en
Publication of WO2019091181A1 publication Critical patent/WO2019091181A1/zh
Publication of WO2019091181A8 publication Critical patent/WO2019091181A8/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2132—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on discrimination criteria, e.g. discriminant analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Multimedia (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

本公开实施例提供一种图像处理方法、处理装置和处理设备，利用生成神经网络结合图像内容特征实现图像转换，使得转换后的输出图像具有多样性并且保持与输入图像的一致性。该图像处理方法包括获取输入图像(110)；利用生成神经网络对输入图像进行图像转换处理(120)；和输出图像转换处理后的输出图像(130)。所述输入图像具有N个通道，N为大于等于1的正整数；所述生成神经网络的输入包括噪声图像通道和输入图像的N个通道；所述生成神经网络的输出为包括N个通道的输出图像。
PCT/CN2018/101372 2017-11-09 2018-08-20 图像处理方法、处理装置和处理设备 WO2019091181A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP18876474.0A EP3709267A4 (en) 2017-11-09 2018-08-20 IMAGE PROCESSING PROCESS, PROCESSING APPARATUS AND PROCESSING DEVICE
US16/338,830 US11138466B2 (en) 2017-11-09 2018-08-20 Image processing method, processing apparatus and processing device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711099143.2 2017-11-09
CN201711099143.2A CN107767408B (zh) 2017-11-09 2017-11-09 图像处理方法、处理装置和处理设备

Publications (2)

Publication Number Publication Date
WO2019091181A1 WO2019091181A1 (zh) 2019-05-16
WO2019091181A8 true WO2019091181A8 (zh) 2019-08-01

Family

ID=61272292

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/101372 WO2019091181A1 (zh) 2017-11-09 2018-08-20 图像处理方法、处理装置和处理设备

Country Status (4)

Country Link
US (1) US11138466B2 (zh)
EP (1) EP3709267A4 (zh)
CN (1) CN107767408B (zh)
WO (1) WO2019091181A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111340905A (zh) * 2020-02-13 2020-06-26 北京百度网讯科技有限公司 图像风格化方法、装置、设备和介质

Families Citing this family (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018091486A1 (en) 2016-11-16 2018-05-24 Ventana Medical Systems, Inc. Convolutional neural networks for locating objects of interest in images of biological samples
CN107767408B (zh) * 2017-11-09 2021-03-12 京东方科技集团股份有限公司 图像处理方法、处理装置和处理设备
WO2019194256A1 (ja) * 2018-04-05 2019-10-10 株式会社小糸製作所 演算処理装置、オブジェクト識別システム、学習方法、自動車、車両用灯具
CN108805833B (zh) * 2018-05-29 2019-06-18 西安理工大学 基于条件对抗网络的字帖二值化背景噪声杂点去除方法
CN110555808B (zh) * 2018-05-31 2022-05-31 杭州海康威视数字技术股份有限公司 一种图像处理方法、装置、设备及机器可读存储介质
RU2709661C1 (ru) * 2018-09-19 2019-12-19 Общество с ограниченной ответственностью "Аби Продакшн" Обучение нейронных сетей для обработки изображений с помощью синтетических фотореалистичных содержащих знаки изображений
US11080832B2 (en) 2018-09-26 2021-08-03 Canon Kabushiki Kaisha Image processing method, image processing apparatus, imaging apparatus, and storage medium
CN110956575B (zh) 2018-09-26 2022-04-12 京东方科技集团股份有限公司 转变图像风格的方法和装置、卷积神经网络处理器
US20200184321A1 (en) * 2018-12-11 2020-06-11 Fotonation Limited Multi-processor neural network processing apparatus
CN109816612A (zh) * 2019-02-18 2019-05-28 京东方科技集团股份有限公司 图像增强方法和装置、计算机可读存储介质
CN111724309B (zh) * 2019-03-19 2023-07-14 京东方科技集团股份有限公司 图像处理方法及装置、神经网络的训练方法、存储介质
CN111008692A (zh) * 2019-11-08 2020-04-14 国网天津市电力公司 基于改进生成对抗网络的多能计量特征数据生成方法及装置
CN111260570B (zh) * 2020-01-10 2023-03-14 西安理工大学 基于循环一致性对抗网络的碑帖二值化背景噪声模拟方法
CN111475496B (zh) * 2020-03-26 2023-07-21 深圳先进技术研究院 基于多条件约束的时间序列数据生成方法、装置及介质
US11797372B2 (en) 2020-03-26 2023-10-24 Shenzhen Institutes Of Advanced Technology Method and apparatus for generating time series data based on multi-condition constraints, and medium
CN111428678B (zh) * 2020-04-02 2023-06-23 山东卓智软件股份有限公司 一种空间约束条件下生成对抗网络遥感影像样本扩充方法
CN111524207B (zh) * 2020-04-21 2023-01-06 腾讯科技（深圳）有限公司 基于人工智能的图像生成方法、装置、电子设备
JP7446903B2 (ja) * 2020-04-23 2024-03-11 株式会社日立製作所 画像処理装置、画像処理方法及び画像処理システム
CN113642592A (zh) * 2020-04-27 2021-11-12 武汉Tcl集团工业研究院有限公司 一种训练模型的训练方法、场景识别方法、计算机设备
CN111710011B (zh) * 2020-06-10 2021-06-25 广州梦映动漫网络科技有限公司 一种漫画生成方法、系统、电子设备及介质
CN112927180B (zh) * 2020-10-15 2022-11-15 内蒙古鄂尔多斯资源股份有限公司 一种基于生成对抗网络的羊绒羊毛光学显微镜图像识别方法
CN112308094B (zh) * 2020-11-25 2023-04-18 创新奇智(重庆)科技有限公司 一种图像处理方法、装置、电子设备及存储介质
CN112598775B (zh) * 2020-12-21 2021-10-29 广东工业大学 一种基于对比学习的多视图生成方法
CN112767377B (zh) * 2021-01-27 2022-07-05 电子科技大学 一种级联医学图像增强方法
CN113723171B (zh) * 2021-06-16 2022-11-11 陕西师范大学 基于残差生成对抗网络的脑电信号去噪方法
CN113269209B (zh) * 2021-06-30 2022-06-07 山东建筑大学 一种图像识别方法、系统、介质及电子设备
CN113627289B (zh) * 2021-07-27 2023-06-16 广西电网有限责任公司 一种基于深度学习的电力设备识别方法及其装置
CN115797479B (zh) * 2021-09-09 2024-05-24 北京三快在线科技有限公司 地标图像的生成方法、装置、计算机设备和存储介质
CN114091538B (zh) * 2021-11-23 2024-04-30 吉林大学 一种基于信号特征的判别损失卷积神经网络智能降噪方法
CN114387467B (zh) * 2021-12-09 2022-07-29 哈工大（张家口）工业技术研究院 一种基于多模块卷积特征融合的医学图像分类方法

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102288280B1 (ko) 2014-11-05 2021-08-10 삼성전자주식회사 영상 학습 모델을 이용한 영상 생성 방법 및 장치
US10504004B2 (en) * 2016-09-16 2019-12-10 General Dynamics Mission Systems, Inc. Systems and methods for deep model translation generation
US10607329B2 (en) * 2017-03-13 2020-03-31 Adobe Inc. Illumination estimation from a single image
CN106971202A (zh) * 2017-03-24 2017-07-21 南京大学 一种基于卷积神经网络的中国水墨画风格提取方法
CN106952224B (zh) * 2017-03-30 2019-08-13 电子科技大学 一种基于卷积神经网络的图像风格转移方法
CN107180410A (zh) * 2017-04-11 2017-09-19 中国农业大学 一种图像的风格化重建方法及装置
CN107122826B (zh) * 2017-05-08 2019-04-23 京东方科技集团股份有限公司 用于卷积神经网络的处理方法和系统、和存储介质
US10210631B1 (en) * 2017-08-18 2019-02-19 Synapse Technology Corporation Generating synthetic image data
CN107767408B (zh) * 2017-11-09 2021-03-12 京东方科技集团股份有限公司 图像处理方法、处理装置和处理设备

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111340905A (zh) * 2020-02-13 2020-06-26 北京百度网讯科技有限公司 图像风格化方法、装置、设备和介质

Also Published As

Publication number Publication date
CN107767408A (zh) 2018-03-06
US11138466B2 (en) 2021-10-05
EP3709267A1 (en) 2020-09-16
WO2019091181A1 (zh) 2019-05-16
CN107767408B (zh) 2021-03-12
EP3709267A4 (en) 2021-07-28
US20200065619A1 (en) 2020-02-27

Similar Documents

Publication Publication Date Title
WO2019091181A8 (zh) 图像处理方法、处理装置和处理设备
MX2018005690A (es) Sistemas y metodos para procesar contenido utilizando redes neuronales convolucionales.
MY183858A (en) Reducing correlation between higher order ambisonic (hoa) background channels
MX366333B (es) Dispositivo de transmision, metodo de transmision, dispositivo de recepcion, y metodo de recepcion.
MY178066A (en) Method and apparatus for performing analog-to-digital conversion on multiple input signals
WO2016170413A8 (en) Analog-to-digital converter (adc) dynamic range enhancement for voice-activated systems
EP3176749A3 (en) Efficient image processing on content-adaptive pq signal domain
WO2019023079A3 (en) COORDINATED BEAM TRAINING PROTOCOL (COBF) FOR NON-MANAGED NETWORKS
SG10201803184UA (en) Image processing device and image processing method performing slice-based compression
AU2018344830A8 (en) Apparatus, method and computer program for encoding, decoding, scene processing and other procedures related to DirAC based spatial audio coding
EP3280138A3 (en) Image processing apparatus, image projection apparatus, and image processing method
MX2019000038A (es) Aparato de transmision, aparato de recepcion y metodo de procesamiento de se?al de los mismos.
GB2573238A (en) Method of video transmission and display
MX2021008715A (es) Aparato de transmision y metodo de procesamiento por se?al del mismo.
MX2017010251A (es) Aparato de transmision, metodo de transmision, aparato de recepcion y metodo de recepcion.
EP3629240A3 (en) Generative adversarial networks for local noise removal from an image
EP4270976A3 (en) Devices and methods for high dynamic range video
EP3336753A3 (en) Face direction estimation device and face direction estimation method
WO2016139055A3 (en) Radiation system
WO2016118929A3 (en) Transmission scheme for sc-fdma with two dft-precoding stages
EP3745744A3 (en) Audio processing
AU2019394097A8 (en) Apparatus, method and computer program for encoding, decoding, scene processing and other procedures related to DirAC based spatial audio coding using diffuse compensation
MX2018003615A (es) Dispositivo de transmision, metodo de transmision, dispositivo de recepcion y metodo de recepcion.
MX2019011522A (es) Aparato y métodos para procesar una señal de audio.
WO2014200322A3 (ko) 신호 변환 방법 및 디바이스

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18876474

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018876474

Country of ref document: EP

Effective date: 20200609