CN112750067B - 图像处理系统及其训练方法 - Google Patents

图像处理系统及其训练方法 Download PDF

Info

Publication number
CN112750067B
CN112750067B CN202011145264.8A CN202011145264A CN112750067B CN 112750067 B CN112750067 B CN 112750067B CN 202011145264 A CN202011145264 A CN 202011145264A CN 112750067 B CN112750067 B CN 112750067B
Authority
CN
China
Prior art keywords
image
neural network
post
processing
input
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202011145264.8A
Other languages
English (en)
Chinese (zh)
Other versions
CN112750067A (zh
Inventor
金泰贤
金镇寿
裵钟贤
洪性柱
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SK Hynix Inc
Original Assignee
SK Hynix Inc
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 SK Hynix Inc filed Critical SK Hynix Inc
Publication of CN112750067A publication Critical patent/CN112750067A/zh
Application granted granted Critical
Publication of CN112750067B publication Critical patent/CN112750067B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06N3/0475—Generative networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/094—Adversarial learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/60—Image enhancement or restoration using machine learning, e.g. neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
CN202011145264.8A 2019-10-29 2020-10-23 图像处理系统及其训练方法 Active CN112750067B (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020190135041A KR20210050684A (ko) 2019-10-29 2019-10-29 이미지 처리 시스템
KR10-2019-0135041 2019-10-29

Publications (2)

Publication Number Publication Date
CN112750067A CN112750067A (zh) 2021-05-04
CN112750067B true CN112750067B (zh) 2024-05-07

Family

ID=75378970

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011145264.8A Active CN112750067B (zh) 2019-10-29 2020-10-23 图像处理系统及其训练方法

Country Status (5)

Country Link
US (1) US11599981B2 (https=)
JP (1) JP2021072106A (https=)
KR (1) KR20210050684A (https=)
CN (1) CN112750067B (https=)
DE (1) DE102020213289A1 (https=)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12235651B1 (en) * 2021-03-29 2025-02-25 Amazon Technologies, Inc. Autonomous navigation correction system
KR102728337B1 (ko) * 2021-05-31 2024-11-11 한국전자기술연구원 Gan 구조를 활용한 영상 영역 분할 방법 및 시스템

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107909621A (zh) * 2017-11-16 2018-04-13 深圳市唯特视科技有限公司 一种基于双生成对抗网络的医学图像合成方法
CN108257116A (zh) * 2017-12-30 2018-07-06 清华大学 一种生成对抗图像的方法
CN108830827A (zh) * 2017-05-02 2018-11-16 通用电气公司 神经网络训练图像生成系统
CN108932527A (zh) * 2018-06-06 2018-12-04 上海交通大学 使用交叉训练模型检测对抗样本的方法
CN109036389A (zh) * 2018-08-28 2018-12-18 出门问问信息科技有限公司 一种对抗样本的生成方法及装置
CN109685200A (zh) * 2018-11-19 2019-04-26 华东师范大学 基于生成对抗网络的雾计算工业协议构建方法及构建系统
CN110222774A (zh) * 2019-06-10 2019-09-10 百度在线网络技术（北京）有限公司 非法图像鉴别方法、装置、内容安全防火墙及存储介质
CN110322396A (zh) * 2019-06-19 2019-10-11 怀光智能科技（武汉）有限公司 一种病理切片颜色归一化方法及系统

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10169662B2 (en) 2015-06-15 2019-01-01 Google Llc Remote biometric monitoring system
US10460231B2 (en) 2015-12-29 2019-10-29 Samsung Electronics Co., Ltd. Method and apparatus of neural network based image signal processor
JP6463512B2 (ja) 2016-05-24 2019-02-06 オリンパス株式会社 画像信号処理装置、画像信号処理方法および画像信号処理プログラム
US10602126B2 (en) * 2016-06-10 2020-03-24 Lucid VR, Inc. Digital camera device for 3D imaging
KR101961177B1 (ko) 2016-07-22 2019-03-22 한국과학기술원 뉴럴 네트워크를 이용한 영상 처리 방법 및 장치
WO2018053340A1 (en) 2016-09-15 2018-03-22 Twitter, Inc. Super resolution using a generative adversarial network
KR101791573B1 (ko) 2016-10-21 2017-10-31 서강대학교산학협력단 컨볼루션 신경망을 이용한 비디오 스트림에 대한 수퍼 해상도 장치 및 방법
US10803378B2 (en) 2017-03-15 2020-10-13 Samsung Electronics Co., Ltd System and method for designing efficient super resolution deep convolutional neural networks by cascade network training, cascade network trimming, and dilated convolutions
US10497257B2 (en) * 2017-08-31 2019-12-03 Nec Corporation Parking lot surveillance with viewpoint invariant object recognition by synthesization and domain adaptation
US10430937B2 (en) * 2017-09-25 2019-10-01 United Technologies Corporation Automated material characterization system including conditional generative adversarial networks
US11188783B2 (en) * 2017-10-19 2021-11-30 Nokia Technologies Oy Reverse neural network for object re-identification
US10467501B2 (en) * 2017-10-30 2019-11-05 Sap Se Computer vision architecture with machine learned image recognition models
US10936863B2 (en) * 2017-11-13 2021-03-02 Way2Vat Ltd. Systems and methods for neuronal visual-linguistic data retrieval from an imaged document
US10944767B2 (en) * 2018-02-01 2021-03-09 International Business Machines Corporation Identifying artificial artifacts in input data to detect adversarial attacks
US10748314B2 (en) * 2018-02-15 2020-08-18 Microsoft Technology Licensing, Llc Controllable conditional image generation
US10552714B2 (en) * 2018-03-16 2020-02-04 Ebay Inc. Generating a digital image using a generative adversarial network
US20190297326A1 (en) * 2018-03-21 2019-09-26 Nvidia Corporation Video prediction using spatially displaced convolution
US10825219B2 (en) * 2018-03-22 2020-11-03 Northeastern University Segmentation guided image generation with adversarial networks
US11100632B2 (en) * 2018-04-13 2021-08-24 Elekta, Inc. Image synthesis using adversarial networks such as for radiation therapy
CN108764091B (zh) * 2018-05-18 2020-11-17 北京市商汤科技开发有限公司 活体检测方法及装置、电子设备和存储介质
JP2022526718A (ja) * 2019-03-14 2022-05-26 ハイパーファイン，インコーポレイテッド 空間周波数データから磁気共鳴画像を生成するための深層学習技術
US11126891B2 (en) * 2019-09-11 2021-09-21 Toyota Research Institute, Inc. Systems and methods for simulating sensor data using a generative model

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108830827A (zh) * 2017-05-02 2018-11-16 通用电气公司 神经网络训练图像生成系统
CN107909621A (zh) * 2017-11-16 2018-04-13 深圳市唯特视科技有限公司 一种基于双生成对抗网络的医学图像合成方法
CN108257116A (zh) * 2017-12-30 2018-07-06 清华大学 一种生成对抗图像的方法
CN108932527A (zh) * 2018-06-06 2018-12-04 上海交通大学 使用交叉训练模型检测对抗样本的方法
CN109036389A (zh) * 2018-08-28 2018-12-18 出门问问信息科技有限公司 一种对抗样本的生成方法及装置
CN109685200A (zh) * 2018-11-19 2019-04-26 华东师范大学 基于生成对抗网络的雾计算工业协议构建方法及构建系统
CN110222774A (zh) * 2019-06-10 2019-09-10 百度在线网络技术（北京）有限公司 非法图像鉴别方法、装置、内容安全防火墙及存储介质
CN110322396A (zh) * 2019-06-19 2019-10-11 怀光智能科技（武汉）有限公司 一种病理切片颜色归一化方法及系统

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Rob-GAN: Generator, Discriminator, and Adversarial Attacker;Xuanqing;《arXiv:1807.10454v3》;第3.3节 *
对抗样本生成在人脸识别中的研究与应用;张加胜;《计算机应用与软件》;第36卷(第05期);第158-164页 *

Also Published As

Publication number Publication date
KR20210050684A (ko) 2021-05-10
US20210125320A1 (en) 2021-04-29
DE102020213289A1 (de) 2021-04-29
CN112750067A (zh) 2021-05-04
US11599981B2 (en) 2023-03-07
JP2021072106A (ja) 2021-05-06

Similar Documents

Publication Publication Date Title
CN111475797B (zh) 一种对抗图像生成方法、装置、设备以及可读存储介质
CN112396129B (zh) 一种对抗样本检测方法及通用对抗攻击防御系统
CN109190470B (zh) 行人重识别方法及装置
KR101381455B1 (ko) 생체 정보 처리 장치
CN110348475B (zh) 一种基于空间变换的对抗样本增强方法和模型
CN113435264A (zh) 基于寻找黑盒替代模型的人脸识别对抗攻击方法及装置
KR102313215B1 (ko) 특징 생성 기술을 이용한 머신러닝 기반 결함 분류 장치 및 방법
CN113870254B (zh) 目标对象的检测方法、装置、电子设备及存储介质
CN112750067B (zh) 图像处理系统及其训练方法
JP7710520B2 (ja) 行動バイオメトリクスについての時空間深層学習
CN113420582A (zh) 用于掌静脉识别的防伪检测方法及其系统
JP2020144735A (ja) 画像処理装置及びプログラム
Park et al. Paired mini-batch training: A new deep network training for image forensics and steganalysis
Fang et al. Attacking image splicing detection and localization algorithms using synthetic traces
CN115065504A (zh) 面向目标检测模型的安全评估方法和系统、电子设备
CN117934379A (zh) 噪声检测方法、设备以及存储介质
KR101991307B1 (ko) 다중 객체 추적을 위한 트랙렛의 특징 벡터 할당이 가능한 전자 장치 및 그 동작 방법
CN114612824A (zh) 目标识别方法及装置、电子设备和存储介质
Shibel et al. Deep learning detection of facial biometric presentation attack
CN117197877B (zh) 一种基于区域加权光流特征的微表情识别方法及系统
KR100472953B1 (ko) Ｓｖｍ을 이용한 얼굴 영역 검출 방법
CN116434287B (zh) 一种人脸图像检测方法、装置、电子设备及存储介质
CN117351579A (zh) 基于多源信息融合的虹膜活体检测方法及装置
CN116453185A (zh) 基于考场的身份识别方法、装置、电子设备及存储介质
CN119234259A (zh) 图像处理方法及装置

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant