TWI735669B - 使用影像分析演算法以提供訓練資料至神經網路 - Google Patents

使用影像分析演算法以提供訓練資料至神經網路 Download PDF

Info

Publication number
TWI735669B
TWI735669B TW106133689A TW106133689A TWI735669B TW I735669 B TWI735669 B TW I735669B TW 106133689 A TW106133689 A TW 106133689A TW 106133689 A TW106133689 A TW 106133689A TW I735669 B TWI735669 B TW I735669B
Authority
TW
Taiwan
Prior art keywords
image
digital
macro block
training
images
Prior art date
Application number
TW106133689A
Other languages
English (en)
Chinese (zh)
Other versions
TW201814596A (zh
Inventor
尼可拉斯 丹尼歐森
星 范
Original Assignee
瑞典商安訊士有限公司
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 瑞典商安訊士有限公司 filed Critical 瑞典商安訊士有限公司
Publication of TW201814596A publication Critical patent/TW201814596A/zh
Application granted granted Critical
Publication of TWI735669B publication Critical patent/TWI735669B/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
    • G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
    • 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
    • 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
    • G06N3/08—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
    • G06N3/09—Supervised learning
    • 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
    • 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
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/19—Recognition using electronic means
    • G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G06V30/19173—Classification techniques
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • 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)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
TW106133689A 2016-10-04 2017-09-29 使用影像分析演算法以提供訓練資料至神經網路 TWI735669B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
EP16192142.4 2016-10-04
??16192142.4 2016-10-04
EP16192142.4A EP3306528B1 (en) 2016-10-04 2016-10-04 Using image analysis algorithms for providing traning data to neural networks

Publications (2)

Publication Number Publication Date
TW201814596A TW201814596A (zh) 2018-04-16
TWI735669B true TWI735669B (zh) 2021-08-11

Family

ID=57083180

Family Applications (1)

Application Number Title Priority Date Filing Date
TW106133689A TWI735669B (zh) 2016-10-04 2017-09-29 使用影像分析演算法以提供訓練資料至神經網路

Country Status (6)

Country Link
US (1) US10496903B2 (OSRAM)
EP (1) EP3306528B1 (OSRAM)
JP (1) JP6842395B2 (OSRAM)
KR (1) KR102203694B1 (OSRAM)
CN (1) CN107895359B (OSRAM)
TW (1) TWI735669B (OSRAM)

Families Citing this family (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6624125B2 (ja) * 2017-03-13 2019-12-25 コニカミノルタ株式会社 画像検査装置、画像形成システム及び画像圧縮方法
JP7028333B2 (ja) * 2018-03-05 2022-03-02 オムロン株式会社 照明条件の設定方法、装置、システム及びプログラム並びに記憶媒体
DE102019208257A1 (de) * 2018-07-03 2020-01-09 Heidelberger Druckmaschinen Ag Druckqualitätsanalyse mit neuronalen Netzen
CN109271847B (zh) 2018-08-01 2023-04-07 创新先进技术有限公司 无人结算场景中异常检测方法、装置及设备
KR102194303B1 (ko) 2018-10-08 2020-12-22 단국대학교 산학협력단 ３ｄ 데이터 프로세싱에 이용되는 ａｉ 트레이닝을 위한 데이터 셋 확장 생성과 전처리를 위한 장치 및 방법
EP3667557B1 (en) * 2018-12-13 2021-06-16 Axis AB Method and device for tracking an object
TWI701565B (zh) * 2018-12-19 2020-08-11 財團法人工業技術研究院 資料標記系統及資料標記方法
US11853812B2 (en) * 2018-12-20 2023-12-26 Here Global B.V. Single component data processing system and method utilizing a trained neural network
US10540572B1 (en) * 2019-01-31 2020-01-21 StradVision, Inc. Method for auto-labeling training images for use in deep learning network to analyze images with high precision, and auto-labeling device using the same
US10762393B2 (en) * 2019-01-31 2020-09-01 StradVision, Inc. Learning method and learning device for learning automatic labeling device capable of auto-labeling image of base vehicle using images of nearby vehicles, and testing method and testing device using the same
WO2020170036A1 (en) * 2019-02-22 2020-08-27 Stratuscent Inc. Systems and methods for learning across multiple chemical sensing units using a mutual latent representation
US11823348B2 (en) * 2019-05-17 2023-11-21 Barco N.V. Method and system for training generative adversarial networks with heterogeneous data
DE102019207575A1 (de) * 2019-05-23 2020-11-26 Volkswagen Aktiengesellschaft Verfahren zum Beurteilen einer funktionsspezifischen Robustheit eines Neuronalen Netzes
DE102019208733A1 (de) * 2019-06-14 2020-12-17 neurocat GmbH Verfahren und Generator zum Erzeugen von gestörten Eingangsdaten für ein neuronales Netz
EP3796231A1 (en) * 2019-09-19 2021-03-24 Robert Bosch GmbH Device and method for generating a compressed network from a trained neural network
KR102339181B1 (ko) * 2020-03-09 2021-12-13 에스케이 주식회사 Machine Learning을 이용한 데이터 연관성 자동 탐색 방법 및 시스템
TWI809266B (zh) * 2020-04-21 2023-07-21 中華電信股份有限公司 電梯事件偵測模型之產生與更新方法
EP3905659B1 (en) * 2020-04-28 2022-06-01 Axis AB Statistics-based electronics image stabilization
WO2021230675A1 (ko) * 2020-05-13 2021-11-18 (주)사맛디 딥러닝 기반 대상체 감성 인식 방법 및 장치
US11379697B2 (en) 2020-05-20 2022-07-05 Bank Of America Corporation Field programmable gate array architecture for image analysis
US11295430B2 (en) 2020-05-20 2022-04-05 Bank Of America Corporation Image analysis architecture employing logical operations
CN111767985B (zh) * 2020-06-19 2022-07-22 深圳市商汤科技有限公司 一种神经网络的训练方法、视频识别方法及装置
KR102213291B1 (ko) * 2020-07-30 2021-02-04 배도연 웹사이트 제작 시스템
US12185100B2 (en) * 2020-08-18 2024-12-31 Qualcomm Incorporated Encoding a data set using a neural network for uplink communication
US12423858B2 (en) * 2021-03-12 2025-09-23 Acronis International Gmbh Systems and methods for determining environment dimensions based on landmark detection
KR20230068508A (ko) * 2021-11-11 2023-05-18 한국전자기술연구원 효율적인 딥러닝 학습을 위한 메모리 구조 및 제어 방법
KR20240082865A (ko) * 2022-12-02 2024-06-11 삼성전자주식회사 표준 공간을 통해 영상을 처리하는 전자 장치 및 이의 제어 방법
US12556718B2 (en) 2022-12-29 2026-02-17 Samsung Electronics Co., Ltd. Electronic device and method with image encoding and decoding

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI355843B (en) * 2004-11-12 2012-01-01 Aptina Imaging Corp Image encoding with dynamic buffer-capacity-level-
CN102957912A (zh) * 2011-08-09 2013-03-06 杜比实验室特许公司 视频编码中的受指导图像上采样
CN103442629A (zh) * 2011-03-18 2013-12-11 Smi创新传感技术有限公司 通过设定数据速率确定双眼的至少一个参数的方法和光学测量装置
US20160007077A1 (en) * 2013-06-17 2016-01-07 Spotify Ab System and method for allocating bandwidth between media streams
TW201631973A (zh) * 2014-12-03 2016-09-01 安訊士有限公司 用於訊框序列之影像編碼的方法和編碼器

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6757602B2 (en) * 1997-02-06 2004-06-29 Automotive Technologies International, Inc. System for determining the occupancy state of a seat in a vehicle and controlling a component based thereon
JP3524250B2 (ja) * 1995-11-27 2004-05-10 キヤノン株式会社 デジタル画像処理プロセッサ
US7840502B2 (en) * 2007-06-13 2010-11-23 Microsoft Corporation Classification of images as advertisement images or non-advertisement images of web pages
JP5193931B2 (ja) * 2009-04-20 2013-05-08 富士フイルム株式会社 画像処理装置、画像処理方法およびプログラム
US9208405B2 (en) * 2010-08-06 2015-12-08 Sony Corporation Systems and methods for digital image analysis
US8965112B1 (en) * 2013-12-09 2015-02-24 Google Inc. Sequence transcription with deep neural networks
CN104103033B (zh) * 2014-08-05 2017-06-06 广州国米科技有限公司 图像实时处理方法
EP3021583B1 (en) 2014-11-14 2019-10-23 Axis AB Method of identifying relevant areas in digital images, method of encoding digital images, and encoder system
CN104679863B (zh) 2015-02-28 2018-05-04 武汉烽火众智数字技术有限责任公司 一种基于深度学习的以图搜图方法和系统
CN105260734A (zh) * 2015-10-10 2016-01-20 燕山大学 一种具有自建模功能的商品油表面激光标码识别方法
CN105430394A (zh) 2015-11-23 2016-03-23 小米科技有限责任公司 视频数据压缩处理方法、装置和设备
CN105551036B (zh) * 2015-12-10 2019-10-08 中国科学院深圳先进技术研究院 一种深度学习网络的训练方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI355843B (en) * 2004-11-12 2012-01-01 Aptina Imaging Corp Image encoding with dynamic buffer-capacity-level-
CN103442629A (zh) * 2011-03-18 2013-12-11 Smi创新传感技术有限公司 通过设定数据速率确定双眼的至少一个参数的方法和光学测量装置
CN102957912A (zh) * 2011-08-09 2013-03-06 杜比实验室特许公司 视频编码中的受指导图像上采样
US20160007077A1 (en) * 2013-06-17 2016-01-07 Spotify Ab System and method for allocating bandwidth between media streams
TW201631973A (zh) * 2014-12-03 2016-09-01 安訊士有限公司 用於訊框序列之影像編碼的方法和編碼器

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
2015 *
網路文獻作者名稱:"Rui Zhao"，著作名稱:Saliency Detection by Multi-Context Deep Learning，網址:"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7298731" *
網路文獻作者名稱:"Rui Zhao"，著作名稱:Saliency Detection by Multi-Context Deep Learning，網址:"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7298731"。 2015。

Also Published As

Publication number Publication date
CN107895359B (zh) 2023-06-09
JP2018101406A (ja) 2018-06-28
EP3306528A1 (en) 2018-04-11
JP6842395B2 (ja) 2021-03-17
EP3306528B1 (en) 2019-12-25
KR102203694B1 (ko) 2021-01-15
US10496903B2 (en) 2019-12-03
TW201814596A (zh) 2018-04-16
CN107895359A (zh) 2018-04-10
US20180096232A1 (en) 2018-04-05
KR20180037593A (ko) 2018-04-12

Similar Documents

Publication Publication Date Title
US10496903B2 (en) Using image analysis algorithms for providing training data to neural networks
CN108780499B (zh) 基于量化参数的视频处理的系统和方法
CN109076198B (zh) 基于视频的对象跟踪遮挡检测系统、方法和设备
US11477468B2 (en) Method and device for compressing image and neural network using hidden variable
CN108090470B (zh) 一种人脸对齐方法及装置
CN115115552B (zh) 图像矫正模型训练及图像矫正方法、装置和计算机设备
US10592725B2 (en) Neural network systems
KR102449841B1 (ko) 타겟의 검측 방법 및 장치
KR101622344B1 (ko) 적응적 영역 가중치가 적용된 센서스 변환 기반 스테레오 정합을 통한 시차 계산 방법 및 그 시스템
CN110198444A (zh) 视频帧编码方法、视频帧编码设备及具有存储功能的装置
KR102287891B1 (ko) 라이다와 카메라 퓨전 기술을 이용한 인공지능 기반 골재 품질 분석 방법, 장치 및 시스템
TWI512685B (zh) 移動物體偵測方法及其裝置
CN104683802A (zh) 一种基于h.264/avc压缩域的运动目标跟踪的方法
CN109614933A (zh) 一种基于确定性拟合的运动分割方法
CN104050677A (zh) 一种基于多层神经网络的超光谱图像分割方法
JP6600288B2 (ja) 統合装置及びプログラム
CN102479330A (zh) 调整摄影机的视频对象检测的运算功能的参数方法及其装置
CN106127234A (zh) 基于特征字典的无参考图像质量评价方法
CN119233045A (zh) 视频数据的生成方法及装置、非易失性存储介质
KR101675692B1 (ko) 구조 학습 기반의 군중 행동 인식 방법 및 장치
TW202001700A (zh) 影像的量化方法、神經網路的訓練方法及神經網路訓練系統
US20210241068A1 (en) Convolutional neural network
CN104125470A (zh) 一种视频数据传输方法
He et al. Fast image quality assessment via supervised iterative quantization method
CN110855989A (zh) 一种网络视频图像编码方法和装置