FR3094532B1 - Procédé et système d'identification d'objets à partir d'images labellisées desdits objets - Google Patents

Procédé et système d'identification d'objets à partir d'images labellisées desdits objets Download PDF

Info

Publication number
FR3094532B1
FR3094532B1 FR1903232A FR1903232A FR3094532B1 FR 3094532 B1 FR3094532 B1 FR 3094532B1 FR 1903232 A FR1903232 A FR 1903232A FR 1903232 A FR1903232 A FR 1903232A FR 3094532 B1 FR3094532 B1 FR 3094532B1
Authority
FR
France
Prior art keywords
labeled
images
adjustment
objects
mutualized
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
FR1903232A
Other languages
English (en)
Other versions
FR3094532A1 (fr
Inventor
Stefan Berechet
Ion Berechet
Gérard Berginc
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.)
Thales SA
Sispia SARL
Original Assignee
Thales SA
Sispia SARL
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 Thales SA, Sispia SARL filed Critical Thales SA
Priority to FR1903232A priority Critical patent/FR3094532B1/fr
Priority to EP20712507.1A priority patent/EP3948664A1/fr
Priority to US17/598,177 priority patent/US20220180620A1/en
Priority to PCT/EP2020/057107 priority patent/WO2020193253A1/fr
Priority to KR1020217032215A priority patent/KR20210140740A/ko
Priority to JP2021557475A priority patent/JP2022525812A/ja
Publication of FR3094532A1 publication Critical patent/FR3094532A1/fr
Application granted granted Critical
Publication of FR3094532B1 publication Critical patent/FR3094532B1/fr
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • 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
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/778—Active pattern-learning, e.g. online learning of image or video features
    • G06V10/7784—Active pattern-learning, e.g. online learning of image or video features based on feedback from supervisors
    • G06V10/7788—Active pattern-learning, e.g. online learning of image or video features based on feedback from supervisors the supervisor being a human, e.g. interactive learning with a human teacher

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Image Analysis (AREA)

Abstract

Le système d’identification d’objets à partir d’images comprend un module d’agréation et de mutualisation d’images recevant en entrée les première, deuxième, et troisième pluralités d’images labellisées respectivement par l’expert métier, par apprentissage automatique et par apprentissage automatique profond et délivrant en sortie une pluralité d’images labélisées mutualisées d’ajustement ayant la meilleure précision ; et un module d’agrégation et de mutualisation d’invariants recevant en entrée les première, deuxième, et troisième pluralités invariants labellisés respectivement par l’expert métier, par apprentissage automatique et par apprentissage automatique profond et délivrant en sortie une pluralité d’invariants labélisés mutualisés d’ajustement ayant la meilleure précision.En réponse à une nouvelle pluralité d’images de l’objet à identifier, les premier, deuxième, et troisième modules d’identification sont conçus pour utiliser en entrée, séparément et séquentiellement pour leur identification respective, la pluralité d’images labellisés mutualisés d’ajustement et/ou la pluralité d’invariants labellisés mutualisés d’ajustement issus des modules d’agrégation et de mutualisation. Figure pour l’abrégé : Fig. 1
FR1903232A 2019-03-28 2019-03-28 Procédé et système d'identification d'objets à partir d'images labellisées desdits objets Active FR3094532B1 (fr)

Priority Applications (6)

Application Number Priority Date Filing Date Title
FR1903232A FR3094532B1 (fr) 2019-03-28 2019-03-28 Procédé et système d'identification d'objets à partir d'images labellisées desdits objets
EP20712507.1A EP3948664A1 (fr) 2019-03-28 2020-03-16 Procede et systeme d'identification d'objets a partir d'images labellisees desdits objets
US17/598,177 US20220180620A1 (en) 2019-03-28 2020-03-16 Method and system for identifying objects from labeled images of said objects
PCT/EP2020/057107 WO2020193253A1 (fr) 2019-03-28 2020-03-16 Procede et systeme d'identification d'objets a partir d'images labellisees desdits objets
KR1020217032215A KR20210140740A (ko) 2019-03-28 2020-03-16 오브젝트들의 픽셀화된 이미지들로부터 오브젝트들을 식별하기 위한 방법 및 시스템
JP2021557475A JP2022525812A (ja) 2019-03-28 2020-03-16 オブジェクトを前記オブジェクトのラベル付き画像から識別するための方法及びシステム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR1903232 2019-03-28
FR1903232A FR3094532B1 (fr) 2019-03-28 2019-03-28 Procédé et système d'identification d'objets à partir d'images labellisées desdits objets

Publications (2)

Publication Number Publication Date
FR3094532A1 FR3094532A1 (fr) 2020-10-02
FR3094532B1 true FR3094532B1 (fr) 2021-09-10

Family

ID=68072534

Family Applications (1)

Application Number Title Priority Date Filing Date
FR1903232A Active FR3094532B1 (fr) 2019-03-28 2019-03-28 Procédé et système d'identification d'objets à partir d'images labellisées desdits objets

Country Status (6)

Country Link
US (1) US20220180620A1 (fr)
EP (1) EP3948664A1 (fr)
JP (1) JP2022525812A (fr)
KR (1) KR20210140740A (fr)
FR (1) FR3094532B1 (fr)
WO (1) WO2020193253A1 (fr)

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4253522B2 (ja) * 2003-03-28 2009-04-15 株式会社日立ハイテクノロジーズ 欠陥分類方法及び装置
FR2981772B1 (fr) 2011-10-21 2017-12-22 Thales Sa Procede de reconstruction 3d d'un objet d'une scene
US10095917B2 (en) 2013-11-04 2018-10-09 Facebook, Inc. Systems and methods for facial representation

Also Published As

Publication number Publication date
WO2020193253A1 (fr) 2020-10-01
JP2022525812A (ja) 2022-05-19
EP3948664A1 (fr) 2022-02-09
US20220180620A1 (en) 2022-06-09
KR20210140740A (ko) 2021-11-23
FR3094532A1 (fr) 2020-10-02

Similar Documents

Publication Publication Date Title
CN107735733B (zh) 全息设备和对象分类系统
EP1986046B1 (fr) Procédé pour déterminer une position de mise au point et système de vision pour une inspection
CN101052979A (zh) 并行脉冲信号处理设备、模式识别设备和图像输入设备
Harder et al. Automatic analysis of dividing cells in live cell movies to detect mitotic delays and correlate phenotypes in time
CN105184238A (zh) 一种人脸识别方法及系统
CN102682514A (zh) 一种纸类识别方法及相关装置
WO2019114380A1 (fr) Procédé d'identification de planche de bois, procédé d'apprentissage machine et dispositif d'identification de planche de bois et dispositif électronique
US10769432B2 (en) Automated parameterization image pattern recognition method
Li et al. Cow individual identification based on convolutional neural network
MY194367A (en) Plant data display processing device and plant control system
CN104200215A (zh) 一种大口径光学元件表面灰尘与麻点识别方法
Al-Jubouri et al. Efficient individual identification of zebrafish using Hue/Saturation/Value color model
FR3094532B1 (fr) Procédé et système d'identification d'objets à partir d'images labellisées desdits objets
US20220092869A1 (en) System and method for generating a mask for object instances in an image
Ling et al. Analyzing u-net robustness for single cell nucleus segmentation from phase contrast images
Liu et al. Detection and recognition of uneaten fish food pellets in aquaculture using image processing
CN113642541B (zh) 一种基于深度学习的人脸属性识别系统
US20230206606A1 (en) Method and system for training a neural network-implemented sensor system to classify objects in a bulk flow
US20220012465A1 (en) Systems and methods for facilitating clone selection
CN204154293U (zh) 一种平面平整度智能测量系统
Angarita‐Jaimes et al. Algorithms for the automated analysis of cellular dynamics within living fungal colonies
Shihavuddin et al. Cascaded 3-stage nuclei segmentation using U-net, Faster-RCNN and segnet for higher precision
Biswal et al. White Blood Cell Classification Using Pre-Trained Deep Neural Networks and Transfer Learning
Yella et al. Automatically detecting the number of logs on a timber truck
CN110866420A (zh) 一种基于光场相机和hog、svm的2d欺骗性行人识别方法

Legal Events

Date Code Title Description
PLFP Fee payment

Year of fee payment: 2

PLSC Publication of the preliminary search report

Effective date: 20201002

PLFP Fee payment

Year of fee payment: 3

PLFP Fee payment

Year of fee payment: 4

PLFP Fee payment

Year of fee payment: 5

PLFP Fee payment

Year of fee payment: 6