FR2675928A1 - Procede et dispositif de classification automatique d'objets. - Google Patents

Procede et dispositif de classification automatique d'objets. Download PDF

Info

Publication number
FR2675928A1
FR2675928A1 FR9105179A FR9105179A FR2675928A1 FR 2675928 A1 FR2675928 A1 FR 2675928A1 FR 9105179 A FR9105179 A FR 9105179A FR 9105179 A FR9105179 A FR 9105179A FR 2675928 A1 FR2675928 A1 FR 2675928A1
Authority
FR
France
Prior art keywords
classification
learning
phase
objects
vector
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.)
Granted
Application number
FR9105179A
Other languages
English (en)
French (fr)
Other versions
FR2675928B1 (OSRAM
Inventor
Quignon Jean
Regef Jean-Luc
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
Original Assignee
Thomson CSF SA
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 Thomson CSF SA filed Critical Thomson CSF SA
Priority to FR9105179A priority Critical patent/FR2675928A1/fr
Priority to EP92401083A priority patent/EP0511060A1/fr
Priority to CA002085012A priority patent/CA2085012A1/fr
Priority to JP4509234A priority patent/JPH06500190A/ja
Priority to PCT/FR1992/000349 priority patent/WO1992020038A1/fr
Publication of FR2675928A1 publication Critical patent/FR2675928A1/fr
Priority to KR1019920703293A priority patent/KR930701799A/ko
Application granted granted Critical
Publication of FR2675928B1 publication Critical patent/FR2675928B1/fr
Granted legal-status Critical Current

Links

Classifications

    • 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
    • G06N3/10—Interfaces, programming languages or software development kits, e.g. for simulating neural networks
    • 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24317—Piecewise classification, i.e. whereby each classification requires several discriminant rules
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Biology (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)
  • Complex Calculations (AREA)
FR9105179A 1991-04-26 1991-04-26 Procede et dispositif de classification automatique d'objets. Granted FR2675928A1 (fr)

Priority Applications (6)

Application Number Priority Date Filing Date Title
FR9105179A FR2675928A1 (fr) 1991-04-26 1991-04-26 Procede et dispositif de classification automatique d'objets.
EP92401083A EP0511060A1 (fr) 1991-04-26 1992-04-17 Procédé et dispositif de classification automatique d'objets
CA002085012A CA2085012A1 (fr) 1991-04-26 1992-04-17 Procede et dispositif de classification automatique d'objets
JP4509234A JPH06500190A (ja) 1991-04-26 1992-04-17 対象の自動分類方法及び装置
PCT/FR1992/000349 WO1992020038A1 (fr) 1991-04-26 1992-04-17 Procede et dispositif de classification automatique d'objets
KR1019920703293A KR930701799A (ko) 1991-04-26 1992-12-21 오브젝트를 자동으로 분류하는 프로세스와 장치

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
FR9105179A FR2675928A1 (fr) 1991-04-26 1991-04-26 Procede et dispositif de classification automatique d'objets.

Publications (2)

Publication Number Publication Date
FR2675928A1 true FR2675928A1 (fr) 1992-10-30
FR2675928B1 FR2675928B1 (OSRAM) 1995-02-17

Family

ID=9412298

Family Applications (1)

Application Number Title Priority Date Filing Date
FR9105179A Granted FR2675928A1 (fr) 1991-04-26 1991-04-26 Procede et dispositif de classification automatique d'objets.

Country Status (6)

Country Link
EP (1) EP0511060A1 (OSRAM)
JP (1) JPH06500190A (OSRAM)
KR (1) KR930701799A (OSRAM)
CA (1) CA2085012A1 (OSRAM)
FR (1) FR2675928A1 (OSRAM)
WO (1) WO1992020038A1 (OSRAM)

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
IJCNN: INTERNAIONAL JOINT CONFERENCE ON NEURAL NETWORKS. 17-21 JUIN 1990,SAN DIEGO, US, IEEE vol. I, pages 423 - 428; D. CASASENT AND E. BARNARD: 'ADAPTIVE CLUSTERING NEURAL NET FOR PIECEWISE NONLINEAR DISCRIMINANT SURFACES' *
INTERNATIONAL NEURAL NETWORK CONFERENCE, 9-13 JUILLET 1990, PARIS, FR,KLUWER ACADEMIC PUBLISHERS, DORDRECHT (NL), ETC. pages 318 - 321; M. SAERENS: 'A PRELIMINARY STUDY OF A COMPETITIVE COST FUNCTION APLLIED TO CLUSTERING' *

Also Published As

Publication number Publication date
EP0511060A1 (fr) 1992-10-28
WO1992020038A1 (fr) 1992-11-12
FR2675928B1 (OSRAM) 1995-02-17
JPH06500190A (ja) 1994-01-06
KR930701799A (ko) 1993-06-12
CA2085012A1 (fr) 1992-10-27

Similar Documents

Publication Publication Date Title
US9830709B2 (en) Video analysis with convolutional attention recurrent neural networks
US20200104692A1 (en) Exploiting activation sparsity in deep neural networks
US20190340510A1 (en) Sparsifying neural network models
FR3025344A1 (fr) Reseau de neurones convolutionnels
FR3050846A1 (fr) Dispositif et procede de distribution de donnees de convolution d'un reseau de neurones convolutionnel
EP0552074A1 (fr) Système de traitement de données multiprocesseur
EP3844679A1 (fr) Architecture de calculateur d'une couche de convolution dans un reseau de neurones convolutionnel
EP0514986B1 (fr) Procédé d'apprentissage d'un réseau de neurones et dispositif de classification pour la mise en oeuvre de ce procédé
EP3633545A1 (fr) Procedes d'apprentissage de parametres d'un reseau de neurones a convolution, de detection d'elements d'interet visibles dans une image et d'association d'elements d'interet visibles dans une image
US10747845B2 (en) System, method and apparatus for computationally efficient data manipulation
FR2690772A1 (fr) Processeur neuronal muni de moyens pour calculer une norme ou une distance.
EP3899800A1 (fr) Processeur de traitement de donnees, procede et programme d'ordinateur correspondant
FR2660085A1 (fr) Dispositif de traitement de donnees et procede pour selectionner des mots de donnees contenus dans un dictionnaire.
FR2675928A1 (fr) Procede et dispositif de classification automatique d'objets.
Keibek et al. A fast partitioning algorithm and a comparison of binary feedforward neural networks
FR3144687A1 (fr) Architecture de réseau neuronal pour un réseau systolique de processeurs et procédé de traitement de données utilisant un réseau neuronal
EP4202770A1 (fr) Reseau de neurones avec generation a la volee des parametres du reseau
JP7732401B2 (ja) 学習装置、学習方法、画像処理装置、画像処理方法およびプログラム
EP3764286A1 (fr) Procédé et outil informatique de détermination de fonctions de transferts entre des paires de couches successives d'un réseau de neurones
US12340313B2 (en) Neural network pruning method and system via layerwise analysis
Blume et al. Optoelectronic fuzzy ARTMAP processor
CN119849580B (zh) 一种面向星载边缘计算的目标检测模型轻量化方法
EP3955167A1 (fr) Architecture de calcul reconfigurable pour la mise en oeuvre de réseaux de neurones artificiels
EP4195061B1 (fr) Calculateur d'algorithme réalisé à partir de mémoires à technologies mixtes
US12159212B1 (en) Shared depthwise convolution

Legal Events

Date Code Title Description
ST Notification of lapse