EP1364337A1 - Procede pour identifier des informations enregistrees - Google Patents

Procede pour identifier des informations enregistrees

Info

Publication number
EP1364337A1
EP1364337A1 EP02737874A EP02737874A EP1364337A1 EP 1364337 A1 EP1364337 A1 EP 1364337A1 EP 02737874 A EP02737874 A EP 02737874A EP 02737874 A EP02737874 A EP 02737874A EP 1364337 A1 EP1364337 A1 EP 1364337A1
Authority
EP
European Patent Office
Prior art keywords
labeling
proposal
suggestions
processor
patterns
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.)
Withdrawn
Application number
EP02737874A
Other languages
German (de)
English (en)
Inventor
Joachim Gloger
Stefan Hahn
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.)
Mercedes Benz Group AG
Original Assignee
DaimlerChrysler AG
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 DaimlerChrysler AG filed Critical DaimlerChrysler AG
Publication of EP1364337A1 publication Critical patent/EP1364337A1/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/40—Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor

Definitions

  • the invention relates to a method for marking patterns according to the preamble of patent claim 1.
  • Manually labeling samples is a time-consuming and expensive process. In order to accelerate this process, methods are used that generate a labeling proposal. The processor must either accept the proposal or modify it if the proposal is incorrect. Labeling methods are used in particular in classification processes in which a set of parameters for identifying objects is determined using training examples. The training data record must cover all boundary conditions of the recognition task. For the recognition of street scenes, samples of a few thousand to ten thousand manually processed images are required, which contain all potentially occurring object classes, e.g. cars, trucks, two-wheelers, pedestrians, weather conditions etc. From the processing of colored video images, a method is known in which an object, for example a tree, is manually identified in an image sequence in the first image (JR Ohm, P.
  • a method is known (AK Jain, Yu Zhong, S. Lakshamanan, "Object matching using deformable templates", IEEE Trans, on Pattern Analysis and Machine Intelligence, Vol. 18, No. 3, March 1996, p. 267-278 ), in which a database of automatically generated contour patterns is used to identify objects (patterns) in image data.
  • the contour patterns are automatically adapted to the objects and superimposed on them.
  • the image data together with the overlays by the contour patterns are then displayed to a viewer on a screen.
  • the object of the invention is to find a novel method for the automatic marking of patterns, which guarantees an optimized coincidence of the pattern and marking.
  • the invention has the advantage that in the automatic generation of labeling suggestions, even with incorrect suggestions due to the mass of the samples to be labeled, a large amount of time is saved in labeling. It is also advantageous that automatic methods are used for the generation of the labeling suggestions, which can be very time-consuming and computationally expensive, since the labeling suggestions can be generated independently of the labeling process.
  • the generated labeling suggestions are up to the test saved by the processor in a database and imported to the processor during labeling.
  • the pattern to be identified is available in electronic form in a computer system.
  • the pattern is e.g. recorded with a camera or a document is scanned into a computer.
  • Acoustic patterns that are available in electronic form are also identified.
  • a labeling proposal is created for the sample. This proposal can be generated separately from the actual labeling process, for example when the method for generating the proposal is very time-consuming. However, it is also possible to generate the proposal during the labeling process, for example when the method is able to generate the proposals in real time or almost in real time.
  • the processor uses a computer program to display the sample and the proposed label in a suitable form on a display.
  • the archetype is displayed, together with the proposed marking, which is shown in the form of a closed line, for example.
  • the line is superimposed on the archetype so that the processor can see both.
  • the processor accepts the proposal and stores it in the system as an indicator. If the proposal is too imprecise, there are several options. On the one hand, the processor himself will delete (or modify) the wrong suggestion and create his own labeling suggestion manually. On the other hand, it is possible that the processor rejects the proposal.
  • the proposal is then used as the basis for a further procedure in order to arrive at a correct labeling proposal. It is also possible to delete the proposal completely and to try to generate a suitable proposal with a more complex process.
  • the labeling process is carried out over the Internet.
  • a device according to the invention for carrying out the method can advantageously be regarded as a two-part system consisting of a server system and a processing device.
  • the server system has a device for storing patterns, a unit for generating labeling suggestions for the stored patterns, a memory for storing the labels assigned to the patterns, and a communication device for communicating with a processing device for evaluating and processing the labeling suggestions .
  • the processing device for evaluating and processing labeling suggestions for the samples is designed in such a way that it includes a display for displaying the samples and the associated labeling suggestions and an input unit for entering the assessment of the labeling of the sample and / or for deleting or modifying the labeling.
  • the processing device has a communication unit for communication with a server system for storing patterns and labels, and for generating labeling suggestions. With the aim of running as many labeling processes as possible at the same time, it is profitable if the server system is connected to a plurality of processing devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Image Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Processing (AREA)

Abstract

La présente invention concerne un procédé pour identifier des modèles se présentant sous forme d'informations enregistrées. Une proposition d'identification est automatiquement produite pour ledit modèle. Cette proposition peut être produite séparément du processus d'identification à proprement dit, par exemple lorsque le procédé pour produire la proposition prend beaucoup de temps. Mais cette proposition peut également être produite au cours du processus d'identification, par exemple lorsque le procédé peut produire les propositions en temps réel ou quasiment en temps réel. Cette invention permet de produire rapidement les propositions d'identification pour l'observateur et d'identifier un objet de manière représentative.
EP02737874A 2001-03-02 2002-02-28 Procede pour identifier des informations enregistrees Withdrawn EP1364337A1 (fr)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
DE10110275 2001-03-02
DE10110275A DE10110275A1 (de) 2001-03-02 2001-03-02 Verfahren zur Kennzeichnung von gespeicherter Information
PCT/EP2002/002171 WO2002086806A1 (fr) 2001-03-02 2002-02-28 Procede pour identifier des informations enregistrees

Publications (1)

Publication Number Publication Date
EP1364337A1 true EP1364337A1 (fr) 2003-11-26

Family

ID=7676198

Family Applications (1)

Application Number Title Priority Date Filing Date
EP02737874A Withdrawn EP1364337A1 (fr) 2001-03-02 2002-02-28 Procede pour identifier des informations enregistrees

Country Status (5)

Country Link
US (1) US7519237B2 (fr)
EP (1) EP1364337A1 (fr)
JP (1) JP2004527048A (fr)
DE (1) DE10110275A1 (fr)
WO (1) WO2002086806A1 (fr)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102004009541A1 (de) * 2004-02-23 2005-09-15 Iris-Gmbh Infrared & Intelligent Sensors Benutzersteuerbares Erfassungssystem
WO2007101452A1 (fr) * 2006-03-09 2007-09-13 Siemens Aktiengesellschaft Procédé et système de traitement d'objet pour réaliser le modèle d'un objet
JPWO2007105651A1 (ja) * 2006-03-10 2009-07-30 パナソニック株式会社 環境影響部材購入装置および環境影響部材購入システム
US8031981B2 (en) * 2007-12-21 2011-10-04 Daon Holdings Limited Method and systems for generating a subset of biometric representations
DE102009009904A1 (de) 2009-02-20 2009-10-15 Daimler Ag Verfahren zur Identifizierung von Objekten
DE102015007299A1 (de) 2015-06-03 2015-12-17 Daimler Ag Verfahren zur Klassifikation von Objekten
DE102018010039A1 (de) 2018-12-19 2020-06-25 Daimler Ag Verfahren zur Erkennung von mindestens einem Muster in einer Umgebung eines Fahrzeugs, Steuergerät zum Ausführen eines solchen Verfahrens, sowie Fahrzeug mit einem solchen Steuergerät
DE102019004075A1 (de) 2019-06-08 2020-01-02 Daimler Ag Verfahren zum Bestimmen einer Relevanz eines Objekts in einer Umgebung eines Kraftfahrzeugs mittels eines Fahrerassistenzsystems sowie Fahrerassistenzsystem

Family Cites Families (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS60196856A (ja) * 1984-03-20 1985-10-05 Olympus Optical Co Ltd 画像検索登録装置
JP2735187B2 (ja) * 1987-03-17 1998-04-02 株式会社東芝 情報検索方法
DE69028573T2 (de) * 1989-05-31 1997-03-27 Toshiba Kawasaki Kk Hochgeschwindigkeitssuchsystem zur Bilddatenspeicherung
US5179652A (en) * 1989-12-13 1993-01-12 Anthony I. Rozmanith Method and apparatus for storing, transmitting and retrieving graphical and tabular data
US5202828A (en) * 1991-05-15 1993-04-13 Apple Computer, Inc. User interface system having programmable user interface elements
EP0514688A2 (fr) * 1991-05-21 1992-11-25 International Business Machines Corporation Autocorrelation de forme généralisée pour l'acquisition et la reconnaissance de forme
US5189709A (en) * 1991-08-26 1993-02-23 The United States Of America As Represented By The United States National Aeronautics And Space Administration Dynamic pattern matcher using incomplete data
US5606693A (en) * 1991-10-02 1997-02-25 International Business Machines Corporation Distributed database management over a network
US5421008A (en) * 1991-11-08 1995-05-30 International Business Machines Corporation System for interactive graphical construction of a data base query and storing of the query object links as an object
US7242988B1 (en) * 1991-12-23 2007-07-10 Linda Irene Hoffberg Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore
US5579471A (en) * 1992-11-09 1996-11-26 International Business Machines Corporation Image query system and method
US6002798A (en) * 1993-01-19 1999-12-14 Canon Kabushiki Kaisha Method and apparatus for creating, indexing and viewing abstracted documents
US5600831A (en) * 1994-02-28 1997-02-04 Lucent Technologies Inc. Apparatus and methods for retrieving information by modifying query plan based on description of information sources
US5809171A (en) * 1996-01-05 1998-09-15 Mcdonnell Douglas Corporation Image processing method and apparatus for correlating a test image with a template
US5893095A (en) * 1996-03-29 1999-04-06 Virage, Inc. Similarity engine for content-based retrieval of images
US5696964A (en) * 1996-04-16 1997-12-09 Nec Research Institute, Inc. Multimedia database retrieval system which maintains a posterior probability distribution that each item in the database is a target of a search
US5852823A (en) * 1996-10-16 1998-12-22 Microsoft Image classification and retrieval system using a query-by-example paradigm
JPH10326286A (ja) * 1997-05-27 1998-12-08 Mitsubishi Electric Corp 類似検索装置及び類似検索プログラムを記録した記録媒体
JP4098880B2 (ja) * 1997-06-06 2008-06-11 松下電器産業株式会社 情報検索装置
JP3166905B2 (ja) * 1997-07-02 2001-05-14 インターナショナル・ビジネス・マシーンズ・コーポレ−ション パターンマッチングによる画像処理方法およびシステム
US6415282B1 (en) * 1998-04-22 2002-07-02 Nec Usa, Inc. Method and apparatus for query refinement
US6154567A (en) * 1998-07-01 2000-11-28 Cognex Corporation Pattern similarity metric for image search, registration, and comparison
US6564206B1 (en) * 1998-10-05 2003-05-13 Canon Kabushiki Kaisha Information search apparatus and method, and storage medium
US6256409B1 (en) * 1998-10-19 2001-07-03 Sony Corporation Method for determining a correlation between images using multi-element image descriptors
US6347313B1 (en) * 1999-03-01 2002-02-12 Hewlett-Packard Company Information embedding based on user relevance feedback for object retrieval
US6510406B1 (en) * 1999-03-23 2003-01-21 Mathsoft, Inc. Inverse inference engine for high performance web search
US6275613B1 (en) * 1999-06-03 2001-08-14 Medsim Ltd. Method for locating a model in an image
US6445822B1 (en) * 1999-06-04 2002-09-03 Look Dynamics, Inc. Search method and apparatus for locating digitally stored content, such as visual images, music and sounds, text, or software, in storage devices on a computer network
US6674915B1 (en) * 1999-10-07 2004-01-06 Sony Corporation Descriptors adjustment when using steerable pyramid to extract features for content based search
US7389208B1 (en) * 2000-06-30 2008-06-17 Accord Solutions, Inc. System and method for dynamic knowledge construction
US6748398B2 (en) * 2001-03-30 2004-06-08 Microsoft Corporation Relevance maximizing, iteration minimizing, relevance-feedback, content-based image retrieval (CBIR)

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO02086806A1 *

Also Published As

Publication number Publication date
US7519237B2 (en) 2009-04-14
DE10110275A1 (de) 2002-09-19
US20040111434A1 (en) 2004-06-10
WO2002086806A1 (fr) 2002-10-31
JP2004527048A (ja) 2004-09-02

Similar Documents

Publication Publication Date Title
DE19718805C2 (de) Verfahren und Anordnung zum Erkennen von Verteilinformationen
DE10034606B4 (de) Verfahren zur Bereitstellung von fertigungsbezogenen Daten in einer Serienfertigung von Fertigungsobjekten, insbesondere von Kraftfahrzeugen
DE19624977A1 (de) Verfahren zur Verarbeitung von Postsachen
DE102019209560A1 (de) Vorrichtung und Verfahren zum Trainieren eines neuronalen Netzwerks
DE102019204139A1 (de) Training für künstliche neuronale Netzwerke mit besserer Ausnutzung der Lern-Datensätze
DE102012206037A1 (de) Lernverfahren zur automatisierten Erkennung von Verkehrszeichen, Verfahren zur Bestimmung eines aktualisierten Parametersatzes für eine Klassifikation von einem Verkehrszeichen und Verkehrszeichenerkennungssystem
EP1364337A1 (fr) Procede pour identifier des informations enregistrees
DE102019204602B4 (de) Verfahren und Vorrichtung zur Maskierung von in einem Bild enthaltenen Objekten
CN112800972A (zh) 文字识别方法及装置、存储介质
DE102008059229A1 (de) Verfahren zum Ausrichten eines Behälters
DE102008057979B4 (de) Lerneinheit für ein Objekterkennungssystem und Objekterkennungssytem
DE102009009904A1 (de) Verfahren zur Identifizierung von Objekten
DE102019127565A1 (de) Verfahren und Vorrichtung zum Verarbeiten von Bildern
DE1549893A1 (de) Verfahren und Anordnung zur elektronischen Klassierung von Bildvorlagen
DE102019208864A1 (de) Erkennungssystem, Arbeitsverfahren und Trainingsverfahren
DE102018205409A1 (de) Verfahren, Vorrichtung, Computerprogramm und Computerprogrammprodukt zum Annotieren eines Bildes
EP4121897B1 (fr) Procédés et systèmes de fourniture des ensembles de données d'apprentissage labellisés synthétiques et leurs applications
EP1202212A1 (fr) Méthode pour l'acquisition de tout le jeu de données de formulaires contenant des caractères manuscripts
WO2024132949A1 (fr) Procédé et système pour l'extraction basée sur des critères de données d'image
DE102022209248A1 (de) Anonymisieren von Bilddaten
DE102022118492A1 (de) Verfahren zum Erkennen von zum Herstellen von Produkten vorgesehenen Objekten, elektronische Recheneinrichtung, Computerprogramm sowie computerlesbares Medium
DE102020114909A1 (de) Optimierung des Zusammenwirkens unterschiedlicher Datenbanken
DE102019133905A1 (de) Verfahren zum Kennzeichnen von manipulierten Bildern oder Videos
DE102021127958A1 (de) Computerimplementiertes Verfahren zum Training einer künstlichen Intelligenz
DE60318448T2 (de) Verfahren zur verarbeitung von poststücken unter verwendung von sprachsynthesen

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20030901

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE TR

AX Request for extension of the european patent

Extension state: AL LT LV MK RO SI

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: DAIMLERCHRYSLER AG

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: DAIMLER AG

17Q First examination report despatched

Effective date: 20110421

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

INTG Intention to grant announced

Effective date: 20140909

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20150120