AT509022A3 - METHOD FOR QUALITY TESTING OF A DIGITAL IMAGE - Google Patents

METHOD FOR QUALITY TESTING OF A DIGITAL IMAGE Download PDF

Info

Publication number
AT509022A3
AT509022A3 AT12862009A AT12862009A AT509022A3 AT 509022 A3 AT509022 A3 AT 509022A3 AT 12862009 A AT12862009 A AT 12862009A AT 12862009 A AT12862009 A AT 12862009A AT 509022 A3 AT509022 A3 AT 509022A3
Authority
AT
Austria
Prior art keywords
digital image
error
optimization method
quantization
pixel
Prior art date
Application number
AT12862009A
Other languages
German (de)
Other versions
AT509022B1 (en
AT509022A2 (en
Original Assignee
Ait Austria Inst Of Technology Gmbh
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 Ait Austria Inst Of Technology Gmbh filed Critical Ait Austria Inst Of Technology Gmbh
Priority to AT12862009A priority Critical patent/AT509022B1/en
Priority to DE201010032806 priority patent/DE102010032806B4/en
Publication of AT509022A2 publication Critical patent/AT509022A2/en
Publication of AT509022A3 publication Critical patent/AT509022A3/en
Application granted granted Critical
Publication of AT509022B1 publication Critical patent/AT509022B1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20004—Adaptive image processing
    • G06T2207/20012—Locally adaptive
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20021—Dividing image into blocks, subimages or windows
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30168—Image quality inspection

Abstract

Die Erfindung betrifft ein Verfahren zur Qualitätsprüfung eines Digitalbilds (3) anhand von fehlerfreien Referenz-Digitalbildern (1).Erfindungsgemäß ist vorgesehen, dass für die Referenz-Digitalbilder (1) pixelweise Fehlerschranken vorgegeben werden, ein verfälschtes Digitalbild (2) erstellt wird, das vorgegebene Abweichungen zum Referenz-Digitalbild (1a) aufweist, wobei die maximale Abweichung (Efull) der Fehlerschranken vom verfälschten Digitalbild (2) für alle Bildkanäle bzw. Elemente eines Feature-Vektors (P1......PN) pixelweise ermittelt werden, und daran anschließend ein Optimierungsverfahren durchgeführt wird, wobei als Parameter des Optimierungsverfahrens die Quantisierung (Q) variabel vorgegeben wird, wobei die maximale Abweichung (Ecbr) der mit der im Optimierungsverfahren als Optimierungsparameter gewählten vorgegebenen Quantisierung (Q) quantisierten Fehlerschranken ermittelt werden, wobei dem Optimierungsverfahren als Zielfunktion (F) die Standardabweichung der Differenz zwischen der ersten Fehlerfläche (FFfull) und der mit der jeweiligen Quantisierung (Q) ermittelten quantisierten Fehlerfläche (FFcbr) zugrunde gelegt und minimiert wird, und überprüft wird, ob die einzelnen Pixel des Digitalbilds (3) innerhalb der quantisierten Fehlerschranken liegen.The invention relates to a method for quality testing of a digital image (3) based on error-free reference digital images (1). According to the invention, pixel-wise error bounds are predetermined for the reference digital images (1), a corrupted digital image (2) is created has predetermined deviations from the reference digital image (1a), wherein the maximum deviation (Efull) of the error barriers from the corrupted digital image (2) are determined pixel by pixel for all image channels or elements of a feature vector (P1 ...... PN), and subsequently an optimization method is carried out, the quantization (Q) being variably specified as a parameter of the optimization method, wherein the maximum deviation (Ecbr) of the quantization (Q) quantized with the predetermined quantization (Q) selected in the optimization method as the optimization method is determined, wherein the optimization method as target function (F) the standard deviation of the The difference between the first error surface (FFfull) and the quantized error surface (FFcbr) determined with the respective quantization (Q) is taken as basis and minimized, and it is checked whether the individual pixels of the digital image (3) lie within the quantized error barriers.

AT12862009A 2009-08-14 2009-08-14 METHOD FOR QUALITY TESTING OF A DIGITAL IMAGE AT509022B1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
AT12862009A AT509022B1 (en) 2009-08-14 2009-08-14 METHOD FOR QUALITY TESTING OF A DIGITAL IMAGE
DE201010032806 DE102010032806B4 (en) 2009-08-14 2010-07-30 Method for quality testing a digital image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
AT12862009A AT509022B1 (en) 2009-08-14 2009-08-14 METHOD FOR QUALITY TESTING OF A DIGITAL IMAGE

Publications (3)

Publication Number Publication Date
AT509022A2 AT509022A2 (en) 2011-05-15
AT509022A3 true AT509022A3 (en) 2012-06-15
AT509022B1 AT509022B1 (en) 2012-09-15

Family

ID=43536316

Family Applications (1)

Application Number Title Priority Date Filing Date
AT12862009A AT509022B1 (en) 2009-08-14 2009-08-14 METHOD FOR QUALITY TESTING OF A DIGITAL IMAGE

Country Status (2)

Country Link
AT (1) AT509022B1 (en)
DE (1) DE102010032806B4 (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5649068A (en) * 1993-07-27 1997-07-15 Lucent Technologies Inc. Pattern recognition system using support vectors
WO2004001683A1 (en) * 2002-06-19 2003-12-31 Mars Incorporated Currency validator
EP1752934A2 (en) * 2005-08-08 2007-02-14 Kabushiki Kaisha Toshiba Sheet identifying apparatus and sheet identifying method
DE60033535T2 (en) * 2000-12-15 2007-10-25 Mei, Inc. Currency validator
WO2008015489A1 (en) * 2006-07-28 2008-02-07 Mei, Inc. Classification using support vector machines and variables selection
WO2009072211A1 (en) * 2007-12-07 2009-06-11 Glory Ltd. Banknote identifying device and banknote identifying method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5649068A (en) * 1993-07-27 1997-07-15 Lucent Technologies Inc. Pattern recognition system using support vectors
DE60033535T2 (en) * 2000-12-15 2007-10-25 Mei, Inc. Currency validator
WO2004001683A1 (en) * 2002-06-19 2003-12-31 Mars Incorporated Currency validator
EP1752934A2 (en) * 2005-08-08 2007-02-14 Kabushiki Kaisha Toshiba Sheet identifying apparatus and sheet identifying method
WO2008015489A1 (en) * 2006-07-28 2008-02-07 Mei, Inc. Classification using support vector machines and variables selection
WO2009072211A1 (en) * 2007-12-07 2009-06-11 Glory Ltd. Banknote identifying device and banknote identifying method

Also Published As

Publication number Publication date
AT509022B1 (en) 2012-09-15
DE102010032806B4 (en) 2015-02-12
DE102010032806A1 (en) 2011-03-10
AT509022A2 (en) 2011-05-15

Similar Documents

Publication Publication Date Title
DE102015212349B4 (en) FAULT DETECTION DEVICE AND FAULT DETECTION PROGRAM
MX2022000354A (en) Video decoding method and apparatus, and video encoding method and apparatus.
DE102019218837A1 (en) METHOD AND SYSTEMS FOR THE NEURONAL NETWORK FACTORY LOOP FILTERING FOR VIDEO CODING
EP3246875A3 (en) Method and system for image registration using an intelligent artificial agent
WO2015191823A3 (en) Apparatus and methods for modifying keratinous surfaces
DE112012003264B4 (en) Image processing apparatus, image processing method and program, and image pickup apparatus having an image processing apparatus
SG164293A1 (en) System and method for inspecting a wafer
EP4173740A3 (en) Light recycling for additive manufacturing optimization
WO2017081542A3 (en) Computational microscopes and methods for generating an image under different illumination conditions
JP2008238590A5 (en)
DE102012215114B4 (en) Method for inspecting a printed product
EP1968011A3 (en) Method and apparatus for camera calibration, and vehicle
DE102020216406A1 (en) VEHICLE UNDERBODY INSPECTION SYSTEM AND PROCEDURE
DE602009000340D1 (en) Method and apparatus for filtering speckle noise in SAR images
WO2017065509A3 (en) Image decoding method and apparatus in image coding system
EP3082102A1 (en) Method of evaluating at least one component layer produced by means of a generative powder layer
WO2009044148A8 (en) Apparatus and method of image analysis
EP2407846A3 (en) Method and apparatus for monitoring the deviation of an object from a sequence and corresponding control system
WO2013076583A3 (en) Active vision method for stereo imaging system and corresponding system
AT509022A3 (en) METHOD FOR QUALITY TESTING OF A DIGITAL IMAGE
WO2009096776A3 (en) Making a three-dimensional reproduction of a relief surface by using a mould
DE69821298T2 (en) Method and device for detecting motion vectors and device for image coding
EP3989237A4 (en) Disease diagnosis system and method for performing segmentation by using neural network and unlocalized block
EP2312499A3 (en) Image processing apparatus and image processing method
JP2008199658A5 (en)

Legal Events

Date Code Title Description
MM01 Lapse because of not paying annual fees

Effective date: 20170814