[go: up one dir, main page]

WO2005096178A1 - Procede et appareil destines a extraire des categories d'objets visuels d'une base de donnees contenant des images - Google Patents

Procede et appareil destines a extraire des categories d'objets visuels d'une base de donnees contenant des images Download PDF

Info

Publication number
WO2005096178A1
WO2005096178A1 PCT/GB2005/001124 GB2005001124W WO2005096178A1 WO 2005096178 A1 WO2005096178 A1 WO 2005096178A1 GB 2005001124 W GB2005001124 W GB 2005001124W WO 2005096178 A1 WO2005096178 A1 WO 2005096178A1
Authority
WO
WIPO (PCT)
Prior art keywords
images
model
visual object
image
object category
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.)
Ceased
Application number
PCT/GB2005/001124
Other languages
English (en)
Other versions
WO2005096178A8 (fr
Inventor
Andrew Zisserman
Robert Fergus
Pietro Perona
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.)
Oxford University Innovation Ltd
Original Assignee
Oxford University Innovation Ltd
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 Oxford University Innovation Ltd filed Critical Oxford University Innovation Ltd
Priority to JP2007505620A priority Critical patent/JP2007531136A/ja
Priority to EP05729251A priority patent/EP1730658A1/fr
Publication of WO2005096178A1 publication Critical patent/WO2005096178A1/fr
Publication of WO2005096178A8 publication Critical patent/WO2005096178A8/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5854—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using shape and object relationship
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • 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

Definitions

  • This invention relates to a method and apparatus for retrieving visual object categories from a database containing images and, more particularly, to an improved method and apparatus for searching for, and retrieving, relevant images corresponding to visual object categories specified by a user by means of, for example, an Internet search engine or the like.
  • the most relevant returned items i.e. those containing precisely the keyword(s) entered, are identified and then ranked according to a numeric value based on the number of links existing to each respective web page in other web pages.
  • the results likely to be of most relevance to the user are listed in the first few pages of the search results.
  • the results most likely to be of relevance are not likely to be returned in the first few pages of the search results, but instead are more likely to be evenly mixed with unrelated images.
  • This method is highly effective in quickly gathering related images from the millions available across the World Wide Web, but the final outcome is far from perfect in the sense that the user may then have to go through tens or even hundreds or thousands of result entries to find the images of interest. We have now devised an improved arrangement.
  • apparatus for determining the relevance of images retrieved from a database relative to a specified visual object category, the apparatus comprising means for transforming a visual object category into a model defining features of said visual object category and a spatial relationship therebetween.
  • Means may be provided for storing said model.
  • means are provided for comparing a set of images retrieved from a database with the stored model and calculating a likelihood value relating to each image based on its correspondence with said model.
  • Means may further be provided for ranking the images in order of the respective likelihood values; and/or for retrieving further images corresponding to the specified visual object category.
  • a method for determining the relevance of images retrieved from a database relative to a specified visual object category comprising transforming a visual object category into a model defining features of said visual object category and a spatial relationship therebetween.
  • the method may further include the step of storing said model.
  • the method may further include the steps of comparing a set of images retrieved from the database with the stored model and calculating a likelihood value relating to each image based on its correspondence with the model.
  • the method includes ranking the images in order of the respective likelihood values; and/or for finding further images corresponding to the specified visual object category.
  • the set of images may be retrieved from a database during a search of that database, using for example, a search engine.
  • each part is represented by one or more of its appearance and/or geometry, its scale relative to the model, and its occlusion probability, which parameters may be modelled by probability density functions, such as Gaussian probability functions or the like.
  • the step of comparing an image with the models preferably includes identifying features of the image and evaluating the features using the above-mentioned probability densities.
  • the method may include the step of selecting a sub-set of the images retrieved during the database search, and creating the model from this sub-set of images.
  • substantially all of the images retrieved during the database search may be used to create the model.
  • at least two different models may be created in respect of a set of images retrieved during, for example, a database search, say patches and curves, although other features are envisaged.
  • a heterogeneous model made up of a combination of features may be created.
  • the method preferably includes the step of selecting the nature or type of model to be used for the comparison and ranking steps in respect of a particular set of images.
  • the selective step may be performed by calculating a differential ranking measure in respect of each model, and selecting the model having the largest differential ranking measure.
  • Figure 1 is a schematic block diagram illustrating the principal steps of a method according to a first exemplary embodiment of the present invention
  • Figure 2 is a schematic block diagram illustrating the principal components of a method according to a second exemplary embodiment of the present invention.
  • Figure 3 is a schematic block diagram illustrating the principal steps of a patch feature extraction method for use in the method of Figure 1 or Figure 2;
  • Figure 4 is a schematic block diagram illustrating the principal steps of a curve feature extraction method for use in a method of Figure 1 or Figure 2;
  • Figure 5 is a schematic block diagram illustrating the principal steps of a model learning method in the supervised case used in the method of Figure 1;
  • Figure 6 is a schematic block diagram illustrating the principal steps of a model learning method in the unsupervised case used in the method of Figure 2 (note: a rectangle denotes a process while a parallelogram denotes data).
  • the present invention is based on the principle that, even without improving the performance of a search engine per se the above-mentioned problems related to image-based Internet searching may be alleviated by measuring 'visual consistency' amongst the images that are returned by the search and re-ranking them on the basis of this consistency, thereby increasing the proportion of relevant images returned to the user within the first few entries in the search results.
  • This concept is based on the assumption that images related to the search requirements will typically be visually similar, while images that are unrelated to the search requirements will typically look different from each other as well.
  • the problem of how to measure 'visual consistency' is approached in the following exemplary embodiments of the present invention as one of probabilistic modelling and robust statistics.
  • the algorithm employed therein robustly learns the common visual elements in a set of returned images so that the unwanted (non-category) images can be rejected, or at least so that the returned images can be ranked according to their resemblance to this commonality. More precisely, a visual object model is learned which can accommodate the intra-class variation in the requested category.
  • the apparatus and method of these exemplary embodiments of the invention employ an extension of a constellation model, and are designed to learn object categories from images containing clutter, thereby at least minimising the requirement for human intervention.
  • An object or constellation model consists of a number of parts which are spatially arranged over the object, wherein each part has an appearance and can be occluded or not.
  • a part in this case may, for example, be a patch of picture elements (pixels) or a curve segment.
  • a part is represented by its intrinsic description (appearance or geometry), its scale relative to the model, and its occlusion probability.
  • the shape of the object is represented by the mutual position of the parts.
  • the entire model is generative and probabilistic, in the sense that part description, scale model shape and occlusion are all modelled by probability density functions, which in this case are Gaussians.
  • the process of learning an object category is one of first detecting features with characteristic scales, and then estimating the parameters of the above densities from these features, such that the model gives a maximum-likelihood description of the training data.
  • a model consists of P parts and is specified by parameters ⁇ .
  • the model is scale invariant. Full details of this model and its fitting to training data using the EM algorithm are given by R. Fergus, P. Perona, and A. Zisserman in Object Class Recognition by Unsupervised Scale-Invariant Learning, In Proc. CVPR, 2003, and essentially the same representations and estimation methods are used in the following exemplary embodiments of the present invention.
  • An interest operator such as that described by T. Kadir and M. Brady in Scale, Saliency and Image Description, IJCV, 45(2):83-105, 2001 , may be used to find regions that are salient over both location and scale. It is based on measurements of the grey level histogram and entropy over the entire region. The operator detects a set of circular regions so that both position (the circle centre) and scale (the circle radius) are determined. The operator is largely invariant to scale changes and rotation of the image. Thus, for example, if the image is doubled in size, then the corresponding set of regions will be detected (at twice the scale).
  • extended edge chains may be used as detected, for example, by the edge operator described by J.F. Canny in A Computational Approach to Edge Detection, IEEE PAMI, 8(6):679-698, 1986.
  • the chains are then segmented into segments between bitangent point, i.e. points at which a line has two points of tangency with the curve.
  • bitangency is covariant with projective transformations. This means that for near planar curves the segmentation is invariant to viewpoint, an important requirement if the same, or similar, objects are imaged at different scales and orientations.
  • each patch exists in a predetermined dimensional space. Since the appearance densities of the model must also exist in this space, it is necessary from a practical point-of-view to somehow reduce the dimensionality of each patch whilst retaining its distinctiveness.
  • PCA principal component analysis
  • the patches from all images are collected and PCA performed on them.
  • the appearance of each patch is then a vector of the coordinates within the first predetermined number k principal components, thereby giving A. This results in a good reconstruction of the original patch whilst using a moderate number of parameters per part.
  • an image search using a search engine such as Google® may be used to download a set of images and the integrity of the downloaded images is checked. In addition, those outside a reasonable size range, say between 100 and 600 pixels on the major axis) are discarded.
  • a typical image search is likely to return in the region of 450-700 usable images and a script may be employed to automate the procedure.
  • the images returned can be divided into three distinct types: • Good images, i.e. good examples of the keyword category, lacking major occlusion, although there may be a variety of viewpoints, scalings and orientations. • Intermediate images, i.e.
  • each image is converted into greyscale (because colour information is not used in the model described above, although colour information may be used in other models applied to embodiments of the present invention, and the invention is not intended to be limited in this regard), and curves and regions of interest are identified within the images.
  • a predetermined number of regions with the highest saliency are used from each image.
  • the learning process takes one of two distinct forms: unsupervised learning ( Figure 6) and limited supervision ( Figure 5).
  • unsupervised learning a model is learnt using all images in a dataset. No human intervention is required in the process.
  • limited supervision an alternative approach using relevance feedback is used, whereby a user selects, say, 10 or so images from the dataset that are close to the required image, and a model is learnt using these selected images.
  • the learning task takes the form of estimating the parameters ⁇ of the model discussed above.
  • the model is ⁇ learnt using the EM algorithm as described by R. Fergus et al in the reference specified above.
  • a variety of models may be learned, each made up of a variety of feature types (e.g. patches, curves, etc), and a decision must then be made as to which should give the final ranking that will be presented to a user.
  • this is done by using a second set of images, consisting entirely of "junk" images (i.e. images which are totally unrelated to the specified visual object category). These may be collected by, for example, typing "things" into a search engine's image search facility.
  • each model evaluates the likelihood of images from both datasets and a differential ranking measure is computed between them, for example, by looking at the area under an ROC curve between the two data sets. The model which gives the largest differential ranking measure is selected to give the final ranking presented to the user.
  • the model fitting situation dealt with herein is equivalent to that faced in the area of robust statistics: in the sense that there is an attempt to learn a model from a dataset which contains valid data (the good images) but also outliers (the intermediate and junk images) which cannot be fitted by the model. Consequently, a robust fitting algorithm, RANS AC may be adapted to the needs of the present invention.
  • a set of images sufficient to train a model (10, in this case) is randomly sampled from the images retrieved during a database search. This model is then scored on the remaining images by the differential ranking measure explained above. The sampling process is repeated a sufficient number of times to ensure a good chance of a sample set consisting entirely of inliers (good images).
  • the models of a category have been shown to be capable of being learnt from training sets containing large amounts of unrelated images (say up to 50% and beyond) and it is this ability that allows the present invention to handle the type of datasets returned by conventional Internet search engines.
  • the algorithm only requires images as its input, so the method and apparatus of the present invention can be used in conjunction with any existing search engine. Still further, it will be appreciated by a person skilled in the art that the present invention has as a significant advantage that it is scale invariant in its ability to retrieve/rank relevant images.
  • category keyword (needed for (i) above) can be automatically selected by choosing the most commonly searched for categories.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Library & Information Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Processing Or Creating Images (AREA)

Abstract

L'invention concerne un procédé destiné à déterminer l'importance d'images extraites d'une base de données dans une catégorie d'objets visuels spécifiques, représentée par le mot-clé de requête, ce procédé consistant à apprendre un modèle définissant des caractéristiques de cette catégorie d'objets visuels et une relation spatiale entre eux, à stocker ce modèle, à comparer un ensemble d'images extraites de cette base de données avec ce modèle stocké et à calculer une valeur de ressemblance entre chaque image basée sur sa correspondance avec le modèle.
PCT/GB2005/001124 2004-03-31 2005-03-11 Procede et appareil destines a extraire des categories d'objets visuels d'une base de donnees contenant des images Ceased WO2005096178A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2007505620A JP2007531136A (ja) 2004-03-31 2005-03-11 画像を有するデータベースからビジュアルオブジェクトカテゴリを抽出する方法及び装置
EP05729251A EP1730658A1 (fr) 2004-03-31 2005-03-11 Procede et appareil destines a extraire des categories d'objets visuels d'une base de donnees contenant des images

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
GB0407252A GB2412756A (en) 2004-03-31 2004-03-31 Method and apparatus for retrieving visual object categories from a database containing images
GB0407252.6 2004-03-31

Publications (2)

Publication Number Publication Date
WO2005096178A1 true WO2005096178A1 (fr) 2005-10-13
WO2005096178A8 WO2005096178A8 (fr) 2006-02-09

Family

ID=32247573

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/GB2005/001124 Ceased WO2005096178A1 (fr) 2004-03-31 2005-03-11 Procede et appareil destines a extraire des categories d'objets visuels d'une base de donnees contenant des images

Country Status (4)

Country Link
EP (1) EP1730658A1 (fr)
JP (1) JP2007531136A (fr)
GB (1) GB2412756A (fr)
WO (1) WO2005096178A1 (fr)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008159056A (ja) * 2006-12-22 2008-07-10 Palo Alto Research Center Inc 画像中に生じる特徴の生成モデルによる分類
CN102144231A (zh) * 2008-06-16 2011-08-03 微软公司 用于基于文本的图像搜索结果重新排序的自适应视觉相似性
EP2350884A4 (fr) * 2008-10-24 2012-11-07 Yahoo Inc Extraction d'image numérique par agrégation de résultats de recherche en fonction d'annotations visuelles
US8364462B2 (en) 2008-06-25 2013-01-29 Microsoft Corporation Cross lingual location search
US8457441B2 (en) 2008-06-25 2013-06-04 Microsoft Corporation Fast approximate spatial representations for informal retrieval
US8527564B2 (en) 2010-12-16 2013-09-03 Yahoo! Inc. Image object retrieval based on aggregation of visual annotations
WO2014151035A1 (fr) * 2013-03-15 2014-09-25 Toyota Motor Engineering & Manufacturing North America, Inc. Procédé et système informatiques de reconnaissance d'objet de catégorie dynamique
GB2529427A (en) * 2014-08-19 2016-02-24 Cortexica Vision Systems Ltd Image processing
CN114091558A (zh) * 2020-07-31 2022-02-25 中兴通讯股份有限公司 特征选择方法、装置、网络设备和计算机可读存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6240424B1 (en) * 1998-04-22 2001-05-29 Nbc Usa, Inc. Method and system for similarity-based image classification
FR2779848B1 (fr) * 1998-06-15 2001-09-14 Commissariat Energie Atomique Procede invariant d'indexation d'une image utilisant des caracterisations fractales et par moments
US7200270B2 (en) * 2001-12-13 2007-04-03 Kabushiki Kaisha Toshiba Pattern recognition apparatus and method using distributed model representation of partial images
US20030123737A1 (en) * 2001-12-27 2003-07-03 Aleksandra Mojsilovic Perceptual method for browsing, searching, querying and visualizing collections of digital images

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
DESELAERS T ET AL: "Features for Image Retrieval Clustering Visually Similar Images to Improve Image Search Engines", PROCEEDINGS INFORMATIKTAGE 2003 DER GESELLSCHAFT FÜR INFORMATIK, BAD SCHUSSENRIED, GERMANY, November 2003 (2003-11-01), XP002333390, Retrieved from the Internet <URL:http://www-i6.informatik.rwth-aachen.de/~deselaers/files/deselaers-clustering.pdf> *
FERGUS R ET AL.: "A Visual Category Filter for Google Images", ECCV 2004: 8TH EUROPEAN CONFERENCE ON COMPUTER VISION, PRAGUE, CZECH REPUBLIC, MAY 11-14, 2004. PROCEEDINGS, vol. 3021, 11 May 2004 (2004-05-11), LECTURE NOTES IN COMPUTER SCIENCE, SPRINGER-VERLAG, pages 242 - 256, XP002333388, ISBN: 3-540-21984-6 *
FERGUS R ET AL: "Object class recognition by unsupervised scale-invariant learning", PROCEEDINGS 2003 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION. CVPR 2003. MADISON, WI, JUNE 18 - 20, 2003, vol. 2, 18 June 2003 (2003-06-18), IEEE CS, USA, pages 264 - 271, XP010644682, ISBN: 0-7695-1900-8 *
HONG-JIANG ZHANG: "Learning semantics in content based image retrieval", ISPA 2003: PROCEEDINGS OF THE 3RD INTERNATIONAL SYMPOSIUM ON IMAGE AND SIGNAL PROCESSING AND ANALYSIS, 2003. ROME, ITALY SEPT. 18-20, 2003, vol. 1, 18 September 2003 (2003-09-18), IEEE, USA, pages 284 - 288, XP010703873, ISBN: 953-184-061-X *
LAVRENKO V ET AL: "A Model for Learning the Semantics of Pictures", PROCEEDINGS NIPS 2003 ANNUAL CONFERENCE ON NEURAL INFORMATION PROCESSING SYSTEMS, DECEMBER 9, 2003 WHISTLER, BC, CANADA, 9 December 2003 (2003-12-09), MIT PRESS, pages 1 - 8, XP002333389, Retrieved from the Internet <URL:http://web.archive.org/web/20040202121612/http://books.nips.cc/nips16.html> *
SU ZHONG ET AL: "Relevance feedback using a Bayesian classifier in content-based image retrieval", PROCEEDINGS OF SPIE, vol. 4315, December 2000 (2000-12-01), pages 97 - 106, XP002333392 *
VASCONCELOS N ET AL: "Learning from User Feedback in Image Retrieval Systems", PROCEEDINGS NIPS 1999 ANNUAL CONFERENCE ON NEURAL INFORMATION PROCESSING SYSTEMS, DENVER, CO, USA, 29 NOVEMBER - 4 DECEMBER 1999, 29 November 1999 (1999-11-29), MIT PRESS, pages 977 - 983, XP002333391, Retrieved from the Internet <URL:http://www.svcl.ucsd.edu/publications> *

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008159056A (ja) * 2006-12-22 2008-07-10 Palo Alto Research Center Inc 画像中に生じる特徴の生成モデルによる分類
EP1936536A3 (fr) * 2006-12-22 2012-05-09 Palo Alto Research Center Incorporated Système et procédé pour réaliser une classification via des modèles génératifs des caractéristiques d'une image
CN102144231A (zh) * 2008-06-16 2011-08-03 微软公司 用于基于文本的图像搜索结果重新排序的自适应视觉相似性
EP2300947A4 (fr) * 2008-06-16 2012-09-05 Microsoft Corp Similarité visuelle adaptative pour le reclassement de résultats de recherche d' images basées sur le texte
US8457441B2 (en) 2008-06-25 2013-06-04 Microsoft Corporation Fast approximate spatial representations for informal retrieval
US8364462B2 (en) 2008-06-25 2013-01-29 Microsoft Corporation Cross lingual location search
EP2350884A4 (fr) * 2008-10-24 2012-11-07 Yahoo Inc Extraction d'image numérique par agrégation de résultats de recherche en fonction d'annotations visuelles
US8527564B2 (en) 2010-12-16 2013-09-03 Yahoo! Inc. Image object retrieval based on aggregation of visual annotations
WO2014151035A1 (fr) * 2013-03-15 2014-09-25 Toyota Motor Engineering & Manufacturing North America, Inc. Procédé et système informatiques de reconnaissance d'objet de catégorie dynamique
US9111348B2 (en) 2013-03-15 2015-08-18 Toyota Motor Engineering & Manufacturing North America, Inc. Computer-based method and system of dynamic category object recognition
GB2529427A (en) * 2014-08-19 2016-02-24 Cortexica Vision Systems Ltd Image processing
GB2529427B (en) * 2014-08-19 2021-12-08 Zebra Tech Corp Processing query image data
CN114091558A (zh) * 2020-07-31 2022-02-25 中兴通讯股份有限公司 特征选择方法、装置、网络设备和计算机可读存储介质

Also Published As

Publication number Publication date
GB0407252D0 (en) 2004-05-05
JP2007531136A (ja) 2007-11-01
EP1730658A1 (fr) 2006-12-13
GB2412756A (en) 2005-10-05
WO2005096178A8 (fr) 2006-02-09

Similar Documents

Publication Publication Date Title
US20050223031A1 (en) Method and apparatus for retrieving visual object categories from a database containing images
Fergus et al. A visual category filter for google images
US6763148B1 (en) Image recognition methods
Kakar et al. Exposing postprocessed copy–paste forgeries through transform-invariant features
US9092458B1 (en) System and method for managing search results including graphics
CN107609541B (zh) 一种基于可变形卷积神经网络的人体姿态估计方法
Beis et al. Indexing without invariants in 3d object recognition
CN102567483B (zh) 多特征融合的人脸图像搜索方法和系统
Bhattacharjee et al. Query adaptive instance search using object sketches
Devareddi et al. Review on content-based image retrieval models for efficient feature extraction for data analysis
Del Bimbo et al. Shape indexing by multi-scale representation
Jiang et al. Gestalt-based feature similarity measure in trademark database
Zachary et al. Content based image retrieval systems
EP1730658A1 (fr) Procede et appareil destines a extraire des categories d&#39;objets visuels d&#39;une base de donnees contenant des images
Cheikh MUVIS-a system for content-based image retrieval
Janu et al. Query-based image retrieval using SVM
Xu et al. Object segmentation and labeling by learning from examples
Mumtaz et al. A novel texture image retrieval system based on dual tree complex wavelet transform and support vector machines
Amelio Approximate matching in ACSM dissimilarity measure
Jaimes et al. Integrating multiple classifiers in visual object detectors learned from user input
Nayef Geometric-based symbol spotting and retrieval in technical line drawings
Amin et al. A novel image retrieval technique using automatic and interactive segmentation.
Nayef et al. Efficient symbol retrieval by building a symbol index from a collection of line drawings
Pitchandi Wild image retrieval with HAAR features and hybrid DBSCAN clustering for 3D cultural artefact landmarks reconstruction
Bashir et al. Fuzzy C-means based image retrieval system

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): BW GH GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
CFP Corrected version of a pamphlet front page
CR1 Correction of entry in section i

Free format text: IN PCT GAZETTE 41/2005 UNDER (72, 75) REPLACE "PERANA, PIETRO " BY "PERONA, PIETRO"

WWE Wipo information: entry into national phase

Ref document number: 2005729251

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2007505620

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

WWW Wipo information: withdrawn in national office

Country of ref document: DE

WWP Wipo information: published in national office

Ref document number: 2005729251

Country of ref document: EP