WO2008003985A2 - procédé d'identification de caractéristiques linéaires à l'intérieur d'une image - Google Patents

procédé d'identification de caractéristiques linéaires à l'intérieur d'une image Download PDF

Info

Publication number
WO2008003985A2
WO2008003985A2 PCT/GB2007/002549 GB2007002549W WO2008003985A2 WO 2008003985 A2 WO2008003985 A2 WO 2008003985A2 GB 2007002549 W GB2007002549 W GB 2007002549W WO 2008003985 A2 WO2008003985 A2 WO 2008003985A2
Authority
WO
WIPO (PCT)
Prior art keywords
image
ilp
target
phase
coefficients
Prior art date
Application number
PCT/GB2007/002549
Other languages
English (en)
Other versions
WO2008003985A3 (fr
Inventor
Nicholas Geoffrey Kingsbury
Ryan Alexander Anderson
Original Assignee
Cambridge Enterprise Limited
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 Cambridge Enterprise Limited filed Critical Cambridge Enterprise Limited
Publication of WO2008003985A2 publication Critical patent/WO2008003985A2/fr
Publication of WO2008003985A3 publication Critical patent/WO2008003985A3/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • 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
    • G06T2207/10016—Video; Image sequence
    • 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
    • G06T2207/20048—Transform domain processing
    • G06T2207/20064—Wavelet transform [DWT]

Definitions

  • a hysteresis window may be applied to any of these thresholds to reduce unnecessary splitting of a coherent edge.
  • Step 6 (reference numeral 62) Local maxima are identified within the blurred ILP coefficients, as shown in figure 3.
  • the cluster content descriptors may be used to match corresponding features of two separate images.
  • a cluster content descriptor may be used to determine whether or not a particular target feature occurs or does not occur in a sample image.
  • Our match method is split into two stages: a) estimation of a homography that transforms the target features onto the image features, and b) generation of a metric that rates and/or "fine-tunes" the final set of potential matches.
  • Geometric hashing provides a fast measure to reduce a large number of affine transformation hypotheses down to a reasonable number. We now wish to apply a metric to the remaining candidates to find the best matches.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un procédé d'identification de caractéristiques linéaires à l'intérieur d'une image utilisant une transformée à échelles multiples telle qu'une transformée d'ondelettes complexes à double arborescence. Des produits de mêmes niveaux et de niveaux intermédiaires sont calculés, et l'existence d'une caractéristique à l'intérieur de l'image est identifiée à un emplacement de magnitude de produits de niveaux intermédiaires localement élevée et cohérente. La caractéristique est ensuite étendue depuis cet emplacement dans une direction déterminée par la phase locale de produits de mêmes niveaux, pour générer un segment de ligne.
PCT/GB2007/002549 2006-07-07 2007-07-09 procédé d'identification de caractéristiques linéaires à l'intérieur d'une image WO2008003985A2 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
GB0613569.3 2006-07-07
GBGB0613569.3A GB0613569D0 (en) 2006-07-07 2006-07-07 Method of identifying linear features within an image

Publications (2)

Publication Number Publication Date
WO2008003985A2 true WO2008003985A2 (fr) 2008-01-10
WO2008003985A3 WO2008003985A3 (fr) 2008-08-07

Family

ID=36926668

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/GB2007/002549 WO2008003985A2 (fr) 2006-07-07 2007-07-09 procédé d'identification de caractéristiques linéaires à l'intérieur d'une image

Country Status (2)

Country Link
GB (1) GB0613569D0 (fr)
WO (1) WO2008003985A2 (fr)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101715097B (zh) * 2008-09-29 2012-01-04 索尼株式会社 图像处理设备和系数学习设备
US8866924B2 (en) 2011-10-28 2014-10-21 Hewlett-Packard Development Company, L.P. Local image feature descriptors according to circular distribution information
CN104200433A (zh) * 2014-08-25 2014-12-10 北京京北方信息技术有限公司 一种图像二维离散小波变换的扫描方法和装置
CN104077765B (zh) * 2013-03-26 2017-03-01 富士通株式会社 图像分割装置、图像分割方法
CN109033967A (zh) * 2018-06-26 2018-12-18 中国林业科学研究院资源信息研究所 一种林木密闭度测算的方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
RYAN ANDERSON, NICK KINGSBURY: "Robust image features from complex wavelet phases" 10 February 2006 (2006-02-10), BRITISH MACHINE VISION ASSOCIATION , XP002482913 Retrieved from the Internet: URL:http://www.bmva.ac.uk/meetings/06/01mar/AndersonCambridge.pdf> [retrieved on 2008-06-04] the whole document *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101715097B (zh) * 2008-09-29 2012-01-04 索尼株式会社 图像处理设备和系数学习设备
US8866924B2 (en) 2011-10-28 2014-10-21 Hewlett-Packard Development Company, L.P. Local image feature descriptors according to circular distribution information
CN104077765B (zh) * 2013-03-26 2017-03-01 富士通株式会社 图像分割装置、图像分割方法
CN104200433A (zh) * 2014-08-25 2014-12-10 北京京北方信息技术有限公司 一种图像二维离散小波变换的扫描方法和装置
CN104200433B (zh) * 2014-08-25 2017-07-28 京北方信息技术股份有限公司 一种图像二维离散小波变换的扫描方法和装置
CN109033967A (zh) * 2018-06-26 2018-12-18 中国林业科学研究院资源信息研究所 一种林木密闭度测算的方法和装置

Also Published As

Publication number Publication date
WO2008003985A3 (fr) 2008-08-07
GB0613569D0 (en) 2006-08-16

Similar Documents

Publication Publication Date Title
Li et al. Segmentation-based image copy-move forgery detection scheme
US9141871B2 (en) Systems, methods, and software implementing affine-invariant feature detection implementing iterative searching of an affine space
US20120301014A1 (en) Learning to rank local interest points
Hegenbart et al. A scale-and orientation-adaptive extension of local binary patterns for texture classification
KR101548928B1 (ko) 불변적인 시각적 장면 및 객체 인식
Davarzani et al. Scale-and rotation-invariant texture description with improved local binary pattern features
Niu et al. Fast and effective Keypoint-based image copy-move forgery detection using complex-valued moment invariants
CN108596867A (zh) 一种基于orb算法的图片校正方法及系统
US10866984B2 (en) Sketch-based image searching system using cell-orientation histograms and outline extraction based on medium-level features
JP2013541119A (ja) オブジェクト認識における特徴生成を改善するためのシステム及び方法
CN111753119A (zh) 一种图像搜索方法、装置、电子设备及存储介质
WO2008003985A2 (fr) procédé d'identification de caractéristiques linéaires à l'intérieur d'une image
Tang et al. Modified sift descriptor for image matching under interference
Nanni et al. Ensemble of shape descriptors for shape retrieval and classification
Sulthana et al. Implementation and evaluation of SIFT descriptors based finger-knuckle-print authentication system
Ng et al. Robust pairwise matching of interest points with complex wavelets
Amelio Approximate matching in ACSM dissimilarity measure
Wu et al. An accurate feature point matching algorithm for automatic remote sensing image registration
Tao et al. Research Progress of the Scale Invariant Feature Transform (SIFT) Descriptors.
Negrinho et al. Shape representation via elementary symmetric polynomials: a complete invariant inspired by the bispectrum
Jayaraman et al. An iris retrieval technique based on color and texture
Isnanto et al. Determination of the optimal threshold value and number of keypoints in scale invariant feature transform-based copy-move forgery detection
Li et al. A fast rotated template matching based on point feature
Fleck et al. Affine invariant-based classification of inliers and outliers for image matching
Kangas Comparison of local feature detectors and descriptors for visual object categorization

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 07766175

Country of ref document: EP

Kind code of ref document: A2

NENP Non-entry into the national phase in:

Ref country code: DE

NENP Non-entry into the national phase in:

Ref country code: RU

122 Ep: pct application non-entry in european phase

Ref document number: 07766175

Country of ref document: EP

Kind code of ref document: A2