WO2001084497A2 - Traitement des images - Google Patents

Traitement des images Download PDF

Info

Publication number
WO2001084497A2
WO2001084497A2 PCT/GB2001/001953 GB0101953W WO0184497A2 WO 2001084497 A2 WO2001084497 A2 WO 2001084497A2 GB 0101953 W GB0101953 W GB 0101953W WO 0184497 A2 WO0184497 A2 WO 0184497A2
Authority
WO
WIPO (PCT)
Prior art keywords
axial
edgelets
predetermined
axial line
pixels
Prior art date
Application number
PCT/GB2001/001953
Other languages
English (en)
Other versions
WO2001084497A3 (fr
Inventor
Mark Pawlewski
Charles Nightingale
Original Assignee
British Telecommunications Public Limited Company
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 British Telecommunications Public Limited Company filed Critical British Telecommunications Public Limited Company
Priority to AU2001252403A priority Critical patent/AU2001252403A1/en
Publication of WO2001084497A2 publication Critical patent/WO2001084497A2/fr
Publication of WO2001084497A3 publication Critical patent/WO2001084497A3/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
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras

Definitions

  • the present invention is concerned with image processing, and more particularly with - in a broad sense - image recognition.
  • recognition means that the image is processed to produce some result which makes a statement about the image.
  • a method of determining whether a digital image contains a feature having at least one prominent axial edge comprising the steps of: determining in accordance with a first predetermined criterion, for the pixels of the digital image, whether or not a pixel is an axial edgelet in relation to an axial line containing that pixel; and processing the pixels of a particular axial line of the digital image by the substeps of: counting, for that particular axial line, the number of said axial edgelets; counting, for that particular axial line, the number of linelets having a run length of axial edgelets greater than a predetermined number; evaluating a predetermined function of said number of axial edgelets and said number of linelets; and deeming that particular axial line to contain a said prominent axial edge if the evaluation meets a second predetermined criterion.
  • an apparatus for determining whether a digital image contains a feature having at least one prominent axial edge comprising: means for determining in accordance with a first predetermined criterion, for the pixels of the digital image, whether or not a pixel is an axial edgelet in relation to an axial line containing that pixel; and means for processing the pixels of a particular axial line of the digital image, said processing means comprising: means for counting, for that particular axial line, the number of said axial edgelets; means for counting, for that particular axial line, the number of linelets having a run length of axial edgelets greater than a predetermined number; means for evaluating a predetermined function of said number of axial edgelets and said number of linelets; and means for deeming that particular axial line to contain a said prominent axial edge if the evaluation meets a second predetermined criterion.
  • a method of determining whether a digital image contains a feature having at least one prominent axial edge comprising the steps of: determining in accordance with a first predetermined criterion, for the pixels of the digital image, whether or not a pixel is an axial edgelet in relation to an axial line containing that pixel; and processing the pixels of a particular axial line of the digital image by the substeps of: ascertaining, for that particular axial line, each linelet having a run length of axial edgelets greater than a predetermined number; counting the number of axial edgelets in said linelets so ascertained; evaluating a predetermined function of said number of axial edgelets; and deeming that particular axial line to contain a said prominent axial edge if the evaluation meets a second predetermined criterion.
  • an apparatus for determining whether a digital image contains a feature having at least one prominent axial edge comprising: means for determining in accordance with a first predetermined criterion, for the pixels of the digital image, whether or not a pixel is an axial edgelet in relation to an axial line containing that pixel; and means for processing the pixels of a particular axial line of the digital image, the processing means comprising: means for ascertaining, for that particular axial line, each linelet having a run length of axial edgelets greater than a predetermined number; counting the number of axial edgelets in said linelets so ascertained; means for evaluating a predetermined function of said number of axial edgelets; and means for deeming that particular axial line to contain a said prominent axial edge if the evaluation meets a second predetermined criterion.
  • Other, preferred, features of these aspects of the invention are set out in the sub-claims.
  • Figure 1 is a block diagram of an image recognition apparatus
  • Figure 2 is a flowchart illustrating the operation of the image recognition apparatus of Figure 1 ;
  • Figure 3 is an illustration of part of a database of images
  • Figure 4 is an illustration of images identified as landscapes using the image recognition apparatus of Figure 1
  • Figure 5 is an illustration of images identified as people using the image recognition apparatus of Figure 1 ;
  • Figure 6 is an illustration of images identified as buildings using the image recognition apparatus of Figure 1 ;
  • Figure 7 is an illustration of images identified as cartoons using the image recognition apparatus of Figure 1 ;
  • Figure 8 is a flowchart showing the operation of a building detector of the present invention.
  • Figure 9 is a flowchart illustrating operation of a vertical edgelet detector
  • Figures 10a, 10b and 10c show the results of application of a building detector according to the present invention to an image
  • Figure 1 1 is a flowchart showing the operation of a landscape detector used in the image recognition apparatus of Figure 1 ;
  • Figure 1 2 is a flowchart illustrating operation of a horizontal edgelet detector;
  • Figures 13a, 13b, and 13c show the results of application of a landscape detector to an image
  • Figures 14a, 14b, and 14c show the results of application of a landscape detector to a second image
  • Figures 15a, 15b, and 15c show the results of application of a landscape detector to a third image
  • Figure 1 6 is a flowchart illustrating the method steps used to apply logic to make a single decision regarding an image.
  • an image recognition apparatus comprising an acquisition device 1 which is in the form of a scanner for scanning photographs or slides.
  • the acquisition device is arranged to capture single frames from a video signal.
  • Acquisition devices are well-known, as indeed is software for driving the devices and storing the resulting image in digital form.
  • the apparatus also has an image store 2 for receiving the digital image, a processing unit 3 and a program store 4. In the present embodiment, these items are conveniently implemented in the form of a conventional desktop computer.
  • the program store 4 contains a program for implementing the process now to be described.
  • the program performs the following method steps as illustrated in Figure 2.
  • step 20 building recognition in accordance with the present invention is performed. The process will be described in more detail later with reference to Figures 8, 9 and 10.
  • step 22 landscape recognition is performed, this process will be described in more detail later with reference to Figures 1 1 to 1 5.
  • Cartoon recognition is then performed at step 24.
  • Cartoon recognition may be performed, for example using the methods described in our co-pending European applications number 99307971 .4 and 00301687.0.
  • the final recognition step is performance of skin recognition at step 26.
  • the choice of skin recognition technique used in the present invention is not significant, and can be any of such techniques known in the art.
  • the recognition steps 20 to 26 may be performed in any order, as each step is independent of the other steps.
  • FIG. 28 logic is applied to decide upon a single classification of an image in case of conflict between the output from the recognition steps.
  • Figures 3 to 7 show how images in a database, a subset of which is shown in Figure 3, are classified as a building, a landscape, a person or a cartoon by the apparatus of Figure 1 . It can be seen from visual inspection of this small sample that the images in Figure 4, which have been classified as landscapes, are indeed subjectively identifiable as such. Similarly all the images of Figure 5 have been correctly classified by this described embodiment of the invention as containing people within the image. The images in Figure 6 have been classified as buildings, although some of the images, for example the leftmost image in the middle row, contain people and a water feature.
  • a method of vertical structure detection using perceptual grouping techniques is now described with reference to Figure 8.
  • the method is used in this embodiment of the invention to recognise features of the image which have at least one prominent axial edge, such features being most commonly buildings, or man- made structures in which vertical lines are prominent.
  • luminance values may be calculated from these luminance values in a conventional manner (step 80). Colour information is not used in this embodiment of the invention.
  • edge detection methods of edge detection are well known, however the method described here for detection of horizontal and vertical edgelets (small edges) are specifically designed to detect edges which extend in a direction which is parallel to the direction of the axis of the pixels in a digital image. In other words, along an axial line, i.e. a row or a column of a rectangular image.
  • axial edgelet or edgelet point or edgelet pixel
  • linelet is used to refer to a run of axial edgelets extending along an axial line. In the specific embodiment described the linelets extend in the vertical and horizontal direction.
  • each pixel is analysed to decide whether the pixel is an axial edgelet forming part of a vertical linelet within the image.
  • each pixel is analysed in turn with each vertical line of pixels being analysed in ascending order of horizontal index, and for each pixel point in each vertical line, in ascending order of vertical index.
  • the gradient of each point is measured as shown at steps 91 and 92.
  • step 91 the difference between the luminance value of the pixel to the left of the current pixel and the luminance value of the current pixel and the difference between the luminance value of the pixel below the current pixel and the luminance value of the current pixel are calculated.
  • the angle and the gradient (dy/dx) calculated at step 92 would be small.
  • a decision process is then used at step 95 to decide whether or not each pixel gives evidence of a strong gradient in the horizontal direction.
  • FIG. 10a shows an image
  • Figure 10b shows the corresponding pixels which are determined to be part of a vertical linelet as determined by the method described above.
  • E(i,k) (the axial edgelet aggregate) is a sum of the number of points which are determined, as above, to be axial edgelets.
  • the variable e W k is defined as the number of linelets of length w in the column k.
  • the maximum value for w N.
  • Wk is effectively a count of the linelets of run length greater than or equal to Pmin.
  • One method is to apply the following thresholds, namely Amin, Wmin and Lmin, which, as defined below, depend upon the size of the image in pixels.
  • Another method is to train neural net using the three parameters as an input and with a set of classified images as a training set. Another method would be by making Wk an inverse function of the maximum length of a linelet, i.e. run of adjacent edgelets, in column k.
  • This system will spot broken vertical lines, although some continuous pieces are required if either Pmin or Rmin is greater than one. It will be appreciated that If Rmin is equal to one then Ak and Lk are equivalent. If Pmin is equal to one then Wk is a count of the total number of linelets.
  • the presence of a vertical line is detected on the basis of a function of only Ak and Wk, i.e.
  • both Ak and Wk are greater than or equal to their respective thresholds; and in a second variant, the presence of a vertical line is detected on the basis of a function of only Lk. i.e. that Lk is greater than or equal to its threshold.
  • vertical edgelets are determined using two columns of adjacent pixels only.
  • function F(x,y) which operated using the average gradient over more than two columns of adjacent pixels.
  • function W so that it operated over plurality of columns. The number of columns over which each of these functions operates could be dependent upon the width of the image.
  • Pmin Amin, Wmin, Lmin, Rmin and Cmin are calculated based on absolute predetermined percentage values and on the size of the image between the y co-ordinate (ImageTop) of the top of the edgelet nearest to the top of the image and the y coordinate (ImageBottom) of the bottom of the edgelet nearest the bottom of the image, and correspondingly on the size of the image between the x co-ordinate (ImageRight) of the right of the edgelet nearest to the right of the image and the x co-ordinate (ImageLeft) of the left of the edgelet nearest the left of the image, as follows:
  • step 82 Wk is calculated for each column.
  • Figure 10c shows an image in which the pixels which meet the criteria of step 83 in Figure 8 are highlighted (in white).
  • step 87 is performed after the step 81 and before the step 82, in a variant, the step 87 is performed after the step 80 and before the step 81 .
  • FIG. 1 1 a method of landscape recognition using perceptual grouping will now be described.
  • the method is based on the observation that many landscapes have horizontal continua extending across a large proportion of the image. Sometimes one of the lines is due to the horizon, but the inventors have discovered the surprising result that many images of landscapes have such horizontal continua, which do not correspond to the presence of the horizon.
  • the image is converted to grey scale, if required.
  • each pixel is analysed to decide whether the pixel forms part of an linelet within the image.
  • the previously described method of determining whether a pixel is a vertical edgelet is modified mutatis mutandis as follows to determine whether a pixel is a horizontal edgelet.
  • the method of edgelet detection used in this embodiment may be used to detect edgelets which extend in a direction parallel to the orientation of pixels in the image.
  • each pixel is analysed in turn with each horizontal line of pixels being analysed in ascending order of vertical index, and for each point in each horizontal line in ascending order of horizontal index.
  • the gradient of each point is measured as shown at step 1 21 and 1 22.
  • the difference between the luminance value of the pixel to the left of the current pixel and the luminance value of the current pixel and the difference between the luminance value of the pixel below the current pixel and the luminance value of the current pixel are calculated.
  • the angle which is not the same angle as that described above for detecting vertical edgelets
  • the gradient (dy/dx), calculated at step 1 22, would be large.
  • a decision process is then used at step 1 25 to decide whether or not each pixel gives evidence of a strong gradient in the vertical direction.
  • the pixel is considered to be a horizontal edgelet at step 1 26 and E(x,y) is set to be equal to 1 , otherwise is it not a horizontal edgelet, as shown at step 1 27 and E(x,y) is set to be equal to 0.
  • FIG. 1 3a, 14a and 1 5a show an image
  • Figures 13b, 14b, 1 5b show the corresponding pixels which are determined to be part of a horizontal linelet as determined by the method described above.
  • Rmin is a predetermined minimum value of w which depends upon the size of the image in pixels.
  • Hmin and Lmin are calculated based on absolute predetermined percentage values and on the size of the image between the rightmost x co-ordinate (ImageRight) of the edgelet nearest to the right of the image and the leftmost x co-ordinate (ImageLeft) of the edgelet nearest the left of the image as follows:
  • Hmin Hminpe cent * (ImageRight - ImageLeft)
  • Lmin Lminpercent * (ImageRight - ImageLeft)
  • Lk is calculated for each row.
  • the maximum value for Lr is calculated. If Lma is greater than Lmin then the image is determined to be a landscape at step 1 1 6. Otherwise the image is determined not to be a landscape at step 1 1 6.
  • Figures 1 3c, 14c and 1 5c show images in which the horizontal lines responsible for L a are highlighted at 1 30, 140 and 1 50 respectively. It is worth noting that these horizontal lines do not necessarily coincide with the horizon. In the method just described, it would be possible to terminate the algorithm once an Lk is calculated which is greater than Wmin. However, it is desirable to calculate the greatest Lk, i.e. Lmax as then the 'best' horizontal line can be detected in the image.
  • the final step 28 shown in Figure 2 is shown in more detail in Figure 16.
  • the outputs from the previous steps are considered and the image is classified as being one of a building, a landscape, a cartoon, a person or unclassified.
  • the cartoon recognition step 24 resulted in a cartoon being identified then the image is classified as a cartoon.
  • the building recognition of step 20 resulted in the image being identified as a building and the skin recognition step 26 resulted in the image being identified as a person then the image is classified as a building.
  • the building recognition of step 20 resulted in the image being identified as a building and the landscape recognition step 22 resulted in the image being identified as a landscape then the image is classified as a building.
  • the landscape recognition step 22 resulted in the image being classified as a landscape and the skin recognition step 26 resulted in the image being classified as a person then the image is classified as a landscape.

Landscapes

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

Abstract

Les contours sont utilisés par les êtres humains pour classifier des objets et émuler une telle classification au moyen d'un algorithme informatique est extrêmement difficile. Un être humain ne requiert que des contours partiaux qui, avec des variations de texture et de tonalité, sont suffisants pour interpréter des images, la capacité de tracer des contours survenant plutôt après la reconnaissance d'un objet qu'avant. Le procédé de détection de contours utilisé dans cette invention permet de détecter les contours minimes horizontaux et verticaux qui s'étendent dans une direction parallèle à la direction de l'axe des pixels dans une image numérique. Les contours minimes verticaux détectés selon cette invention sont ensuite traités de manière à déterminer si une image représente un bâtiment.
PCT/GB2001/001953 2000-05-04 2001-05-03 Traitement des images WO2001084497A2 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2001252403A AU2001252403A1 (en) 2000-05-04 2001-05-03 Image processing

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP00303740 2000-05-04
EP00303740.5 2000-05-04

Publications (2)

Publication Number Publication Date
WO2001084497A2 true WO2001084497A2 (fr) 2001-11-08
WO2001084497A3 WO2001084497A3 (fr) 2003-01-23

Family

ID=8172959

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/GB2001/001953 WO2001084497A2 (fr) 2000-05-04 2001-05-03 Traitement des images

Country Status (2)

Country Link
AU (1) AU2001252403A1 (fr)
WO (1) WO2001084497A2 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103020951A (zh) * 2011-09-26 2013-04-03 江南大学 特征值提取方法及系统
WO2015123646A1 (fr) * 2014-02-14 2015-08-20 Nant Holdings Ip, Llc Systèmes et procédés de reconnaissance utilisant les bords
CN106415606A (zh) * 2014-02-14 2017-02-15 河谷控股Ip有限责任公司 一种基于边缘的识别、系统和方法

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000113201A (ja) * 1998-10-09 2000-04-21 Nec Corp 車両検出方法および装置

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000113201A (ja) * 1998-10-09 2000-04-21 Nec Corp 車両検出方法および装置

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
LIN C ET AL: "DETECTION OF BUILDINGS USING PERCEPTUAL GROUPING AND SHADOWS" PROCEEDINGS OF THE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION. SEATTLE, JUNE 21 - 23, 1994, LOS ALAMITOS, IEEE COMP. SOC. PRESS, US, 21 June 1994 (1994-06-21), pages 62-69, XP000515822 ISBN: 0-8186-5827-4 *
MCGLONE J C ET AL: "Projective and object space geometry for monocular building extraction" COMPUTER VISION AND PATTERN RECOGNITION, 1994. PROCEEDINGS CVPR '94., 1994 IEEE COMPUTER SOCIETY CONFERENCE ON SEATTLE, WA, USA 21-23 JUNE 1994, LOS ALAMITOS, CA, USA,IEEE COMPUT. SOC, 21 June 1994 (1994-06-21), pages 54-61, XP010099259 ISBN: 0-8186-5825-8 *
VENKATESWAR V ET AL: "EXTRACTION OF STRAIGHT LINES IN AERIAL IMAGES" SIGNAL PROCESSING THEORIES AND APPLICATIONS. BARCELONA, SEPT. 18 - 21, 1990, PROCEEDINGS OF THE EUROPEAN SIGNAL PROCESSING CONFERENCE, AMSTERDAM, ELSEVIER, NL, vol. 3 CONF. 5, 18 September 1990 (1990-09-18), pages 1671-1674, XP000365884 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103020951A (zh) * 2011-09-26 2013-04-03 江南大学 特征值提取方法及系统
WO2015123646A1 (fr) * 2014-02-14 2015-08-20 Nant Holdings Ip, Llc Systèmes et procédés de reconnaissance utilisant les bords
CN106415606A (zh) * 2014-02-14 2017-02-15 河谷控股Ip有限责任公司 一种基于边缘的识别、系统和方法
US9665606B2 (en) 2014-02-14 2017-05-30 Nant Holdings Ip, Llc Edge-based recognition, systems and methods
US10083366B2 (en) 2014-02-14 2018-09-25 Nant Holdings Ip, Llc Edge-based recognition, systems and methods
CN106415606B (zh) * 2014-02-14 2019-11-08 河谷控股Ip有限责任公司 一种基于边缘的识别、系统和方法
US11176406B2 (en) 2014-02-14 2021-11-16 Nant Holdings Ip, Llc Edge-based recognition, systems and methods

Also Published As

Publication number Publication date
AU2001252403A1 (en) 2001-11-12
WO2001084497A3 (fr) 2003-01-23

Similar Documents

Publication Publication Date Title
US7657090B2 (en) Region detecting method and region detecting apparatus
KR100422370B1 (ko) 3차원 물체 부피계측시스템 및 방법
KR100936108B1 (ko) 물체 검출 장치 및 엘리베이터의 물체 검출 장치
CN111047655B (zh) 基于卷积神经网络的高清摄像机布料疵点检测方法
CN105261021B (zh) 去除前景检测结果阴影的方法及装置
CN106373125B (zh) 一种基于信息熵的雪花噪声检测方法
JP6095817B1 (ja) 物体検出装置
JP5264457B2 (ja) 物体検出装置
Aviram et al. Evaluating human detection performance of targets and false alarms, using a statistical texture image metric
JP2010277431A (ja) 対象物検出装置
JP5253195B2 (ja) 物体検出装置
CN110349133B (zh) 物体表面缺陷检测方法、装置
Chetverikov Structural defects: General approach and application to textile inspection
WO2001084497A2 (fr) Traitement des images
KR100194583B1 (ko) 얼굴 구성요소 추출시스템 및 그 추출방법
JP3483912B2 (ja) 色判別装置および色判別方法
Desoli et al. A system for automated visual inspection of ceramic tiles
JP3957495B2 (ja) 画像センサ
WO2001084498A2 (fr) Traitement d'image
JP2009059047A (ja) 対象物検出装置、対象物検出方法、および対象物検出プログラム
KR101032581B1 (ko) 유해영상 자동 판별 방법
JP2001307286A (ja) 交通流計測装置
CN109670495A (zh) 一种基于深度神经网络的长短文本检测的方法及系统
EP0725362B1 (fr) Méthode d'extraction d'une zone texturée d'une image d'entrée
JP6891792B2 (ja) 測定プログラム、測定装置および測定方法

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EE 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 NO NZ PL PT RO RU SD SE SG SI SK SL TJ TM TR TT TZ UA UG US UZ VN YU ZA ZW

AL Designated countries for regional patents

Kind code of ref document: A2

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

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
122 Ep: pct application non-entry in european phase
NENP Non-entry into the national phase in:

Ref country code: JP