EP2700050A1 - Analysis of the digital image of the external surface of a tyre and processing of false measurement points - Google Patents

Analysis of the digital image of the external surface of a tyre and processing of false measurement points

Info

Publication number
EP2700050A1
EP2700050A1 EP12710502.1A EP12710502A EP2700050A1 EP 2700050 A1 EP2700050 A1 EP 2700050A1 EP 12710502 A EP12710502 A EP 12710502A EP 2700050 A1 EP2700050 A1 EP 2700050A1
Authority
EP
European Patent Office
Prior art keywords
image
tire
gray level
inspected
transformation
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Withdrawn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
EP12710502.1A
Other languages
German (de)
French (fr)
Inventor
Jean-Paul Zanella
Claire Moreau
Guillaume Noyel
Yusi SHEN
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.)
Michelin Recherche et Technique SA Switzerland
Compagnie Generale des Etablissements Michelin SCA
Michelin Recherche et Technique SA France
Original Assignee
Michelin Recherche et Technique SA Switzerland
Compagnie Generale des Etablissements Michelin SCA
Michelin Recherche et Technique SA France
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 Michelin Recherche et Technique SA Switzerland, Compagnie Generale des Etablissements Michelin SCA, Michelin Recherche et Technique SA France filed Critical Michelin Recherche et Technique SA Switzerland
Publication of EP2700050A1 publication Critical patent/EP2700050A1/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G06T5/70—
    • 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
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00—Testing of vehicles
    • G01M17/007—Wheeled or endless-tracked vehicles
    • G01M17/02—Tyres
    • G01M17/027—Tyres using light, e.g. infrared, ultraviolet or holographic techniques
    • G06T3/10—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration by the use of local operators
    • G06T5/30—Erosion or dilatation, e.g. thinning
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/952—Inspecting the exterior surface of cylindrical bodies or wires
    • 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
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • 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
    • G06T2207/20036—Morphological image processing
    • 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
    • G06T2207/30108—Industrial image inspection
    • 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
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component

Definitions

  • the invention relates to the field of tire manufacturing and more particularly to the field of automatic inspection of the surface of a tire in order to establish a conformity diagnosis with respect to pre-established references.
  • One of the steps of this process consists, in known manner, in acquiring the three-dimensional image of the surface of the tire. [003]
  • the acquisition of this image is done using means based on the principle of optical triangulation, implementing for example a 2D sensor coupled to a laser-type lighting source.
  • the topographic image of the tire surface is in fact a two-dimensional image, called a gray level, in which, at any point, ie at any pixel (x, y) of the image, a value is associated with f (x, y), called gray level, and usually between 0 and 255.
  • This gray level value can usefully be coded on 8, or 16 bits for better dynamics.
  • the gray level represents the altitude of this point relative to the surface. For 8-bit encoding, the value 255 (white) corresponds to the highest altitude, and the value 0 (black) corresponds to the lowest altitude.
  • the pixels of the image are arranged in line and in columns.
  • the method of processing the three-dimensional digital image of the outer surface of a tire according to the invention provides for the use of image processing methods using tools of the morphological type.
  • the morphological erosion or dilation operations consist, for each point of an image, to find the minimum value or the maximum value of gray level of the neighboring points included inside a structuring element , of given shape and area, centered on the point to be analyzed and defining a neighborhood of this point. For an erosion the value at this point then becomes the minimum value, and for a dilation the value at this point becomes the maximum value.
  • the combination of erosion followed by expansion is called opening, and the combination of dilation followed by erosion is called closure.
  • the morphological gradient type operator delimits the zones of strong variation of relief, i. e. outline.
  • a gray level value is assigned equal to the difference between the level value of gis obtained after an expansion and the value of gray level obtained after erosion.
  • the method according to the invention After realizing the three-dimensional image of the surface of said tire in which each pixel of the image contains information relating to the elevation of the corresponding point of the surface to be inspected, the method according to the invention provides for a first transformation of the image of the surface by means of an opening then a closure, so as to recalculate the gray level of the pixels situated abnormally above or below the surface to be inspected.
  • the gray level of each pixel is representative of the elevation of the point corresponding to the surface to be inspected.
  • the morphological operator to perform the opening and closing is a square.
  • a square whose width is between 8 and 15 pixels corresponding to a size slightly greater than the size of the non-measurement zones.
  • a second transformation is then performed after having carried out the first transformation of the image of the surface, in which:
  • the contour elements of the relief of the surface are determined using a morphological operator of the gradient type, followed by a thresholding for extracting the contours of the relief,
  • the morphological operator used to determine the contours of the relief is a square.
  • This method is preferably applied to the inspection of the external surface of the tire.
  • FIGS. 1 to 5 The following description is based on FIGS. 1 to 5 in which:
  • FIG. 1 represents a schematic view of a means of capturing the image of the surface of a tire
  • FIG. 2 represents a view of the image of the external surface of a tire coming directly from the image capture means
  • FIG. 3 represents the partial image of the outer surface after treatment using the first transformation
  • FIG. 4 represents the image of the contours of the reliefs of the external surface of the tire
  • FIG. 1 The acquisition of the image of the surface of a tire is illustrated in FIG. 1. This acquisition is effected by way of example using a slot light emitted by a laser. 1 and a camera 3 capable of capturing the 2D image of the illuminated surface. The camera is positioned so that its aiming direction makes a given angle with the beam emitted by the laser source. By triangulation, it is then possible to determine the coordinates of the relief element 2 relative to the support surface 4.
  • the slot light is directed in an axial or radial direction perpendicular to the circumferential direction corresponding to the direction the rotation imposed on the tire to capture a complete image of its surface.
  • Figure 2 shows the image from this seizure. We observe the presence of false measurement points, noted PFM, whose presence is particularly marked on the edges of the reliefs of the sculpture.
  • This first treatment uses a morphological operator of square shape.
  • the size of this operator is adjusted to the size of the defects that one seeks to filter. In this case, good results are obtained with an operator whose area of the square is of the order of a hundred pixels and whose side is wide of ten pixels.
  • FIG. 1 is a partial view of the image of the tire surface after the completion of the first treatment.
  • this residual of abnormal values is preferentially concentrated or level zones corresponding to a strong variation of the relief.
  • Figure 4 illustrates the result of this operation which detaches from the bottom of the image the only values of the contours of the reliefs of the surface.
  • the second treatment is intended to reduce the false measurement values in the narrow band representing the contours of the reliefs. To do this, we assign to each pixel of this area, the value of gray level equal to the value obtained after the first transformation.
  • Figure 5 illustrates the result obtained after the implementation of the first and second treatment. It is observed that the false measurement points have completely disappeared and are no longer likely to disturb the digital image processing in order to perform the inspection of the conformity of the surface of the tire.
  • this method is particularly applicable to areas showing strong variations of relief and therefore to the external parts of the tire surface.
  • this same method it is not excluded to use this same method to refine the images of the inner part of the tire when the latter comprise relief elements such as streaks.

Abstract

The invention relates to a method for processing the three-dimensional digital image of the surface of a tyre, in which the three-dimensional image of the surface is captured and each pixel of the plane of the image is assigned a datum relating to the elevation of this point in relation to the surface to be inspected. The method is characterised in that, with the aid of a morphological operator using a structuring element, a first transformation of the surface is performed, by means of opening followed by closing, such as to adjust the grey scale of pixels located abnormally above or below the surface to be inspected.

Description

ANALYSE DE L'IMAGE NUMERIQUE DE LA SURFACE EXTERNE D'UN PNEUMATIQUE-TRAITEMENT DES POINTS DE FAUSSE MESURE  ANALYSIS OF THE DIGITAL IMAGE OF THE EXTERNAL SURFACE OF A PNEUMATIC-TREATMENT OF FAILURE MEASUREMENT POINTS
[001] L'invention concerne le domaine de la fabrication des pneumatiques et plus particulièrement le domaine de l'inspection automatique de la surface d'un pneumatique en vue d'établir un diagnostic de conformité par rapport à des références préétablies. [001] The invention relates to the field of tire manufacturing and more particularly to the field of automatic inspection of the surface of a tire in order to establish a conformity diagnosis with respect to pre-established references.
[002] Une des étapes de ce processus consiste, de manière connue, à acquérir l'image en trois dimensions de la surface du pneumatique. [003] L'acquisition de cette image se fait à l'aide de moyens basés sur le principe de la triangulation optique, mettant par exemple en œuvre un capteur 2D couplé à une source d'éclairage de type laser. One of the steps of this process consists, in known manner, in acquiring the three-dimensional image of the surface of the tire. [003] The acquisition of this image is done using means based on the principle of optical triangulation, implementing for example a 2D sensor coupled to a laser-type lighting source.
[004] L'image topographique de la surface du pneumatique est en fait une image bidimensionnelle, dite à niveau de gris, dans laquelle, à tout point, i.e. à tout pixel (x, y) de l'image, est associé une valeur f(x, y), appelée niveau de gris, et généralement comprise entre 0 et 255. Cette valeur de niveau de gris peut utilement être codée sur 8, ou 16 bits pour une meilleure dynamique. Le niveau de gris représente l'altitude de ce point par rapport à la surface. Pour un codage sur 8 bits, la valeur 255 (blanc) correspond à l'altitude la plus haute, et la valeur 0 (noir), correspond à l'altitude la plus basse. En règle générale les pixels de l'image sont disposés en ligne et en colonne. [004] The topographic image of the tire surface is in fact a two-dimensional image, called a gray level, in which, at any point, ie at any pixel (x, y) of the image, a value is associated with f (x, y), called gray level, and usually between 0 and 255. This gray level value can usefully be coded on 8, or 16 bits for better dynamics. The gray level represents the altitude of this point relative to the surface. For 8-bit encoding, the value 255 (white) corresponds to the highest altitude, and the value 0 (black) corresponds to the lowest altitude. As a general rule, the pixels of the image are arranged in line and in columns.
[005] On observe toutefois que l'image de la surface issue de ces moyens d'acquisition peut présenter des points de fausse mesure qu'il est nécessaire de repérer et de faire disparaître avant d'entreprendre les traitements numériques ultérieurs. Faute de quoi, les algorithmes d'analyse pourraient considérer à tort ces zones comme des anomalies structurelles du pneumatique à inspecter. [005] However, it is observed that the image of the surface resulting from these acquisition means may have points of false measurement that it is necessary to identify and remove before undertaking the subsequent digital processing. Otherwise, the analysis algorithms may mistakenly consider these areas as structural anomalies of the tire to be inspected.
[006] Ces points apparaissent en règle générale dans les zones présentant une variation de relief important en raison de l'angle d'incidence de la lumière sur la surface du pneumatique à inspecter. La caméra enregistre à tort les informations provenant de la lumière réfléchie, au lieu de considérer les informations provenant du faisceau incident. Cette situation se présente en règle générale lorsqu'on considère la surface externe du pneumatique notamment en bordure des pains de la sculpture. [006] These points appear as a rule in the areas having a significant variation in relief due to the angle of incidence of the light on the surface of the tire to be inspected. The camera incorrectly records the information from the reflected light, instead of considering information from the incident beam. This situation arises as a rule when considering the external surface of the tire including the edge of the breads of the sculpture.
[007] Tous ces points, dits de fausse mesure, se distinguent par le fait qu'ils ont des positions très décalées par rapport aux points situés dans leur environnement immédiat. On entend ici par très décalé en positif (en bosse) ou en négatif (en creux), un décalage supérieur à 4 ou 5mm, qui se distingue donc nettement des variations de profil apparaissant de manière commune à la surface d'un pneumatique. [008] L'invention a pour objet de proposer une méthode de traitement simple permettant d'identifier ces points, ainsi qu'une méthode de correction des valeurs numériques décrivant la surface. [007] All these points, said to be false, are distinguished by the fact that they have positions very out of step with the points in their immediate environment. Here is meant by very positive shifted (bump) or negative (hollow), a shift greater than 4 or 5mm, which is clearly distinguishable from the profile variations appearing common to the surface of a tire. [008] The invention aims to provide a simple method of processing to identify these points, as well as a method of correcting the numerical values describing the surface.
[009] La méthode de traitement de l'image numérique tridimensionnelle de la surface externe d'un pneumatique selon l'invention prévoit l'utilisation des méthodes de traitement d'image à l'aide des outils de type morphologique. [009] The method of processing the three-dimensional digital image of the outer surface of a tire according to the invention provides for the use of image processing methods using tools of the morphological type.
[010] Ces méthodes consistent, de manière connue, à modifier les motifs de l'image avec des outils permettant de l'éroder ou de le dilater. Ce qui revient dans le cas présent à modifier les reliefs de la surface à inspecter. [010] These methods consist, in known manner, in modifying the image patterns with tools for eroding or expanding. What amounts in this case to modify the reliefs of the surface to be inspected.
[011] Les opérations morphologiques d'érosion ou de dilatation consistent, pour chaque point d'une l'image, à rechercher la valeur minimale ou la valeur maximale de niveau de gris des points voisins compris à l'intérieur d'un élément structurant, de forme et de surface données, centré sur le point à analyser et définissant un voisinage de ce point. Pour une érosion la valeur en ce point devient alors la valeur minimale, et pour une dilatation la valeur en ce point devient la valeur maximale. La combinaison d'une érosion suivie d'une dilatation est dénommée ouverture, et la combinaison d'une dilatation suivie d'une érosion est dénommée fermeture. [011] The morphological erosion or dilation operations consist, for each point of an image, to find the minimum value or the maximum value of gray level of the neighboring points included inside a structuring element , of given shape and area, centered on the point to be analyzed and defining a neighborhood of this point. For an erosion the value at this point then becomes the minimum value, and for a dilation the value at this point becomes the maximum value. The combination of erosion followed by expansion is called opening, and the combination of dilation followed by erosion is called closure.
[012] L'opérateur de type gradient morphologique permet de délimiter les zones de forte variation de relief, i. e. les contours. En chaque point de l'image, on affecte une valeur de niveau de gris égale à la différence entre la valeur de niveau de gis obtenue après une dilatation et la valeur de niveau de gris obtenue après érosion. [012] The morphological gradient type operator delimits the zones of strong variation of relief, i. e. outline. In each point of the image, a gray level value is assigned equal to the difference between the level value of gis obtained after an expansion and the value of gray level obtained after erosion.
[013] Après avoir réalisé l'image tridimensionnelle de la surface dudit pneumatique dans laquelle chaque pixel de l'image contient une information relative à l'élévation du point correspondant de la surface à inspecter, la méthode selon l'invention prévoit d'effectuer une première transformation de l'image de la surface à l'aide d'une ouverture puis d'une fermeture, de manière à recalculer le niveau de gris des pixels situés anormalement au-dessus ou au-dessous de la surface à inspecter. [013] After realizing the three-dimensional image of the surface of said tire in which each pixel of the image contains information relating to the elevation of the corresponding point of the surface to be inspected, the method according to the invention provides for a first transformation of the image of the surface by means of an opening then a closure, so as to recalculate the gray level of the pixels situated abnormally above or below the surface to be inspected.
[014] Le niveau de gris de chaque pixel est représentatif de l'élévation du point correspondant de la surface à inspecter. [014] The gray level of each pixel is representative of the elevation of the point corresponding to the surface to be inspected.
[015] De préférence, l'opérateur morphologique pour effectuer l'ouverture et la fermeture est un carré. On choisira avantageusement un carré dont la largeur est comprise entre 8 et 15 pixels correspondant à une taille légèrement supérieure à la taille des zones de non mesure. [015] Preferably, the morphological operator to perform the opening and closing is a square. We will advantageously choose a square whose width is between 8 and 15 pixels corresponding to a size slightly greater than the size of the non-measurement zones.
[016] Il est possible d'affiner la détection et l'élimination des points de fausse mesure en observant que, dans le cas de l'image d'un pneumatique, les points de fausse mesure sont situés préférentiellement dans les zones présentant de fortes variations de relief et situées de ce fait au niveau des contours. [017] On effectue alors une deuxième transformation, après avoir réalisé la première transformation de l'image de la surface, dans laquelle : [016] It is possible to refine the detection and the elimination of the false measurement points by observing that, in the case of the image of a tire, the false measurement points are preferably located in the zones presenting strong variations of relief and thus located at the contours. [017] A second transformation is then performed after having carried out the first transformation of the image of the surface, in which:
on détermine les éléments de contours du relief de la surface en utilisant un opérateur morphologique de type gradient, suivie d'un seuillage permettant d'extraire les contours du relief,  the contour elements of the relief of the surface are determined using a morphological operator of the gradient type, followed by a thresholding for extracting the contours of the relief,
- on affecte à chaque pixels du contour, la valeur de niveau de gris égale à la valeur obtenue après la première transformation.  - is assigned to each pixel of the contour, the value of gray level equal to the value obtained after the first transformation.
[018] De préférence l'opérateur morphologique utilisé pour déterminer les contours du relief est un carré. On choisira avantageusement un carré dont la largeur est comprise entre 8 et 15 pixels. [019] Cette méthode s'applique de manière préférentielle à l'inspection de la surface externe du pneumatique. [018] Preferably the morphological operator used to determine the contours of the relief is a square. We will advantageously choose a square whose width is between 8 and 15 pixels. [019] This method is preferably applied to the inspection of the external surface of the tire.
[020] La description qui suit s'appuie sur les figures 1 à 5 dans lesquelles : [020] The following description is based on FIGS. 1 to 5 in which:
La figure 1 représente une vue schématique d'un moyen de capture de l'image de la surface d'un pneumatique,  FIG. 1 represents a schematic view of a means of capturing the image of the surface of a tire,
- la figure 2 représente une vue de l'image de la surface extérieure d'un pneumatique issue directement des moyens de capture de l'image,  FIG. 2 represents a view of the image of the external surface of a tire coming directly from the image capture means,
la figure 3 représente l'image partielle de la surface extérieure après traitement à l'aide de la première transformation,  FIG. 3 represents the partial image of the outer surface after treatment using the first transformation,
la figure 4 représente l'image les contours des reliefs de la surface extérieure du pneumatique,  FIG. 4 represents the image of the contours of the reliefs of the external surface of the tire,
l'image de la figure 5 représente une vue de la surface extérieure après traitement à l'aide de la première et de la seconde transformation. [021] L'acquisition de l'image de la surface d'un pneumatique est illustrée à la figure 1. Cette acquisition s'opère, à titre d'exemple, à l'aide d'une lumière de fente émise par un laser 1 et d'une caméra 3 apte à capter l'image 2D de la surface éclairée. La caméra est positionnée de sorte que sa direction de visée fasse un angle donné a avec le faisceau émis par la source laser. Par triangulation, il est alors possible de déterminer les coordonnées de l'élément de relief 2 par rapport à la surface support 4. En règle générale, la lumière de fente est dirigée selon une direction axiale ou radiale perpendiculairement à la direction circonférentielle correspondant au sens de la rotation imposée au pneumatique pour saisir une image complète de sa surface. [022] La figure 2 représente l'image issue de cette saisie. On observe la présence de points de fausse mesure, notés PFM, dont la présence est particulièrement marquée sur les bords des reliefs de la sculpture. the image of Figure 5 shows a view of the outer surface after treatment using the first and the second transformation. [021] The acquisition of the image of the surface of a tire is illustrated in FIG. 1. This acquisition is effected by way of example using a slot light emitted by a laser. 1 and a camera 3 capable of capturing the 2D image of the illuminated surface. The camera is positioned so that its aiming direction makes a given angle with the beam emitted by the laser source. By triangulation, it is then possible to determine the coordinates of the relief element 2 relative to the support surface 4. In general, the slot light is directed in an axial or radial direction perpendicular to the circumferential direction corresponding to the direction the rotation imposed on the tire to capture a complete image of its surface. [022] Figure 2 shows the image from this seizure. We observe the presence of false measurement points, noted PFM, whose presence is particularly marked on the edges of the reliefs of the sculpture.
[023] A chaque point (x,y) du plan support on affecte une valeur de niveau de gris proportionnelle à l'élévation de ce point par rapport à la surface de référence. [024] Cette image est alors traitée à l'aide des opérateurs morphologiques de type ouverture puis fermeture dans le but de filtrer les valeurs de niveau de gris anormalement élevées ou basse par rapport aux valeurs de niveau de gris affectées aux points voisins. [023] At each point (x, y) of the support plane is assigned a gray level value proportional to the elevation of this point relative to the reference surface. [024] This image is then processed using the opening and closing type morphological operators in order to filter the abnormally high or low gray level values with respect to the gray level values assigned to the neighboring points.
[025] Ce premier traitement utilise un opérateur morphologique de forme carrée. La taille de cet opérateur est ajustée à la taille des défauts que l'on cherche à filtrer. En l'espèce, de bons résultats sont obtenus avec un opérateur dont la surface du carré est de l'ordre d'une centaine de pixel et dont le coté est large d'une dizaine de pixels. [025] This first treatment uses a morphological operator of square shape. The size of this operator is adjusted to the size of the defects that one seeks to filter. In this case, good results are obtained with an operator whose area of the square is of the order of a hundred pixels and whose side is wide of ten pixels.
[026] Le carré est orienté selon les axes x et y correspondant respectivement, dans le cas illustré par la figure 2, à la direction axiale et à la direction circonférentielle du pneumatique. [027] La figure 3 est une vue partielle de l'image de la surface du pneumatique après la réalisation du premier traitement. [026] The square is oriented along the x and y axes respectively corresponding, in the case illustrated in Figure 2, to the axial direction and to the circumferential direction of the tire. [027] Figure 3 is a partial view of the image of the tire surface after the completion of the first treatment.
[028] Il est possible que ce premier traitement ne parvienne pas à éliminer toutes les valeurs anormales considérées comme des points de fausse mesure. [028] It is possible that this first treatment fails to eliminate all the abnormal values considered as false measurement points.
[029] Aussi, on va considérer que ce résidu de valeurs anormales est concentré de manière préférentielle ou niveau des zones correspondant à une forte variation du relief. [029] Also, it will be considered that this residual of abnormal values is preferentially concentrated or level zones corresponding to a strong variation of the relief.
[030] Ces zones sont facilement identifiables, en raison de la forte variation du gradient de niveau de gris, à l'aide d'un opérateur morphologique de type gradient, qui consiste à soustraire les valeurs de niveau de gris obtenues après une érosion de l'image issue de la première transformation des valeurs de niveau de gris obtenues après une dilatation de ladite image. [031] Pour cette opération on utilise à nouveau un opérateur morphologique de forme carrée dont la taille est ajustée de manière à faire apparaître la zone où se produit la forte variation de gradient, et dont la largeur dépend de la pente des motifs en relief figurant à la surface du pneumatique. En règle générale cette pente est relativement importante, en particulier au niveau des pains de sculpture ou des motifs de marquage figurant sur les flancs. Ici encore un carré d'une centaine de pixel donne de bons résultats. [030] These areas are easily identifiable because of the strong variation in gradient gradient, using a gradient type morphological operator, which subtracts the gray level values obtained after erosion of the image from the first transformation of the gray level values obtained after a dilation of said image. [031] For this operation we use again a morphological operator of square shape whose size is adjusted so as to reveal the area where the high gradient variation occurs, and whose width depends on the slope of the patterns in relief appearing on the surface of the tire. In general, this slope is relatively important, especially at the level of the carving loaves or marking patterns on the flanks. Here again a square of a hundred pixels gives good results.
[032] La figure 4 illustre le résultat de cette opération qui permet de détacher du fond de l'image les seules valeurs des contours des reliefs de la surface. [032] Figure 4 illustrates the result of this operation which detaches from the bottom of the image the only values of the contours of the reliefs of the surface.
[033] Le deuxième traitement a pour objet de réduire les valeurs de fausse mesure dans la bande étroite représentant les contours des reliefs. Pour ce faire, on affecte à chaque pixel de cette zone, la valeur de niveau de gris égale à la valeur obtenue après la première transformation. [033] The second treatment is intended to reduce the false measurement values in the narrow band representing the contours of the reliefs. To do this, we assign to each pixel of this area, the value of gray level equal to the value obtained after the first transformation.
[034] La figure 5 permet d'illustrer le résultat obtenu après la mise en œuvre du premier et du deuxième traitement. On observe que les points de fausse mesure ont totalement disparus et ne sont plus susceptibles de perturber les traitements numériques de l'image en vue de réaliser l'inspection de la conformité de la surface du pneumatique. [034] Figure 5 illustrates the result obtained after the implementation of the first and second treatment. It is observed that the false measurement points have completely disappeared and are no longer likely to disturb the digital image processing in order to perform the inspection of the conformity of the surface of the tire.
[035] Comme cela a été indiqué précédemment, cette méthode s'applique particulièrement bien aux zones faisant apparaître de fortes variations de reliefs et donc aux parties externes de la surface du pneumatique. Toutefois, de manière non limitative, il n'est pas exclu d'utiliser cette même méthode pour affiner les images de la partie interne du pneumatique lorsque ces dernières comportent des éléments de relief tels que des stries. [035] As indicated above, this method is particularly applicable to areas showing strong variations of relief and therefore to the external parts of the tire surface. However, in a nonlimiting manner, it is not excluded to use this same method to refine the images of the inner part of the tire when the latter comprise relief elements such as streaks.

Claims

REVENDICATIONS
1) Méthode de traitement de l'image numérique tridimensionnelle de la surface d'un pneumatique dans laquelle, on capture l'image tridimensionnelle de ladite surface en affectant à chaque pixel du plan de l'image une information relative à l'élévation de ce point par rapport à la surface à inspecter, dans laquelle on effectue les étapes suivantes : 1) Method for processing the three-dimensional digital image of the surface of a tire in which the three-dimensional image of said surface is captured by assigning to each pixel of the plane of the image information relating to the elevation of this surface point with respect to the surface to be inspected, in which the following steps are carried out:
à l'aide d'un opérateur morphologique comprenant une ouverture puis une fermeture et utilisant un élément structurant de taille et de forme donnée, on réalise une première transformation de l'image de la surface de manière à ajuster le niveau de gris des pixels situés anormalement au-dessus ou au-dessous de la surface à inspecter et,  by means of a morphological operator comprising an opening and a closure and using a structuring element of given size and shape, a first transformation of the image of the surface is carried out so as to adjust the gray level of the pixels situated abnormally above or below the surface to be inspected and,
on détermine les éléments de contours du relief de la surface en utilisant un opérateur morphologique de type gradient, suivie d'un seuillage permettant d'extraire les contours du relief et on effectue une deuxième transformation de l'image de la surface en affectant à chaque pixel du contour la valeur de niveau de gris égale à la valeur obtenue après la première transformation.  the contours elements of the relief of the surface are determined using a morphological operator of the gradient type, followed by a thresholding enabling the contours of the relief to be extracted and a second transformation of the image of the surface is carried out, affecting each contour pixel the gray level value equal to the value obtained after the first transformation.
2) Méthode de traitement selon la revendication 1 , dans laquelle le niveau de gris de chaque pixel est représentatif de l'élévation du point correspondant de la surface à inspecter. 3) Méthode de traitement selon l'une des revendications 1 ou 2, dans laquelle l'opérateur morphologique est un carré. 2) A method of treatment according to claim 1, wherein the gray level of each pixel is representative of the elevation of the corresponding point of the surface to be inspected. 3) Method of treatment according to one of claims 1 or 2, wherein the morphological operator is a square.
4) Méthode de traitement selon la revendication 3, dans laquelle la largeur du carré de l'opérateur morphologique est comprise entre 8 et 15 pixels. 4) A method of treatment according to claim 3, wherein the width of the square of the morphological operator is between 8 and 15 pixels.
5) Méthode de traitement selon l'une des revendications 1 à 4, dans laquelle l'image capturée est celle de la surface externe du pneumatique. 5) Method of treatment according to one of claims 1 to 4, wherein the captured image is that of the outer surface of the tire.
EP12710502.1A 2011-04-18 2012-03-21 Analysis of the digital image of the external surface of a tyre and processing of false measurement points Withdrawn EP2700050A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR1153345A FR2974219A1 (en) 2011-04-18 2011-04-18 ANALYSIS OF THE DIGITAL IMAGE OF THE OUTER SURFACE OF A TIRE - TREATMENT OF MISCONCEPTION POINTS
PCT/EP2012/055016 WO2012143198A1 (en) 2011-04-18 2012-03-21 Analysis of the digital image of the external surface of a tyre and processing of false measurement points

Publications (1)

Publication Number Publication Date
EP2700050A1 true EP2700050A1 (en) 2014-02-26

Family

ID=45878948

Family Applications (1)

Application Number Title Priority Date Filing Date
EP12710502.1A Withdrawn EP2700050A1 (en) 2011-04-18 2012-03-21 Analysis of the digital image of the external surface of a tyre and processing of false measurement points

Country Status (7)

Country Link
US (1) US9230318B2 (en)
EP (1) EP2700050A1 (en)
JP (1) JP2014517265A (en)
CN (1) CN103649989B (en)
BR (1) BR112013024106A2 (en)
FR (1) FR2974219A1 (en)
WO (1) WO2012143198A1 (en)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9291527B2 (en) * 2012-07-25 2016-03-22 TIREAUDIT.COM, Inc. System and method for analysis of surface features
JP5777650B2 (en) * 2013-01-29 2015-09-09 富士フイルム株式会社 Ultrasonic diagnostic apparatus and ultrasonic image generation method
US10063837B2 (en) * 2013-07-25 2018-08-28 TIREAUDIT.COM, Inc. System and method for analysis of surface features
FR3022380A1 (en) 2014-06-13 2015-12-18 Michelin & Cie METHOD FOR PNEUMATIC IMAGE ADJUSTMENT
FR3030042A1 (en) 2014-12-15 2016-06-17 Michelin & Cie METHOD OF DETECTING DEFECT ON A PNEUMATIC SURFACE
JP6279163B1 (en) * 2014-12-22 2018-02-14 ピレリ・タイヤ・ソチエタ・ペル・アツィオーニ Method and apparatus for detecting tire defects in a tire manufacturing process
FR3038111B1 (en) * 2015-06-29 2017-08-11 Michelin & Cie IMAGE SEGMENTATION METHOD
FR3038110B1 (en) * 2015-06-29 2017-08-11 Michelin & Cie IMAGE SEGMENTATION METHOD
CN106904050B (en) * 2016-01-07 2018-07-24 西华大学 A kind of method that tire safety monitoring device carries out safety detection
US10789773B2 (en) 2016-03-04 2020-09-29 TIREAUDIT.COM, Inc. Mesh registration system and method for diagnosing tread wear
US11472234B2 (en) 2016-03-04 2022-10-18 TIREAUDIT.COM, Inc. Mesh registration system and method for diagnosing tread wear
US11027505B2 (en) 2016-12-20 2021-06-08 Pirelli Tyre S.P.A. Method for checking formation of beads of tyres
EP3653563A1 (en) * 2018-11-15 2020-05-20 Siemens Aktiengesellschaft Reliable detection of container crane and tableware
CN114419040B (en) * 2022-03-29 2022-06-03 武汉绿色塑料包装有限公司 Morphology-based bottle blank gate wire drawing detection method and system

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2632071B1 (en) * 1988-05-31 1991-03-15 Labo Electronique Physique ULTRASONIC ECHOGRAPH WITH REDUCED INTERFERENCE NOISE
US20010013823A1 (en) 1997-04-14 2001-08-16 Takeshi Hatakeyama Network control system, network terminal and control terminal
DE10062251C2 (en) 2000-12-14 2002-12-12 Fraunhofer Ges Forschung Device and method for checking the quality of a body
DE10062254C2 (en) 2000-12-14 2002-12-19 Fraunhofer Ges Forschung Method and device for characterizing a surface and method and device for determining a shape anomaly of a surface
US6950211B2 (en) * 2001-07-05 2005-09-27 Corel Corporation Fine moire correction in images
US20030012453A1 (en) 2001-07-06 2003-01-16 Jasc Software, Inc. Method for removing defects from images
DE10143522C2 (en) * 2001-09-05 2003-07-10 Fraunhofer Ges Forschung Method and device for examining an object
JP4679073B2 (en) * 2004-05-18 2011-04-27 株式会社ブリヂストン Tire unevenness pattern inspection method and tire unevenness pattern inspection apparatus
DE102005017624A1 (en) 2005-04-15 2006-10-19 Robert Bosch Gmbh Wheel and/or axial geometry determining method for motor vehicle, involves determining 3-D image points that reproduce three-dimensional surface of object section and obtain wheel and/or reference and/or body characteristics
JP5046688B2 (en) * 2007-03-08 2012-10-10 株式会社神戸製鋼所 Tire shape detection device and tire shape detection method
FR2925706B1 (en) * 2007-12-19 2010-01-15 Soc Tech Michelin DEVICE FOR EVALUATING THE SURFACE OF A TIRE.
EP2235679B1 (en) * 2007-12-19 2012-02-15 Société de Technologie MICHELIN Method for processing a three-dimensional image of the surface of a tyre so that it can be used to inspect the said surface
FR2925687B1 (en) 2007-12-19 2010-02-12 Soc Tech Michelin METHOD OF EVALUATION BY COMPARISON OF AN ACQUIRED IMAGE WITH A REFERENCE IMAGE.
EP2295930B1 (en) * 2008-06-04 2014-01-01 Kabushiki Kaisha Kobe Seiko Sho Tire shape inspection method and tire shape inspection device
JP2010286959A (en) * 2009-06-10 2010-12-24 Nippon Telegr & Teleph Corp <Ntt> Method, device and program for enhancing face image resolution
US9194813B2 (en) * 2009-10-06 2015-11-24 Compagnie Generale Des Etablissements Michelin Method and device for the automatic inspection of a cable spool
FR2966246B1 (en) 2010-10-19 2012-12-14 Michelin Soc Tech METHOD OF IDENTIFYING AND LIMITING THE BASIC PATTERNS FORMING THE SCULPTURE OF THE TIRE TREAD OF A TIRE
FR2966245B1 (en) 2010-10-19 2012-10-19 Michelin Soc Tech METHOD OF IDENTIFYING AND LIMITING THE BASIC PATTERNS FORMING THE SCULPTURE OF THE TIRE TREAD OF A TIRE

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO2012143198A1 *

Also Published As

Publication number Publication date
CN103649989B (en) 2016-12-14
CN103649989A (en) 2014-03-19
WO2012143198A1 (en) 2012-10-26
BR112013024106A2 (en) 2016-12-20
JP2014517265A (en) 2014-07-17
US9230318B2 (en) 2016-01-05
FR2974219A1 (en) 2012-10-19
US20140307941A1 (en) 2014-10-16

Similar Documents

Publication Publication Date Title
WO2012143198A1 (en) Analysis of the digital image of the external surface of a tyre and processing of false measurement points
EP3329460A1 (en) Optimised method for analysing the conformity of the surface of a tyre
EP2761588B1 (en) Fast analysis method for relief parts showing on the interior surface of a tyre
JP5443435B2 (en) Tire defect detection method
EP2700051A1 (en) Analysis of the digital image of the surface of a tyre and processing of non-measurement points
FR2966956A1 (en) METHOD OF PRE-PROCESSING A DIMENSIONAL IMAGE OF THE SURFACE OF A TIRE USING SUCCESSIVE B-SPLINE DEFORMATIONS
EP2710552B1 (en) Method for determining markings in relief on the outer surface of the sidewall of a tyre
WO2012055748A1 (en) Method for the pre-processing of a three-dimensional image of the surface of a tyre for use in the inspection of said surface
EP2630464A1 (en) Method for identifying and defining basic patterns forming the tread design of a tyre
WO2011131410A1 (en) Method of monitoring the appearance of the surface of a tyre
EP2856122A1 (en) Optical method for inspecting transparent or translucent containers bearing visual motifs
EP2700052B1 (en) Analysis of the digital image of the internal surface of a tyre and processing of false measurement points
EP3008445B1 (en) Method for processing a digital image of the surface of a tire in order to detect an anomaly
WO2013045593A1 (en) Improved method of checking the appearance of the surface of a tyre
FR2976090A3 (en) Method for inspecting surface of pneumatic tire to detect defects on surface, involves determining three-dimensional image of surface to be inspected by combining three-dimensional images of different surface areas
TWI590191B (en) Defect compensation method for optical patterns
JP2016217877A (en) Deficiency inspection device and deficiency inspection method

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: 20131118

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN WITHDRAWN

18W Application withdrawn

Effective date: 20170213