• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    A method for detecting geometric discontinuities on the surface of the lateral surface of a body, which body is illuminated with a light beam emitting light source and which body is captured by a camera outputting image data, which image data comprise color property values at a pixel, wherein - the color property values at the individual pixels and an accumulation of deviating color property values determined in a value subregion of the lateral surface is interpreted as a first indication of an image position of a geometrical discontinuity at pixels adjacent to the value subrange or subset domain, and / or the course of the color property values at pixels of an image subrange Reference function is superimposed on generation of overlay image data amount including overlay color property values at the pixels and a maximum value and / or a minimum m value in the sub-picture data set at a pixel is interpreted as a second indication of a geometric discontinuity.
    公开号:AT521215A1
    申请号:T503432018
    申请日:2018-04-24
    公开日:2019-11-15
    发明作者:
    申请人:Avi Systems Gmbh；
    IPC主号:
    专利说明:

    DESCRIPTION
    The invention discussed below relates to a method for the detection of geometric discontinuities on the surface of the lateral surface of a body, which body is illuminated with a light beam emitting light source and which body is recorded by means of an image data output camera, which image data include color property values at a pixel.
    A geometric discontinuity by definition represents a deviation of the geometric properties of the surface of the body. A geometric discontinuity requires a change in the amount of reflected and / or transmitted light rays compared to the rest of the body. In the case of a body made of a weldable material, a discontinuity can represent a weld seam that is visible on the surface of the body. A geometric discontinuity can also be a deformation or break visible on the surface.
    The body can be made from an opaque workpiece. The body can be, for example, a metallic workpiece, a plastic or a material with a proportion of natural raw materials, such as a wood or a wood material.
    The color property values of the image data comprising a pixel thus include a color property value and a coordinate specification or other suitable location information of the image point having the color property value.
    Since the method according to the invention is based on the use of image acquisition, this is limited to the detection of discontinuities visible on the surface.
    According to the prior art, image recordings are used for the detection of discontinuities. A possible approach to this is the comparison of an image recording of a body which has no discontinuities and a further image recording of a further body which has at least one discontinuity. However, it was shown that only methods based on a comparison are not sufficiently precise and are not sufficiently stable against errors in the image recordings.
    A method according to the prior art, which method is limited to a comparison of image data, delivers in particular in an application for recognition
    1/22.
    A 1729 of discontinuities in natural workpieces such as wood, no usable results because the possible discontinuities are too different.
    The method according to the invention has the task of mapping the human detection of discontinuities in a manner that is as similar as possible by means of a computer-implemented method, which is explained in detail below. This task is associated with the fact that the method according to the invention is stable against interference.
    According to the invention this is achieved in that
    - The color property values at the individual pixels are compared and a cluster of deviating color property values determined in a partial value area of the lateral surface, which deviating color property values deviate from a color average of the color property values of the lateral surface or from a dominance color property value by a limit value, as a first indication of an image position of a geometric one Discontinuity at pixels adjacent to the partial value area or in the partial value area is interpreted, and / or
    - The course of the color property values at pixels of an image subarea is overlaid with a reference function with generation of overlay image data amount comprising overlay color property values at the pixels and a maximum value and / or a minimum value in the overlay image data amount at one pixel is interpreted as a second indication of a geometric discontinuity.
    A person perceives a discontinuity primarily through color differences and tries to form areas with similar colors. Furthermore, the person compares an area with a similar color with his or her wealth of experience in order to evaluate such an area as a discontinuity if necessary.
    The colors recognizable to the human eye are used as color values in computer-implemented processes. Color values can be defined according to defined codes.
    Like the human perception, the solution according to the invention is based on a two-stage detection approach. The method according to the invention is characterized in that very precise image position information is determined from geometric discontinuities. The position of the discontinuity can be determined from the image position information
    2/22 2
    A 1729 position information given on the surface of the hollow cross section can be calculated.
    In a first method step, the partial value areas with different color property values are detected. In a second process step, the amount of overlay image data is examined for a minimum or maximum. The first process step provides a first indication of the image position of a discontinuity in the image arranged on the surface of the hollow cross section. The second method step provides a second indication of the image position of a discontinuity arranged on the surface of the hollow cross section.
    A color property value can be, for example, a color code according to the prior art, such as RGB, or a gray value. The person skilled in the art chooses the color property value on which the method according to the invention is based on the ascertainable colors of the surface of the body. If the body essentially only has variants of a certain color value, such as, for example, the gray tones of a metal cross section or the surface, then the use of gray tones as color property values is sufficient.
    The implementation of the method according to the invention can require that the body to be examined is illuminated. The person skilled in the art can use light sources with directed, preferably parallel light beams for this purpose. According to the current teaching, LED light sources can be used. For example, an LED ring can be used to illuminate the body, which extends in a ring around the image sensor or the lens.
    Conventional digital cameras can be used to carry out the method.
    In the second method step, the color property values of the pixels of a selected partial image area and / or a color property function describing the color property values can be mathematically superimposed by means of a mathematical function.
    The mathematical superimposition can take place by multiplying (mathematical folding) and / or adding and / or subtracting and / or dividing et cetera the color property values of the pixels and / or the course of the color property values of the pixels with a function and / or a number of functions.
    3/22 3
    A 1729
    In the second method step, the optically perceptible color property values can be overlaid with an optical filter to generate an optically perceptible overlay image data set.
    The second method step can be based on the use of the method of generating neural networks known according to the current teaching and the training of the neural networks from image data which is also known according to the current teaching.
    The first method step and the second method step can be carried out in parallel with one another in time or in succession in any order.
    The functions to be overlaid mathematically or defined by the optical filter can be reference functions which describe the course of color property values of image data of a surface having a discontinuity or no discontinuity. The function can also describe environmental influences and thus minimize the influence of the environmental influences on the detection of the geometric discrepancies, since this smoothes a change in the color property values caused by environmental influences.
    An overlay of the course of the color property values with a reference function describing reference color property values has the effect that the deviations in the image data become clear due to a coincidence with the function. The person skilled in the art essentially expects the occurrence of certain discontinuities and can select the reference function on the basis of this expectation.
    For example, those skilled in the art can expect a weld as a discontinuity. The person skilled in the art can mathematically or optically superimpose the color property values with a reference function, which reference function reflects the usual course of the color property values of a weld seam.
    The method according to the invention is in no way restricted to the fact that the first indication and the second indication must be identical. The method according to the invention can include the method step that the first indication and the second indication for determining a position of a discontinuity are compared.
    4/22.
    A 1729
    The method according to the invention can be characterized in that several image recordings are made of a body, the method according to the invention being applied to each image recording. The latter can in turn include the fact that, with a defined number of matching first indications and second indications, a discontinuity was recognized with sufficient accuracy.
    The first method step can provide a first indication of which first indication comprises a first probability measure of the occurrence of a discontinuity.
    The second method step can provide a second indication, which second indication comprises a second probability measure of the occurrence of a discontinuity.
    The above-mentioned comparison of the first clue and the second clue can take place in such a way that the first probability measure and the second probability measure must exceed a threshold value, so that the first clue and the second clue can be combined to form a statement about the existence of a discontinuity.
    The method according to the invention can advantageously be used both on stationary bodies and on moving bodies. The comparison of instructions can require that a number of image recordings be made within a period of time, to which number of image recordings the method according to the invention for generating the instructions is applied. The person skilled in the art calculates the required images per second from the required number of image recordings within a period of time.
    Image data can be created and / or used, which image data represent light beams with a defined waveform and / or with a defined wavelength and / or with a defined light frequency. The method according to the invention can include the use of filters according to the prior art, such as H-wavelet filters.
    Image data in the form of a negative image can also be created and / or used. The method according to the invention can be characterized in relation to the use and / or the creation of image data by means of filters and / or according to the negative image technique in that only certain light rays are examined with reference to the discontinuity to be expected. As a result, the discontinuities in
    5.22
    A 1729 represented a stronger contrast visually or in the form of image data. The method according to the invention can be highly effective in relation to the use of filters or negative image technology.
    The method according to the invention can be characterized in that a network part area comprising a geometric discontinuity is stored in the database as a reference discontinuity. As a result, the database, in which, in the broadest sense, forms of the discontinuities are stored, is essentially continuously expanded by information describing the form of a discontinuity in the power supply area.
    The ongoing expansion of the database by network areas, which are classified as a discontinuity comprising network area, includes that this process can be system-controlled and / or user-controlled.
    This ongoing expansion of the database by network areas classified as a discontinuity is particularly advantageous when the method according to the invention is used with natural materials. In an analogous manner to this, the color property values of the pixels of a partial value area comprising a geometric discontinuity can be stored in the database. With this method step, if the geometric discontinuity extends over a number of pixels, courses or patterns of the color property values over the pixels of the geometric discontinuity can also be stored.
    The method according to the invention can therefore include routines, by means of which routines a database comprising color property values of pixels are continuously expanded, which pixels comprise a geometric discontinuity. Information about color property values of individual pixels and / or about courses of color property values over several pixels can be stored. The course of color property values over several pixels can be described using mathematical functions.
    The person skilled in the art recognizes that the above method can be applied essentially to any body shape, which body shape comprises a surface that can be recorded by means of image recording techniques. However, this can mean that it is known if a body is depicted in the image.
    6/22 _
    A 1729
    The second method step, in which second method step the superimposed image data quantity is generated, can be characterized in that the partial image area is selected as a function of the occurrence of a maximum value and / or a minimum value at pixels.
    The partial image area is preferably selected by a person or by independent process routines such that the partial image area includes the pixels comprising the maximum value or minimum value and further pixels adjacent to these pixels, the maximum value or the minimum value using the method according to the invention using a previous partial image area is determined. The method according to the invention can be characterized in that the amount of image data is reduced, since the partial image area is smaller than the previous partial image area.
    The method according to the invention can also include that the presence of a body is detected and verified in the image, the edges of the body being detected by methods according to the prior art and the verification being carried out via the virtual construction of vanishing points.
    The method according to the invention is further explained on the basis of the following description of the figures and the figures below. The following elements are identified in the figures by the preceding reference symbols.
    body
    cross-section
    edge
    Right wall weld free
    movement direction
    Reflecting surface light
    Value subrange rectangular area further value range
    Figure 1 and Figure 2 show black and white images of the body to be examined.
    7.22
    A 1729
    FIG. 3 shows a section of the view of the body shown in FIG. 2, FIG. 3 being created using a filter.
    FIG. 4 shows a diagram, which diagram is derived from the color property values shown in FIG. 3.
    FIG. 1 shows a hollow body as body 1 with a cross section 2. The direction of view of the view shown in FIG. 1 on body 1 is parallel to the longitudinal axis of body 1.
    In the exemplary embodiment shown in FIG. 1, a tube having a length of 12.0 m and a cross section of approximately 10.0 cm by 10.0 cm is moved past cameras as body 1 at a high speed - up to 6 m / sec.
    Figure 1 shows a direction of movement 7 of the tubes in a system according to the prior art. In the system, the pipes are moved past the cameras in a continuous process. The cameras required to carry out the method according to the invention are integrated in the system.
    It is the object of the method according to the invention to detect the body in the image recorded by the camera in a first step and to recognize discontinuities in the form of a weld seam on the surface of the body 1 in a second step. The step of recognizing the discontinuities includes that the image position of the discontinuity is also determined, so that the tube can subsequently be positioned as a function of the position and / or as a function of a desired position of the weld seam.
    The first method step and the second method step of the method according to the invention can be carried out essentially independently of one another. The second step can mean that the presence of the tube as a body is known, which the person skilled in the art can also determine by other methods according to the prior art than by the first step of the method according to the invention.
    To carry out the method according to the invention, the body is illuminated with a light source emitting light rays and recorded using cameras that output image data.
    8/22 8
    A 1729
    For this purpose, the cameras are essentially aligned with the pipe axes. The camera for recording an example shown in FIG. 1 is aligned parallel to the longitudinal axis of the body 1. The focus of the camera for the image encompassed in FIG. 1 is set in such a way that a working area of 20.0-200 .OMEGA.
    The recording direction of the further camera for recording an image shown by way of example in FIG. 2 is oriented essentially at right angles to the surface to be examined.
    In the images shown in FIG. 1 and FIG. 2, the image data per pixel comprise a gray value. A reduction in the image data from color property values to gray data entails a reduction in the amount of data. The method according to the invention is characterized in that sufficiently precise information is provided so that this reduction in the amount of data is possible.
    In a first step, the edges 3 of the body 1 are detected, the person skilled in the art under no circumstances having to carry out the detection of all the edges when carrying out the method according to the invention. Prior art methods for edge detection are used here. In the method illustrated in the figures, the edges are determined via the gradients of the gray values of neighboring pixels.
    The vanishing points of these edges can be determined on the basis of the detected edges and the presence of the body 1 in the image can thereby be verified.
    In Figure 1, the approximate positions of the edges 3 determined are entered by dashed lines. The vanishing points which can be determined from the edges 3 comprise, in the exemplary embodiment illustrated in FIG. 1, a vanishing point located in the “infinite”. The determination of at least one vanishing point of the edges of the body located in the “infinite” has the advantage that the body can be differentiated from the surroundings without a great deal of computation. In the embodiment discussed here, the environment is formed by a hall, in which hall the plant for processing and / or transporting the pipes is located as body 1.
    In a second step, the discontinuities and the image position of these are detected.
    9/22 9
    A 1729
    The person skilled in the art recognizes that the hollow body 1 shown in a cross-sectional view in FIG. 1 comprises a weld 4 in the right wall 5. The weld seam 4, which represents a geometric discontinuity, is recognizable to the human eye on the basis of the course of the gray tones in the right-hand wall 5 and by making out partial areas of the right-hand wall.
    FIG. 2 shows a frontal view of the right wall 5. For this purpose, the camera for recording the image shown in FIG. 2 is oriented essentially parallel to a cross-sectional axis of the body. Here too, the weld seam 4, which represents a discontinuity, can be recognized by the course of the gray tones and by the identification of partial areas.
    FIG. 2 shows, in addition to the tube as body 1 together with the weld seam 4, a bright area, which bright area is a reflection area 8 of light, with which light the body 1 is illuminated for producing the images shown in FIG. 1 and FIG. 2. It is also an object of the method according to the invention to recognize such reflection surfaces 8 as such.
    The subjective identification of partial areas by a person includes that the person compares the recognized partial areas with their wealth of experience about discontinuities and also selects the corresponding areas depending on the color property values.
    The method according to the invention tries to reproduce this briefly described human perception known according to the common teaching by means of a computer-implemented method.
    For this purpose, the color property values at the individual pixels are compared and partial value ranges with deviating color property values are determined, which deviating color property values differ by a limit from a color average measure measured over the surface of the jacket or from a dominance color property value. In this way, a search is made for subareas with color values that deviate from the average or with the dominant color values within a range of values defined by limit values.
    FIG. 3 shows a section of the weld seam shown in FIG. 2, FIG. 3 being created by means of an edge detector using the conventional Sobel or Lenny teaching. With the help of the edge detector, only those pixels with the i ° / 22io
    A 1729
    Properties are displayed at which pixels the gradient of a function describing the color values has a high gradient in the horizontal direction or in the vertical direction. FIG. 4 shows a diagram derived from FIG. 3. The diagram shown in FIG. 4 represents a color value on a pixel on the z-axis as a function of the position of the pixel shown in the xy area. FIG. 4 further comprises the image contained in FIG. 3 in a three-dimensional representation.
    The detection of discontinuities with the aid of the method according to the invention is essentially based on one of the graphics shown in FIGS. 3 and 4, the implementation of the method according to the invention not requiring the creation of such graphics, but can also be based exclusively on the processing of data. To illustrate the method according to the invention, this is explained by way of example with reference to FIGS. 3 and 4.
    FIG. 3 comprises a rectangular area 10. In this area 10 information was covered, which information is written in a font that is too small for display in FIG. 3 and has no influence on the subject matter of the patent application.
    FIG. 3 shows a partial value range 9, which partial value range 9 comprises color property values that differ from an average measure of the color property values. The partial value range 9 thus includes color property values which deviate from the dominance color property value by at least one defined limit value.
    A dominance color property value is to be understood as that range of color property values which dominates over the outer surface. FIG. 3 shows the special case that the average color value is also the dominance color property value.
    The person skilled in the art recognizes that in FIG. 3 and FIG. 4 two partial areas can be identified as such value areas 9 with deviating color property values, while three further value partial areas with average color properties can be seen equal to the dominant color property values.
    The value sub-areas 4 in FIG. 3 are marked with a dashed ellipse in addition to the reference symbols; the other sections are not marked further. In Figure 4, the value ranges 4 are identified only by reference numerals.
    11/22 ..
    A 1729
    The presence of the two partial areas as partial value areas 9 with deviating color property values is evaluated as a first indication of a discontinuity on the surface of the jacket.
    The method according to the invention is characterized in particular by the fact that the first indication of the presence of a discontinuity is verified by a further analysis of the images included in FIGS. 1 and 2.
    FIG. 5 shows, using the pixel graph 12, the basic course of the surface curve shown in FIG. 4 along a sectional plane parallel to the x-axis. The exact position is the sectional plane in FIG. 4 and the exact course of the graphs shown in FIG. 5 is irrelevant for the following discussion of the effects of the use of the method according to the invention illustrated by FIG. 5.
    The pixel graph 12 thus represents the course of the color property values. The pixel graph 12 is a sufficiently accurate representation of the course of the surface curve shown in FIG. 4 along a section plane parallel to the x-axis, reducing the amount of data to be processed.
    FIG. 5 also includes a reference curve 13. The person skilled in the art selects the reference curve 13 and, if appropriate, the position of the reference curve 13 based on his specialist knowledge. The reference curve 13 can be chosen with regard to an expected discontinuity. The person skilled in the art recognizes that the use of the method according to the invention also permits the use of a plurality of reference curves, only the use of one reference curve being shown in FIG. 5 to maintain clarity.
    By using the second method step of the method according to the invention, pixel graph 12 and reference graph 13 are folded to form an overlay graph 14.
    FIG. 6 shows an optical reference model comprising reference curves for superimposition with a partial area of the surface curve shown in FIG. 4.
    FIG. 7 shows the result of a superposition of a partial area of the surface curve shown in FIG. 4 with the reference model shown in FIG. 6. The discontinuities are clearly recognizable from the light areas.
    12/22 12
    A 1729
    This verification can be carried out by forming neural networks according to the current teaching, which is explained with reference to FIG. 8.
    Figure 8 shows an image 12, which image 12 has a size of 224x224. The image 12 comprises image data with color property values per pixel. The image data of the image 12 are overlaid with two reference functions, whereby two so-called planes are formed. The levels each comprise a sub-picture data set, which are generated by multiplying the color property values by one function each. Thus, in the exemplary embodiment shown in FIG. 8, two sub-picture data sets are generated, each of which comprises maximum values and minimum values.
    The occurrence of these maximum and minimum values is interpreted as a second indication of the existence of geometric discontinuities.
    Accordingly, the image partial area is selected when three additional functions are superimposed on the image data. While the image partial area corresponded to the size of the image 12 in the first overlay of the image data with two functions, the image partial area can be considerably reduced in the second overlay.
    The person skilled in the art can carry out the superimposition of the image data n times and accordingly reduce the image partial area and restrict the local presence of the discontinuity.
    i3 / 22i3
    A 1729
    权利要求:
    Claims (8)
    [1]
    1. A method for the detection of geometric discontinuities on the surface of the lateral surface of a body, which body is illuminated with a light beam emitting light source and which body is recorded by means of a camera which outputs image data, which image data comprise color property values at a pixel, characterized in that
    - The color property values at the individual pixels are compared and a cluster of deviating color property values determined in a partial value area of the lateral surface, which differing color property values from a color average of the color property values of the lateral surface or from a dominance color property value by a limit value, as a first indication of an image position of a geometric Discontinuity at pixels adjacent to the partial value area or in the partial value area is interpreted, and / or
    - The course of the color property values at pixels of an image subarea is overlaid with a reference function with generation of overlay image data amount comprising overlay color property values at the pixels and a maximum value and / or a minimum value in the overlay image data amount at one pixel is interpreted as a second indication of a geometric discontinuity.
    [2]
    2. The method according to claim 1, characterized in that the first hint and the second hint for determining a position of a discontinuity are compared.
    [3]
    3. The method according to any one of claims 1 to 2, characterized in that the image data are created and / or used, which image data represent light rays with a defined waveform and / or with a defined wavelength and / or with a defined light frequency.
    [4]
    4. The method according to any one of claims 1 to 3, characterized in that the image data are created and / or used in the form of a negative image.
    [5]
    5. The method according to any one of claims 1 to 4, characterized in that a network part comprising a geometric discontinuity is stored in the database as a reference discontinuity.
    14/22 d λ
    A 1729
    [6]
    6. The method according to any one of claims 1 to 5, characterized in that the color property values of the pixels of a partial value area comprising a geometric discontinuity are stored in the database.
    [7]
    7. The method according to any one of claims 1 to 6, characterized in that the image area is selected depending on the occurrence of a maximum value and / or a minimum value at pixels.
    [8]
    8. The method according to any one of claims 1 to 7, characterized in that the edges of the body which can be reproduced entirely in the image are detected and the presence of a body is verified by determining the vanishing points defined by the edges.
    15/22.
    A 1729
    类似技术:
    公开号 | 公开日 | 专利标题
    EP2275989A1|2011-01-19|Stereoscopic 3D camera
    DE10020893A1|2000-12-28|Optical determination of the shape of an object by determination of the normal to the surface of the object at a large number of points and relating the normals to image points so that an entire surface image is built-up
    EP1718926A1|2006-11-08|Device and method for determining spatial co-ordinates of an object
    DE102017122010A1|2018-04-05|Detection method and detection device for detecting a three-dimensional position of an object
    DE112017005711T5|2019-08-14|Ceramic body defect inspection device and defect inspection method
    DE102014002531A1|2014-08-28|DEVICE AND METHOD FOR VISUAL INSPECTION OF AN OBJECT WITH LINE PATTERNS
    WO2015169730A1|2015-11-12|Method and sensor for determining the surface of an object by means of deflectometry
    AT521215B1|2021-06-15|Method for the detection of discontinuities on the surface of a body
    DE102011103510A1|2012-12-06|Method for creating three-dimensional CAD representation of e.g. workshop, involves detecting coherent surface elements in scatter-plot representation, and creating three-dimensional CAD representation of object arrangement
    DE19840969A1|2000-03-23|Process and device for opto-electronic determination of contact reflection | between gear teeth uses a process where a marking material is applied to one set of gear teeth and a digital image is obtained
    AT513126A4|2014-02-15|Co-occurrence matrix
    DE10335595A1|2004-02-26|Motion capture method for determination of the spatial positions of markers in a 3D volume from 2D digital images for use in motion capture systems so that the marker positions can be related to a coordinate system
    DE102004023322A1|2005-11-24|Position and position measurement of objects using image processing techniques
    DE102017105910A1|2018-09-20|Frequency-based projection segmentation
    DE102018129425B4|2020-07-30|System for recognizing a machining error for a laser machining system for machining a workpiece, laser machining system for machining a workpiece by means of a laser beam comprising the same, and method for detecting a machining error in a laser machining system for machining a workpiece
    DE3817321A1|1989-05-18|Method and device for carrying out the dimensional checking | of a workpiece in an optoelectronic way
    DE102004024595B3|2005-08-18|Determining usability of remote sensing data involves determining distances between first and second image matrix elements and automatically assessing usability of image matrix using the distances
    DE102009024030B3|2011-01-27|Method for optical determination of e.g. length of edges of machined metallic object surface of object, involves determining surface characteristics of surface section of object surface based on evaluation result of pixels or image segments
    DE102017130897A1|2019-06-27|A method of determining range information from a map of a space area
    DE102007014475A1|2008-09-25|Method for determining surface properties, involves evaluating locally resolved sketch of surface to be examined with multiple measured values, where sketch represents certain physical properties that are characterized by measured values
    EP3174010A2|2017-05-31|Method for creating a 3d representation and corresponding image recording apparatus
    DE102005041633B4|2007-06-06|Method and device for determining the position and similarity of object points in images
    EP3142068A1|2017-03-15|Method for three-dimensional recording of objects
    DE102020120887A1|2022-02-10|METHOD OF DETECTING A HANGING POSITION OF A SUPPORT BAR AND FLAT BED MACHINE TOOL
    DE102019101313A1|2020-07-23|Measuring device and method for three-dimensional optical measurement of measurement objects
    同族专利:
    公开号 | 公开日
    EP3561769A3|2019-11-06|
    AT521215B1|2021-06-15|
    EP3561769A2|2019-10-30|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    JPH0382940A|1989-08-25|1991-04-08|Kubota Corp|Detection of inner surface defect of cylindrical work|
    US20020088952A1|2000-11-15|2002-07-11|Rao Nagaraja P.|Optical method and apparatus for inspecting large area planar objects|
    EP1304560A1|2001-10-22|2003-04-23|Laserquipment AG|Method for quality-control of plastic weld seams|
    DE102007014475A1|2007-03-22|2008-09-25|Byk-Gardner Gmbh|Method for determining surface properties, involves evaluating locally resolved sketch of surface to be examined with multiple measured values, where sketch represents certain physical properties that are characterized by measured values|
    DE102016114465A1|2016-08-04|2018-02-08|Hydro Aluminium Rolled Products Gmbh|Apparatus and method for alloy analysis of metal scrap fragments|
    DE10102387C1|2001-01-19|2002-05-29|Atlas Mat Testing Tech Gmbh|Surface defect detection and evaluation method e.g. for automobile bodywork paint finish, uses light reflection from examined surface|
    US20130073221A1|2011-09-16|2013-03-21|Daniel Attinger|Systems and methods for identification of fluid and substrate composition or physico-chemical properties|
    US20170046615A1|2015-08-13|2017-02-16|Lyrical Labs Video Compression Technology, LLC|Object categorization using statistically-modeled classifier outputs|DE102019128503A1|2019-10-22|2021-04-22|Krones Aktiengesellschaft|Method and device for the optical inspection of containers|
    法律状态:
    优先权:
    申请号 | 申请日 | 专利标题
    ATA50343/2018A|AT521215B1|2018-04-24|2018-04-24|Method for the detection of discontinuities on the surface of a body|ATA50343/2018A| AT521215B1|2018-04-24|2018-04-24|Method for the detection of discontinuities on the surface of a body|
    EP19169740.8A| EP3561769A3|2018-04-24|2019-04-17|Method for detecting discontinuities on the surface of a body|
    [返回顶部]