Identification of defect in wood panel

Abstract

A method for generating an estimation of a defect in a wood panel (110) comprising a plurality of layers is provided, the method comprises: receiving (310) an X-ray image data; receiving (340) an image data representing at least part of an edge of the wood panel (110); wherein the image data and the X-ray image data representing a common portion; the method further comprises: detecting (330) a first candidate defect by analyzing (320) the X-ray image data; detecting (360) a second candidate defect indicative of a deviation in a layered structure of the wood panel (110) by analyzing (360) the image data; and generating (370) the estimation of the defect in the wood panel (110) based on the analysis of X-ray image data and the analysis of the image data Also a computing system (120), a computer program and a detection system are provided to.

Description

[0001] IDENTIFICATION OF DEFECT IN WOOD PANEL

[0002] TECHNICAL FIELD

[0003] The invention concerns in general the technical field of wood processing. More particularly, the invention concerns an identification of defects in wood panels.

[0004] BACKGROUND

[0005] Manufacturing of wood panels is a sophisticated process comprising a plurality of manufacturing phases. In spite of sophisticated processing techniques there occurs various kinds of events that may generate a defect to the wood panel during the manufacturing. The defects may be present in an edge of the wood panel, on a surface of the wood panel or even inside the wood panel. The detection of the defects is traditionally made by an operator of the system during the manufacturing process. However, the approach is problematic due to a fact that the operator’s visual inspection is directed to the outer surfaces of the wood panels and the angle of view may be limited, thus, at least some of the defects may be missed by the operator. Moreover, the visual inspection is difficult due to the fact that the manufacturing process is fast and the panels travel fast in the manufacturing process.

[0006] To overcome the challenges in the visual inspection especially with respect to defects on edges of the wood panel there are introduced solutions for automatically detecting such specific defects in the wood panels. The following solutions are available:

[0007] • Edge detection with 2D camera: o Defects on edges of the wood panels may be detected with a camera configured to capture images from the edge of the panel and the image data is analyzed with pattern recognition algorithms to detect defects if any. The challenge with this approach is to define a depth of layers not extending on the same level as others. Also a detection of so-called dark knots is a challenge. Moreover, the solution does not either work fine with edges not scarfed.

[0008] • Laser based detection: o Laser profiling technique works for analysing the surface(s) and / or edges of the wood panels but the laser has a limitation of not reaching the bottom of the defect e.g. in case the defect is a narrow crack. Besides, the laser allows a detection to a depth of 5 mm in maximum due to computational theory applied for laser measurements. In other words, it does not work solidly for the edge detection.

[0009] The above-listed solutions are operative as such in their specific fields and with respect to specific defects. However, there is room for introducing novel approaches to improve defect analysis of the wood panels especially in relation to defects in the edges of the wood panels.

[0010] SUMMARY

[0011] The following presents a simplified summary in order to provide basic understanding of some aspects of various invention embodiments. The summary is not an extensive overview of the invention. It is neither intended to identify key or critical elements of the invention nor to delineate the scope of the invention. The following summary merely presents some concepts of the invention in a simplified form as a prelude to a more detailed description of exemplifying embodiments of the invention.

[0012] An object of the invention is to present a method, a computing system, a computer program and a detection system for identifying a defect in a wood panel.

[0013] The objects of the invention are reached by a method, a computing system, a computer program and a detection system as defined by the respective independent claims. According to a first aspect, a method for generating an estimation of a defect in a wood panel comprising a plurality of layers is provided to, the method comprises: receiving an X-ray image data representing a first portion of the wood panel, receiving an image data representing a second portion of the wood panel, the second portion of the wood panel representing at least part of an edge of the wood panel, wherein the image data and the X-ray image data representing a common portion of the wood panel, the method further comprises: detecting a first candidate defect in a position of the wood panel by analyzing the X-ray image data, detecting a second candidate defect indicative of a deviation in a layered structure of the wood panel in a position of the wood panel by analyzing the image data, generating the estimation of the defect in the wood panel based on the analysis of X-ray image data and the analysis of the image data.

[0014] For example, the image data representing the second portion of the edge of the wood panel may be received from a camera unit arranged to capture image on at least part of the wood panel having a layered structure.

[0015] The X-ray image data representing the first portion of the wood panel may be received from X-ray imaging unit configured to capture X-ray image in a direction deviating from a parallel direction of a surface layer of the wood panel.

[0016] Moreover, the generation of the estimation of the defect may be performed by determining at least one value expressing at least one characteristic of the defect. The at least one characteristic may be at least one of the following: a size of the defect, a position of the defect.

[0017] According to a second aspect, a computing system of a detection system for generating an estimation of a defect in a wood panel comprising a plurality of layers is provided, the computing system is configured to carry out the method according to the first aspect as defined above.

[0018] According to a third aspect, a computer program is provided, the computer program comprising instructions, when the program is executed by a computing system according to the second aspect as defined above, cause the computing system to carry out the method according to the first aspect as defined above.

[0019] According to a fourth aspect, a detection system is provided, the detection system comprising: a camera unit, an X-ray imaging unit, and the computing system according to the second aspect as defined above.

[0020] For example, the camera unit may be operative in a spectrum of an electromagnetic radiation corresponding to one of: visible light, ultraviolet light, infrared light.

[0021] The camera unit may also be implemented with an arrangement applying laser light.

[0022] The expression "a number of” refers herein to any positive integer starting from one, e.g. to one, two, or three.

[0023] The expression "a plurality of” refers herein to any positive integer starting from two, e.g. to two, three, or four.

[0024] Various exemplifying and non-limiting embodiments of the invention both as to constructions and to methods of operation, together with additional objects and advantages thereof, will be best understood from the following description of specific exemplifying and non-limiting embodiments when read in connection with the accompanying drawings.

[0025] The verbs “to comprise” and “to include” are used in this document as open limitations that neither exclude nor require the existence of unrecited features. The features recited in dependent claims are mutually freely combinable unless otherwise explicitly stated. Furthermore, it is to be understood that the use of “a” or “an”, i.e. a singular form, throughout this document does not exclude a plurality.

[0026] BRIEF DESCRIPTION OF FIGURES

[0027] The embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings.

[0028] Figure 1 illustrates schematically a detection system according to an example from a first viewing angle.

[0029] Figure 2 illustrates schematically a detection system according to an example from a first viewing angle.

[0030] Figure 3 illustrates schematically a method according to an example.

[0031] Figure 4 illustrates schematically aspects in relation to a detection system according to an example.

[0032] Figures 5A and 5B illustrate schematically images captured with various imaging units according to examples.

[0033] Figure 6 illustrates schematically computing system according to an example.

[0034] DESCRIPTION OF THE EXEMPLIFYING EMBODIMENTS

[0035] The specific examples provided in the description given below should not be construed as limiting the scope and / or the applicability of the appended claims. Lists and groups of examples provided in the description given below are not exhaustive unless otherwise explicitly stated.

[0036] Figure 1 illustrates schematically, as a side-view, an example of a detection system 100 configured to implement the present invention to identifying a defect on an edge of a wood panel 110 comprising a plurality of layers. In Figure 1 a view of the edge of the wood panel 110 is provided. The detection system 100 comprises a computing system 120, an X-ray imaging unit 130 and at least one camera unit 140. The computing system 120 is communicatively connected to the X-ray imaging unit 130 and the camera unit 140 at least to receive image data from the respective units. In some embodiments the computing system 120 may also perform control operations with respect to the imaging units 130, 140. The X-ray imaging unit at least comprises one or more X-ray sources and one or more X-ray detectors (cf. sensors) wherein the X-rays generated by the X-ray source (cf. tube) at least in part penetrate an object (cf. the wood panel 110) and end up to the respective detector to form an X-ray image of at least part of the object. In other words, the X-ray imaging unit 130 is arranged so that the X-rays penetrate the surface of the wood panel 110 through the topmost layer from the X-ray source point of view and travel through mid-layers if any and possibly exit through the bottom-most layer of the wood panel 110 to the detector. Thus, the X-ray imaging unit 130 is arranged to capture the X-ray image in a direction deviating from a parallel direction of a surface layer of the wood panel 110. The detector is preferably such that it generates the X-ray image as digital data directly transmittable to the computing system 120. For avoidance of doubt it is worthwhile to mention that in a preferred embodiment of the invention the X- ray unit 130 is arranged so that the X-rays arrive at the wood panel 110 substantially perpendicular to the surface of the wood panel 110. However, they may also be arranged to arrive at any angle as long as they are able to penetrate the panel 110. This kind of arrangement may require an adjustment of the positions of the X-ray source and the detector as well as may require selection of at least the X-ray source so that it is capable to generate X-rays with required energy level to penetrate to the detector at least in part. Correspondingly, the camera unit 140 comprises a detector for receiving reflected light from at least one edge of the wood panel 110. The camera unit 140 is arranged with respect to the wood panel 110 so that it may capture image of at least part of the edge of the wood panel 110 so as to implement visual imaging at least on the edge of the wood panel 110. The edge of the wood panel here refers to the surface of the wood panel 110 on which the layered structure is visible. The camera unit 140 is preferably arranged to receive electromagnetic radiation that is light in a visible spectrum (cf. in wavelength range 400 nm - 700 nm). However, the camera unit 140 may also be implemented with a camera unit 140 operating in a spectrum of the electromagnetic radiation corresponding to infrared spectrum (cf. in wavelength range 750 nm - 1 mm) or ultraviolet spectrum (cf. in wavelength range 10 nm - 400 nm). A special case is that the camera unit 140 is implemented with an arrangement operating with laser light. In other words, a laser camera (cf. laser sensor) is applied to as the camera unit 140, wherein the device is arranged to emit laser beams to illuminate the target, i.e. the edge of the wood panel 110 under monitoring, and capture the reflected light therefrom. In the context of the application of the laser light the known way to interpret the result of imaging is applied, i.e. the measurement is based on a position of the reflected light on the laser sensor is used to determine the surface profile of the edge of the wood panel 110. It is also worthwhile to mention that the so-called line laser is directly applicable in the context of the present invention to evaluate the edge(s) of the wood panel 110. For avoidance of doubt, all the mentioned techniques of imaging perform visual imaging, and thus generate visual images, for the purpose of the present invention as is described herein. For sake of completeness, it is worth mentioning that the camera unit 140 may be positioned to capture image data from at least part of the edge formed by the layers together forming the wood panel 110 in any angle in which the image data may be obtained.

[0037] The implementation of the imaging may correspond to the embodiment of Figure 1 wherein wood panels 110 are transported with a number of conveyors 150 by the imaging units 130, 140 that are arranged statically on the travel path of the wood panel 110 in a manner that the images may be captured in the described manner. According to an embodiment the X-ray imaging unit 130 is arranged to capture respective image of the wood panel 110 at least in part e.g. in a manner as shown in Figure 2 wherein a surface view of the wood panel 110 is provided and the system is shown as a top-view. This may require at least a selection of the X-ray imaging unit 130 in a necessary way and adjustment its operation accordingly with respect to the travel path of the wood panel 110. Worth understanding is that only a portion of the wood panel 110 or the whole wood panel 110 may be imaged by the X-ray image unit 130 and in the context of the present invention. In case only portion of the wood panel 110 is imaged it refers to that at least one or more edge areas of the wood panel 110 are imaged at least in part in a manner as is described in the forthcoming description.

[0038] Correspondingly, the at least one camera unit 140 may be configured to capture image over a full length of the edge of the wood panel 110 (cf. in z direction of the coordinate system shown in Figure 2) when the panel 110 travels by the camera unit 140. Naturally, only a portion of the length of the edge may be imaged. It is also possible to combine images together if they illustrate only the portions of the length of the edge if necessary.

[0039] For sake of clarity it is worthwhile to mention that the X-ray image unit 130 may be implemented so that it comprises only one X-ray source and a detector extending over the width of the wood panel 110 so that the whole wood panel 110 may be imaged. Alternatively, the X-ray image unit 130 may comprise two X-ray source and X-ray detector setups positioned so that they generate data from the respective edge areas of the wood panel 110 into which they are arranged. This kind of approach is schematically illustrated in Figure 2. Further derivatives of the implementation may be introduced, e.g. such that only one X-ray source extending over the width of the wood panel 110 is used whereas two separate detectors are arranged in the areas of interest, i.e. on the edge areas of the wood panel 110, so that desired image data may be generated. The X-ray image unit 130 and the camera unit 140 are configured to operate so that both pieces of image data comprise a portion that represents the image captured with the different imaging techniques representing the same portion of the wood panel 110. In other words, even if the imaging units 130, 140 are arranged to capture images from different angles, the same portion of the wood panel 110 is at least partially represented in the pieces of image data from different perspectives.

[0040] The implementation according to Figure 1 is based on that the source of X-ray radiation is above the travel path of the wood panel 110 and the at least one camera unit 140 is on the side of the travel path of the wood panel 110. Naturally, the detector of the X-ray unit 130 is then below the travel path of the wood panel 100. However, the implementation of the X-ray imaging unit 130 may be arranged so that the source or X-ray radiation is below the travel path of the wood panel 110 and the detector of the X-ray unit 130 is above the travel path. In at least some preferred embodiments both side edges of the wood panel 110 are imaged by arranging the camera unit 140 on both sides of the wood panel 110 in terms of the travel direction as shown in Figure 2. Any of the implementations shall be implemented so that the number of conveyors 150, nor other entities, does not block the imaging of the wood panel 110 with any of the imaging techniques. For example, the X-ray imaging unit 130 may be arranged between the conveyors 150 so that the wood panel travels between the X-ray source and the X-ray detector when the panel 150 travels from one conveyor 150 to another as shown in Figures 1 and 2. It may also be arranged that the conveyor 150 applied in the context of the present invention is such that it is arranged to grip the panel 110 with specific gripping devices, such as suction units, and the wood panel 110 may then be imaged without any blocking elements of the conveyor(s) 150. Worth recognizing is that Figures 1 and 2 are provided with coordinate systems in order to increase understanding on the implementation of the system in a 3-dimensional space (cf. xyz-coordinate system). In accordance with another embodiment the imaging units 130, 140, or at least one of them, may be configured to be movable so that it may be arranged to perform the imaging by moving with respect to the wood panel 110 at a different speed than the wood panel 110 is moving if any. For example, the wood panel 110 may be stopped at a predefined position wherein a scanning of the wood panel 110 with at least one of the imaging techniques is performed with a movable imaging unit 130, 140. The movable imaging unit 130, 140 may refer to that the X-ray imaging unit 130 is arranged to move above or below the stopped wood panel 110 e.g. over a predefined area of the wood panel 110, such as over the whole area of the wood panel 110, and the one or more camera units 140 are arranged to travel on the side of the wood panel 110 so that the edge of the wood panel 110 may be imaged. Alternatively or in addition, the at least one imaging unit 130, 140 may be arranged to be movable at a predefined position over at least one axis, i.e. the imaging unit 130, 140 performs the movement over at least one axis so that it may direct the beam or capture light over the wood panel 110 from the position the imaging unit 130, 140 resides. Naturally, the respective detector unit(s) is / are arranged to follow the source of the X-ray radiation so that the measurement data may be captured. The movement of the mentioned entities may be arranged with movable arms and / or by arranging the movable entities to guide rails along which the entities may be moved with a help of actuators / motors providing the force for movement.

[0041] For avoidance of doubt it is worthwhile to mention that the imaging units 130, 140 may be controlled in a desired manner, such as the wood panel 110 is automatically imaged with both imaging techniques. Alternatively, the operations of the imaging units 130, 140 may be made dependent on each other. For example, in a preferred approach each wood panel 110 may be imaged with the X-ray unit 130 and the X-ray image data is analyzed. If the analysis generates one or more predefined detections, the imaging with the camera unit 140 is triggered. This kind of approach may require that the imaging units 130, 140 are positioned with respect to each other so that the analysis and the control of them may be optimally performed. Alternatively or in addition, it may be arranged that the movement of the wood panel 110 in the travel path is arranged so that the wood panel 110 may be brought to the camera unit 140 if it is triggered by the analysis of X-ray image data.

[0042] Next at least some aspects of the invention are described by referring to Figure

[0043] 3 schematically illustrating a method according to an example. The method is for generating an estimation of a defect in a wood panel 110 comprising a plurality of layers. The invention is especially advantageous with wood panels 110 comprising more than three layers because the invention enables an estimation of defects intruding the wood panel 1 10, i.e. not fully visible on the surface portions of the wood panel 110. The method may be performed by a computing system 120 as mentioned.

[0044] For increasing an understanding of the method it is also referred to Figure 4 wherein aspects of the detection system 100 for evaluating a wood panel 110 are provided. The wood panel 110 of Figure 4 comprises four layers wherein the topmost and the bottommost layers also called as surface layers in Figure

[0045] 4 and the other two layers are mid-layers between the surface layers. The wood panel 110 as schematically illustrated in Figure 4 comprises a defect visible at the edge of the wood panel 110 which also intrudes the panel 110 as a cavity. More specifically, the defect is in at least one of the mid-layers. Further, the camera unit 140 is arranged to capture image data at least on the edge of the wood panel 110, i.e. from the surface of the wood panel 110 showing the layers, i.e. the ends of them, from which the wood panel 110 is formed, and the X-ray imaging unit 130 is arranged to generate image data captured with X-rays at least partially penetrating through the layered structure of the wood panel 110. Naturally the defect may be another type of defect and / or reside in another manner but the advantages of the present invention become clear in the best manner when the defect is in the mid-layer(s) and intruding the wood panel 110 even though the invention is applicable with other types of defects as well.

[0046] In accordance with the method X-ray image data representing a first portion of the wood panel 110 is received 310. This refers to an approach wherein at least a portion of the wood panel 110 is imaged with the X-ray imaging unit 130 wherein the imaged portion comprises image data representing at least one edge area of the wood panel 110. The computing system 120 is configured to analyse 320 the X-ray image data to detect if there is possible defects, i.e. candidate defects, in the wood panel 110 on the basis of the analysis 320 of the X-ray image data. The analysis 320 of the X-ray image data may be based on a detection of candidate defects based on density analysis, i.e. since the X- rays attenuate in a different manner in accordance with the density in the imaged object and the differences in the density of the object, i.e. the wood panel 110, may be identified on the basis of variations in contrast in various regions in the X-ray image. In other words, if e.g. a portion of a layer being part of the wood panel 110 is missing, the deviation in a density of the wood panel 110 in the area the layer is missing may be detected as a deviating portion, such as a darker or lighter portion depending on the applied imaging technique, in the image data because there occurs less attenuation of the X-rays than in other portions of the wood panel 110. Correspondingly, if there has occurred overlapping of a layer in the structure of the wood panel 110 imaged with X- ray imaging unit 130, the increased attenuation of the X-rays may be detected in the X-ray image data as a deviation in the contrast compared to the surrounding area. Hence, the analysis 320 of the X-ray image data may generate detections in one or more positions, or sub-areas, in the wood panel 110. Such a detection is called as a first candidate defect herein. Thus, the analysis 320 may generate a detection 330 of the first candidate defect in a first position of the wood panel 110. The data indicative of the detection 330 may comprise a definition of the position of the first candidate defect as coordinates in a coordinate system into which the wood panel 110 is computationally positioned to. Additionally, it may comprise a definition with respect to the first candidate defect, such as a value of a contrast within the position of the first candidate defect. In the positioning of the wood panel 110 computationally in the coordinate system predefined markers of the wood panel 110 may be applied to in a known manner (cf. corners / edges of the wood panel 110 / specific markings implemented on the wood panel 110 / etc.). For avoidance of doubt it is worthwhile to mention that in case the analysis 320 of the X-ray image data does not generate the detection 330 of the first candidate defect, a predefined operation may be performed. The predefined operation may e.g. refer to that an execution of the method according to the present invention is discontinued with respect to the wood panel 110 in question. Alternatively or in addition, a notification indicative of that no candidate defects are detected from the X-ray image data may be generated, for example. This is not shown in Figure 3 wherein it is assumed that the candidate defect is detected 330 from the X-ray image data as referred with the step denoted with 330.

[0047] Correspondingly, in accordance with the present invention an image data representing a second portion of the wood panel 110 is received 340 from the camera unit 140. The pieces of image data with the X-ray image unit 130 and with the camera unit 140 may be captured simultaneously to each other at least in part or consecutively to each other. For example, the capturing of the image with the camera unit 140 may be triggered by a predefined condition with respect to the X-ray image data and vice versa.

[0048] In accordance with the invention the images with the different imaging techniques are captured so that the X-ray image and the visual image represent at least in part a common portion of the wood panel 110, i.e. the same portion, or area, of the wood panel 110 is at least in part imaged with both imaging techniques from different perspectives. For example, the first portion may cover the whole wood panel 110 in question whereas the second portion may cover the edge of the wood panel 110 over its full length. In any case, for the purpose of the present invention the first portion and the second portion comprise a portion that is detected as a candidate defect from both image data and the information is combined in a manner as is described in the forthcoming description. In accordance with an embodiment of the invention the detection system 100 may be configured so that the imaging units 130, 140 are configured to capture the images so that there always exists the common portion in the manner as described herein. In response to the receipt 340 of the image data the computing system 120 is configured to analyse 350 the image data and to detect 350 whether there exists candidate defects on the edge of the wood panel 110 based on the image data. Hence, the analysis 350 of the image data may generate detections in one or more positions on the edge of the wood panel 110 from which the image data is captured from. Such a detection is called as a second candidate defect herein (cf. the defect on the edge of the wood panel 110 as shown in Figure 4). Thus, the analysis 350 may generate a detection 360 of the second candidate defect in a second position of the wood panel 110. The data indicative of the detection 360 may comprise a definition of the position of the second candidate defect as coordinates in a coordinate system into which the wood panel 110 is computationally positioned to. In the case of the defect on the edge the coordinate may e.g. define the position as a distance from the leading edge and / or the trailing edge of the wood panel 110 in the direction of transport (cf. travel direction). The candidate defect detected through the analysis 350 of the image data is a deviation in the edge of the wood panel 110. The deviation may e.g. correspond to a missing portion of at least one layer of the wood panel 110, such as one of the inner layers, in a position of the edge. Correspondingly, the deviation may correspond to an overlapping layer, i.e. a layer is not correctly stacked in the structure, and it is visible on the edge of the wood panel 110 and detectable therefrom through the imaging and analysis of the image(s). The detection 360 of this kinds of defects may be based on predefined pattern recognition algorithms, for example, that are applied in the analysis step 350 of the method.

[0049] For avoidance of doubt, the positions of the candidate defects from the X-ray image data analysis 320 and the visual image data analysis 350 are defined in the same coordinate system so as to make them comparable in position with respect to each other. The coordinate system is at least two-dimensional, but also a three-dimensional coordinate system may be applied to especially when defining an estimation of the defect e.g. in terms of its characteristics. For example, the same kind of computational positioning of the second candidate defect to the coordinate system may be applied to as already described in the context of the X-ray image processing in the foregoing description (cf. markers). For avoidance of doubt it is worthwhile to mention that in case the analysis 350 of the image data does not generate the detection 360 of the second candidate defect, a predefined operation may be performed. The predefined operation may e.g. refer to that an execution of the method according to the present invention is discontinued with respect to the wood panel 110 in question. Alternatively, or in addition, a notification indicative of that no candidate defects are detected from the visual image data may be generated, for example. This is not shown in Figure 3 wherein it is assumed that the second candidate defect is detected 360 from the image data as referred with the step denoted with 330.

[0050] In the foregoing description there is provided various aspects how the image data and the X-ray image data are positioned in the same coordinate system. As such the applied methods are commonly known. As a further example it may be mentioned that the images from the different image units 130, 140 may be aligned together on a basis of a known physical distance of them from each other measured e.g. with respect to a certain point, such as with respect to a certain pixel of the visual image, i.e. the first pixel in the detector of the image unit 130, e.g. in necessary directions. These pieces of known information may be combined with other system specification data e.g. comprising a resolution of the detector of the image unit 130, a resolution of the detector of the X-ray image unit 140 and that allows an adjustment (cf. stretching) of the X-ray image to the same coordinate system with the visual image, i.e. computationally manipulating the sizes of the images to visually correspond to each other so as to make the information in them comparable e.g. in terms of a position. The approach is known as such and the description herein is thus simplified.

[0051] The analysis 350 of the image data is based on that a structure with or without defects generate specific kinds of reflections of the light or certain reflections are lacking (that are present when the wood panel 110 is proper) which may be identified from the image data and, thus, the defect may be determined with a certain probability on the edge of the wood panel 110. For example, a missing portion of a layer in the wood panel 110 (of. a cavity on the edge of the wood panel 110) or an overlap of a layer generate reflections of light that may be detected in the image data e.g. on the basis of the pattern recognition algorithms or even by applying a trained machine-learning model for that. Hence, the outcome of the analysis 350 may be a position of the candidate defect and a definition of the type of the defect.

[0052] It is also worth mentioning that the steps of analyzing 320, 350 of the respective image data may generate detections 330, 360 of a plurality of candidate defects and these may be processed individually in the corresponding manner as described herein.

[0053] As a result of the method as described above the computing system 120 is aware of the result of the X-ray image data analysis 320 and the result of the image data analysis 350 and is configured to generate 370 a detection result based on these. The generation 370 of the detection result may refer to an operation in which the computing system 120 is configured to generate 370 the detection result by evaluating data representing the first candidate defect and the second candidate defect with respect to each other. The evaluation at least comprises that the positions of the first and the second candidate defects are compared to each other in order to confirm that they represent the same position, and thus the same defect, in the wood panel 110 in a predefined manner, i.e. if the first position representing the position of the first candidate defect and the second position representing the position of the second candidate defect match with a predefined accuracy. The predefined accuracy may e.g. correspond to a situation in which a candidate defect is detected from the image data representing the edge of the wood panel 1 10 and at the same position but detected from the X-ray image data a candidate defect is also detected even if these two pieces of image data are captured from the wood panel 110 from different perspectives e.g. as derivable from Figure 4. Thus, in case at least one of the analyses 320, 350 generate a plurality of candidate detections all these are compared to each other in terms of the position in order to find if any of the first candidate defects and any of the second candidate defects represent the same position. As already mentioned, this is possible since at least part of the X-ray image data and at least part of the image data represent the same portion, aka. the common portion, of the wood panel 110 even if captured from different perspectives. To describe the present invention further it is hereby assumed that the evaluation of the first candidate defect and the second candidate defect generates a detection that they reside in the same position wherein the term ‘position’ refer to a definition of the position in a predefined manner in both analysis 320, 350. For example, the first candidate defect generated from the X-ray image data may define the position as an area defined by coordinates that extend from an edge of the wood panel 110 inwards. The position of the second candidate defect may e.g. be defined as coordinates on the edge of the wood panel 110. Hence, these two definitions for the positions of the candidate defects may comprise common points in the same coordinate system and, thus, an estimation of the defect may be generated as is described in the forthcoming description.

[0054] More specifically, the generation 370 of the estimation of the defect comprises an operation in which one or more values expressing one or more characteristics of the defect are determined. The one or more characteristic may refer to a determination at least a size of the defect and the position of it. To elaborate this further it is hereby referred to Figures 5A and 5B wherein Figure 5A illustrates schematically an X-ray image captured over the whole wood panel 110 and Figure 5B illustrates schematically a visual image of the edge of the wood panel 110. Through the analyses, e.g. with a pattern recognition of a trained machine-learning model, the same defect may be detected from both image data. From the X-ray image data, as shown in Figure, 5A the defect may be detected due to a deviating contrast in the image based on which the area of the defect may be defined as coordinates (e.g. as an area in xz-domain in xyz-coordinate system) as shown in Figure 5A. For avoidance of doubt it is worthwhile to mention that naturally the defect may also be defined in y-axis as to correspond the full thickness of the wood panel 110. Further, from the visual image data, as shown in Figure 5B, the same defect may be detected and its position may be defined as coordinates (e.g. as an area in xy-domain in xyz-coordinate system). Correspondingly, for avoidance of doubt the defect may also be defined in z-axis as to correspond the full width of the wood panel 110. Thus, since the coordinates at least in x- axis, but also in z-axis, at least partly correspond to each other in a predefined margin it may be concluded that they relate to the same defect. As a result, the computing system 120 may be configured to generate 370 the estimation by defining a size of the defect in xyz-directions which may e.g. define the one or more layers in which the defect exists thus to enrich the information from the X-ray image data defining the depth, and form, of the cavity starting from the edge of the wood panel 110. In case the wood panel 110 is a solid structure (i.e. not composed from a plurality of layers) the position of the cavity may be expressed as coordinates in y-direction. For avoidance of doubt, the applied coordinate system comprises an origo that may be set on a predefined position, such as in a corner of the wood panel 100 in 3-dimensional space.

[0055] In the foregoing description of at least some aspects of the present invention it is assumed that the X-ray imaging and the visual imaging are performed and processed independently from each other until the final detection result is generated 370. However, the invention may be implemented so that a first image is captured with one of imaging techniques among the X-ray imaging and the visual imaging and the captured image data is processed until it may be used to control an imaging of the wood panel 110 with the other imaging technique among the X-ray imaging and the visual imaging. For example, the X-ray imaging may be performed first so that the computing system 120 receives 310 the X-ray image data. The analysis 320 and the detection of the one or more first candidate defects 330 may be performed as described in the foregoing description. As a result, the computing system is 120 aware of the at least one first candidate defect in the wood panel 110 and its position. In accordance with an embodiment of the invention the computing system 120 may be configured to control the camera unit 140 on the basis of the information generated in the analysis 320 of the X-ray image data. For example, the control of the camera unit 140 may be performed so that it is instructed with a control signal, by the computing system 120, to capture the visual image from the position in which the first candidate defect is determined to reside in the analysis 320 of the X-ray image data. In response to capturing of the visual image from the position and receiving 340 the data the computing system 120 may perform the analysis 350 and the detection 360 of second candidate defect as already described in the foregoing description. In the context of the present invention a preferred approach may be that one or more edges of the wood panel 110 are continuously imaged over the full length of the wood panel 110 and if a defect is identified from the image data, the X-ray imaging unit 130 is controlled to capture X-ray image from the corresponding position defined in a manner that it at least covers a predefined area of the wood panel 110 with respect to the defined position. The advantage of this kind of approach is that an efficiency of the detection system 100 may be improved since the X-ray imaging is not performed over the whole wood panel 110 and the data needed to be analyzed is optimized. In view of the present invention the middle portion of the wood panel 110 is not necessary to get imaged as already indicated in the foregoing description when discussing on the implementation of the system in the context of Figure 2, for instance.

[0056] The described method according to at least one embodiment of the invention generates the estimation of the defect so that it may be utilized at later stages of the production. Namely, the computing system 120 may be configured to evaluate if the position of the defect may be cut away from the wood panel 110. This e.g. refers to an evaluation whether the size of the defect is with predefined limits. If this is the case the computing system 120 may be configured to generate a control signal to a controller of a trimming line so as to control the trimming line to finalize the wood panel 110 so that the defect may be removed. Naturally, in some cases the defect may be evaluated to be such that it cannot be trimmed and the wood panel 110 may then be abandoned.

[0057] An example of a computing apparatus suitable to implement a functionality of the computing system 120 is schematically illustrated in Figure 6. The computing apparatus implanting the functionality of the computing system 120 may be a computer device, for example. For sake of clarity, it is worthwhile to mention that the block diagram of Figure 6 depicts some components of an entity that may be employed to implement a functionality of the apparatus.

[0058] The apparatus of Figure 6 comprises a processing unit 610 consisting of a number of processors and a memory 620. The memory 620 may store data, but also computer program code 625, causing an operation in a manner as is described in the foregoing description. The apparatus may further comprise a communication interface 630, such as a wireless communication interface or a communication interface for wired communication, or both to communicate with other entities at least belonging to the detection system 100 as described. The communication interface 630 may thus comprise one or more modems, antennas, and any other hardware and software for enabling an execution of the communication e.g. under control of the processing unit 610. Furthermore, I / O (input / output) components may be arranged, together with the processing unit 610 and a portion of the computer program code 625, to provide a user interface for receiving input from an operator and / or providing output to the operator of the apparatus when necessary. In particular, the I / O components may include user input means, such as one or more keys or buttons, a keyboard, a touchscreen, or a touchpad, etc. The I / O components may also include output means, such as a loudspeaker, a display, or a touchscreen. The components of the apparatus may be communicatively connected to each other via data bus that enables transfer of data and control information between the components.

[0059] The memory 620 and at least a portion of the computer program code 625 stored therein may further be arranged, with the processing unit 610, to cause the apparatus to perform at least a portion of a method as is described in the forthcoming description. The processor 610 may be configured to read from and write to the memory 620. Although the processing unit 610 is depicted as a respective single component, it may be implemented as respective one or more separate processing components. Similarly, although the memory 620 is depicted as a respective single component, it may be implemented as respective one or more separate components, some, or all of which may be integrated I removable and I or may provide permanent I semi-permanent I dynamic / cached storage.

[0060] The computer program code 625 may comprise computer-executable instructions that implement functions that correspond to steps implemented in the method when loaded into the processing unit 610 of the respective computing system 120. As an example, the computer program code 625 may include a computer program consisting of one or more sequences of one or more instructions which may relate to an execution of the generation of estimation but also other operations, such as to control the trimming based on the result of the generation of the estimation. The processing unit 610 is able to load and execute the computer program by reading the one or more sequences of one or more instructions included therein from the memory 620. The one or more sequences of one or more instructions may be configured to, when executed by the processing unit 610, cause the apparatus to perform a method as described. Hence, the apparatus may comprise at least one processing unit 610 and at least one memory 620 including the computer program code 625 for one or more programs, the at least one memory 620 and the computer program code 625 configured to, with the at least one processor 610, cause the apparatus implementing the computing system 120 to perform at least the method as described.

[0061] The computer program code 625 may be provided e.g. a computer program product comprising at least one computer-readable non-transitory medium having the computer program code 625 stored thereon, which computer program code 625, when executed by the at least one processor of the processing unit 610, causes the apparatus to perform the method. The computer-readable non-transitory medium may comprise a memory device or a record medium, such as a CD-ROM, a DVD, a Blu-ray disc, or another article of manufacture that tangibly embodies the computer program. As another example, the computer program may be provided as a signal configured to reliably transfer the computer program. Still further, the computer program code 625 may comprise a proprietary application, such as computer program code for causing an execution of the method in the manner as described in the description herein.

[0062] Any of the programmed functions mentioned may also be performed in firmware or hardware adapted to or programmed to perform the necessary tasks.

[0063] The operation of the apparatus implementing the computing system 120 may be implemented with a plurality of apparatuses, such as with the one schematically illustrated in Figure 6, as a distributed computing environment. The distributed computing environment may be implemented as a cloud computing system wherein a number of apparatuses are harnessed to execute operations to generate an implementation of a method as is described herein. In the distributed computing environment the plurality of apparatuses are each configured to perform a dedicated task or dedicated tasks and the cooperation of the apparatuses cause the operation of the controller to occur in the manner as is described herein.

[0064] The invention is primarily described herein in relation to wood panels 110 comprising a plurality of layers, but the invention as such is not limited only to such kinds of wood panels 110. For example, the invention may be used with so-called blockboards in the corresponding manner as described. Moreover, it is mainly described that the defect identified corresponds to a missing portion of at least one layer. However, the invention is also applicable with situations in which there has occurred an overlap of a layer in the structure of the wood panel 110.

[0065] Hence, the invention is based on utilization various imaging techniques to generate image data based on which conclusions on a wood panel may be made. In other words, the pieces of image data from the different imaging techniques are evaluated and combined in the described manner so that improved conclusions on the wood panel, and specifically estimations of defect(s) therein, may be made. The specific examples provided in the description given above should not be construed as limiting the applicability and / or the interpretation of the appended claims. Lists and groups of examples provided in the description given above are not exhaustive unless otherwise explicitly stated.

Claims

WHAT IS CLAIMED IS:1 . A method for generating an estimation of a defect in a wood panel (110) comprising a plurality of layers, the method, performed by a computing system (120), comprises: receiving (310) an X-ray image data representing a first portion of the wood panel (110), receiving (340) an image data representing a second portion of the wood panel (110), the second portion of the wood panel (110) representing at least part of an edge of the wood panel (110), wherein the image data and the X-ray image data representing a common portion of the wood panel (110), the method further comprises: detecting (330) a first candidate defect in a position of the wood panel (110) by analyzing (320) the X-ray image data, detecting (360) a second candidate defect indicative of a deviation in a layered structure of the wood panel (110) in a position of the wood panel (110) by analyzing (360) the image data, generating (370) the estimation of the defect in the wood panel (110) based on the analysis of X-ray image data and the analysis of the image data.

2. A method according to claim 1 , wherein the image data representing the second portion of the wood panel (110) is received from a camera unit (140) arranged to capture image on at least part of the edge of the wood panel (110) having a layered structure.

3. The method according to any of the preceding claims, wherein the X-ray image data representing the first portion of the wood panel (110) is received from X-ray imaging unit (130) configured to capture X-ray image in a direction deviating from a parallel direction of a surface layer of the wood panel (110).

4. The method according to any of the preceding claims, wherein the generation of the estimation of the defect is performed by determining at least one value expressing at least one characteristic of the defect.

5. The method according to claim 4, wherein the at least one characteristic is at least one of the following: a size of the defect, a position of the defect.

6. A computing system (120) of a detection system (100) for generating an estimation of a defect in a wood panel (110) comprising a plurality of layers, the computing system (120) is configured to carry out the method according to any of the claims 1 to 5.

7. A computer program comprising instructions, when the program is executed by a computing system (120) of claim 6, cause the computing system (120) to carry out the method according to claim 1 .

8. A detection system (120) comprising: a camera unit (140), an X-ray imaging unit (130), and the computing system (120) according to claim 6.

9. The detection system (120) according to claim 8, wherein the camera unit (140) is operative in a spectrum of an electromagnetic radiation corresponding to one of: visible light, ultraviolet light, infrared light.

10. The detection system (120) according to claim 8 or claim 9, wherein the camera unit (140) is implemented with an arrangement applying laser light.

Images