Apparatus and method for inspecting appearance of product
By calculating and correcting the average brightness of the region of interest, the problem that image brightness changes affect the inspection accuracy is solved, and uniform brightness and efficient defect detection are achieved.
Patent Information
- Application Number
- CN202380032509.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-07-31
- Filing Date
- 2023-09-18
- Publication Date
- 2024-11-26
AI Technical Summary
In the prior art In product appearance inspection, changes in image brightness lead to a decrease in the predetermined capability of the inspection algorithm, and it is impossible to effectively deal with the brightness changes caused by the end of the lighting life or the change in the surface color.
By calculating the average brightness of the region of interest and calculating the correction gain value based on the target brightness, each pixel is brightly corrected to ensure the uniform brightness of the image, thereby improving the accuracy of defect inspection.
Even if the lighting conditions of the optical system change, an image with uniform brightness can be obtained, thereby improving the accuracy of checking whether the product has defects.
Smart Images

Figure CN119032267A_ABST
Abstract
Description
Technical Field
[0001] This application claims priority to and the benefit of Korean Patent Application No. 10-2022-0117571 filed in the Korean Intellectual Property Office on September 19, 2022, and Korean Patent Application No. 10-2023-0099316 filed in the Korean Intellectual Property Office on July 31, 2023, the entire contents of which are incorporated herein by reference.
[0002] The present invention relates to an apparatus and method for inspecting the appearance of a product, and more particularly, to an apparatus and method for inspecting the appearance of a product by processing an inspection image by adjusting the brightness of an inspection area in the image. Background Art
[0003] Secondary batteries that can be recharged and reused can be used as energy sources for small devices such as mobile phones, tablet PCs, and vacuum cleaners, and can also be used as energy sources for medium to large devices such as personal mobile devices, automobiles, and energy storage systems (ESS) for smart grids. Depending on the requirements of the system, secondary batteries can be used in the form of components such as battery modules in which multiple battery cells are connected in series or in parallel, or battery packs in which multiple battery modules are connected in series or in parallel.
[0004] The battery can be manufactured through processes including electrode processes, assembly processes, forming processes, and other processes, and inspection equipment is used to inspect the defects of the manufactured battery cells or the results of each process. Among the defect inspection methods, one of the commonly used techniques is appearance inspection. Appearance inspection can be done by using an optical system to obtain an image of the product and using an inspection algorithm to inspect defects.
[0005] However, after a specific inspection algorithm is determined, the brightness of the obtained image may become different from the original intended brightness of the image due to changes in the surface color of the product or changes in the lighting due to the end of the lighting life. In this case, the problem of the inspection capability of the predetermined algorithm arises. Summary of the invention
[0006] Technical issues
[0007] To avoid one or more problems in the background art, embodiments of the present disclosure provide a method for inspecting appearance of a product, which processes an inspection image by adjusting the brightness of an inspection area in the image to a predetermined value.
[0008] In order to avoid one or more problems in the background art, embodiments of the present disclosure also provide a visual inspection device using a visual inspection method for a product.
[0009] Technical Solution
[0010] In order to achieve the purpose of the present disclosure, a product appearance inspection method may include the following steps: acquiring and preprocessing an appearance image of a target object; extracting a region of interest from the preprocessed image and performing brightness correction on the extracted region of interest; extracting defect candidates from the brightness corrected image; performing image post-processing on the extracted defect candidates; and determining whether the target object is defective from the post-processed image.
[0011] The step of performing brightness correction on the extracted region of interest may include the following steps: calculating an average brightness of pixels within the extracted region of interest; calculating a correction gain value based on the calculated average brightness and a target brightness; and correcting the brightness of each pixel according to the correction gain value.
[0012] The step of calculating the correction gain value based on the calculated average brightness and the target brightness may include the step of calculating the correction gain value by dividing the target brightness by the average brightness.
[0013] The step of correcting the brightness of each pixel according to the correction gain value may include the step of multiplying the original brightness of each pixel by the correction gain value to correct the brightness of each pixel.
[0014] The step of calculating the average brightness of the pixels within the extracted region of interest may include the step of calculating the average brightness based on the number of pixels in the region of interest and the brightness of each pixel.
[0015] Here, the target brightness may be determined by a user.
[0016] The step of performing brightness correction on the extracted region of interest may comprise the step of changing the captured color image into a grayscale image before applying the brightness correction to the captured color image.
[0017] The step of performing brightness correction on the extracted region of interest may include the step of separating the captured color image into an R channel, a G channel, and a B channel before applying the brightness correction to the color image.
[0018] Therefore, the step of calculating the average brightness of the pixels, the step of calculating the correction gain value, and the step of correcting the brightness of each pixel may be performed on each of the R channel, the G channel, and the B channel.
[0019] According to another embodiment of the present disclosure, a product appearance inspection device may include: at least one processor; and a memory, the memory being configured to store at least one instruction executed by the at least one processor, and the at least one instruction may include: instructions for acquiring and preprocessing an appearance image of a target object; instructions for extracting a region of interest from a preprocessed image and performing brightness correction on the extracted region of interest; instructions for extracting defect candidates from a brightness-corrected image; instructions for performing image post-processing on the extracted defect candidates; and instructions for determining whether the target object is defective from the post-processed image.
[0020] The appearance inspection apparatus according to the embodiment of the present invention may cooperate with an imaging device that captures the appearance of the target object, or the appearance inspection apparatus may include the imaging device.
[0021] The instructions for performing brightness correction on the extracted region of interest may include: instructions for calculating the average brightness of pixels within the extracted region of interest; instructions for calculating a correction gain value based on the calculated average brightness and a target brightness; and instructions for correcting the brightness of each pixel according to the correction gain value.
[0022] The instructions for calculating the correction gain value based on the calculated average brightness and the target brightness may include instructions for calculating the correction gain value by dividing the target brightness by the average brightness.
[0023] The instructions for correcting the brightness of each pixel according to the correction gain value may include instructions for multiplying the original brightness of each pixel by the correction gain value to correct the brightness of each pixel. The instructions for calculating the average brightness of the pixels within the extracted region of interest may include instructions for calculating the average brightness based on the number of pixels in the region of interest and the brightness of each pixel.
[0024] Here, the target brightness may be determined by a user.
[0025] Additionally, the instructions for performing brightness correction on the extracted region of interest may include instructions for changing the captured color image to a grayscale image before applying the brightness correction to the captured color image.
[0026] The instructions for performing brightness correction on the extracted region of interest may include instructions for separating a captured color image into an R channel, a G channel, and a B channel before applying the brightness correction to the color image.
[0027] Therefore, the instruction for calculating the average brightness of the pixels, the instruction for calculating the correction gain value, and the instruction for correcting the brightness of each pixel may be executed on each of the R channel, the G channel, and the B channel.
[0028] Beneficial Effects
[0029] According to the embodiments of the present invention as described above, the average brightness of the inspection target region (region of interest: ROI) is calculated and corrected to a specified brightness, and therefore, an image of uniform brightness can be obtained even if the illumination condition of the optical system changes.
[0030] Therefore, the inspection accuracy for determining whether a product is defective can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 It is an operation flow chart of the general appearance inspection method.
[0032] Figure 2 is an operation flow chart of a visual inspection method according to an embodiment of the present invention.
[0033] Figure 3 is a diagram showing a detailed process of brightness correction according to an embodiment of the present invention.
[0034] Figure 4 FIG. 1 is a diagram showing a comparison between an image obtained by brightness correction according to an embodiment of the present invention and an original image.
[0035] Figure 5 is an example of providing a user interface screen for appearance inspection according to an embodiment of the present invention.
[0036] Figures 6a to 6c is a graph comparing appearance inspection results using an image with brightness correction and an image without brightness correction according to an embodiment of the present invention.
[0037] Figure 7 Images measured and processed using various illumination intensities and various correction target brightnesses are shown in accordance with an embodiment of the present invention.
[0038] Figure 8 is a graph showing a deviation in inspection size between a contamination size inspected by performing brightness correction according to the present invention and an inspection result through a microscope.
[0039] Fig. 9 is a perspective view of an imaging device according to an embodiment of the present invention.
[0040] Fig.10 is a cross-sectional view of an imaging device according to an embodiment of the present invention.
[0041] Fig.11a is a diagram showing the appearance of an imaging device according to another embodiment of the present invention.
[0042] Fig.11b is a diagram showing a multi-channel illumination configuration of an imaging device according to another embodiment of the present invention.
[0043] Fig.12 is a block diagram of a visual inspection apparatus according to an embodiment of the present invention.
[0044] 1000: Appearance inspection equipment
[0045] 1010: Processor
[0046] 1020: Memory
[0047] 1040: Input interface device
[0048] 1050: Output interface device
[0049] 1060: Storage device DETAILED DESCRIPTION
[0050] The present invention can be modified in various forms and has various embodiments, and its specific embodiments are shown in the accompanying drawings by way of example and will be described in detail below. However, it should be understood that it is not intended to limit the present invention to a specific embodiment, but on the contrary, the present invention will cover all modifications, equivalents and replacements that fall within the spirit and technical scope of the present invention. Throughout the description of the drawings, the same reference numerals refer to the same elements.
[0051] It should be understood that, although various elements may be described herein using terms such as first, second, A, B, etc., these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. As used herein, the term "and / or" includes a combination of any of a plurality of associated listings or a plurality of associated listings.
[0052] It should be understood that when an element is referred to as being "coupled" or "connected" to another element, the element may be directly coupled or connected to the other element, or there may be intermediate elements. Conversely, when an element is referred to as being "directly coupled" or "directly connected" to another element, there are no intermediate elements.
[0053] The terms used herein are only used for the purpose of describing specific embodiments and are not intended to limit the present invention. As used herein, the singular forms "one", "an" and "the" are also intended to include plural forms unless the context clearly indicates otherwise. It will also be understood that the terms "comprise", "include", "contain", "consist of" and / or "have" when used herein specify the presence of the features, integers, steps, operations, constituent elements, components and / or combinations thereof, but do not exclude the presence or addition of one or more other features, integers, steps, operations, constituent elements, components and / or combinations thereof.
[0054] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and will not be interpreted in an idealized or overly formal sense unless expressly defined as such herein.
[0055] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.
[0056] Figure 1 It is an operation flow chart of the general appearance inspection method.
[0057] A general appearance inspection method for a component or product may include an image preprocessing process (S11), a defect candidate extraction process (S12), an image postprocessing process (S13), and a defect determination process (S14).
[0058] The parts / products to be inspected can be obtained as image data by an imaging device (photographic device) as an optical system, and one or more objects related to a plurality of parts / products can be included in one image.
[0059] The image preprocessing process (S11) is a process of highlighting the features of the image of the target object before inspection to facilitate inspection, and methods such as binarization and normalization can be used as image preprocessing. The image preprocessing process can also include overall amplification of the brightness of the image of the target object.
[0060] In the defect candidate extraction process (S12), a candidate group suspected of having defects is extracted from a plurality of objects included in the inspected image. Objects with potential defect characteristics appearing in the image may be selected as candidates.
[0061] In the image post-processing process (S13), feature values of defect candidates are extracted. Here, the feature values may be values related to brightness (intensity), shape, texture, etc. of an object included in the image.
[0062] In the defect determination process (S14), the extracted feature values are analyzed to determine whether a defect or abnormality has occurred in the product / part associated with the object.
[0063] In the above-mentioned general appearance inspection method, the brightness amplification included in the image preprocessing process is performed by randomly amplifying the overall brightness of the image. According to this method, the brightness of the image may not be uniformly corrected to the desired brightness, and therefore, the brightness correction value must be adjusted differently for each image.
[0064] As a result, when the brightness changes due to the end of the life of the lighting, or when there is a deviation in the color of some cell materials, the inspection result according to the conventional method may change, and therefore, an appropriate inspection result may not be obtained.
[0065] Figure 2 is an operation flow chart of a visual inspection method according to an embodiment of the present invention.
[0066] The appearance inspection method of a product according to an embodiment of the present invention may include an image preprocessing process (S100), a brightness correction process (S200), a defect candidate extraction process (S300), an image postprocessing process (S400), and a defect determination process (S500).
[0067] An image of a component / product to be inspected may be obtained by an imaging device as an optical system, and one or more objects related to a plurality of components / products may be included in one image.
[0068] The image preprocessing process (S100) is a process of highlighting the features of the image of the target object before inspection to facilitate inspection and converting the image obtained by the imaging device through a correction or synthesis process so that defects can be easily identified. The preprocessing process may adopt methods such as image synthesis, binarization, normalization, blurring, and stretching.
[0069] Here, image synthesis can be particularly useful for inspecting defects such as dents and scratches by using multi-channel images to represent a sense of depth in the image, which will be discussed later. In particular, photometric stereo synthesis and phase shift synthesis can be used as image synthesis methods.
[0070] In addition, binarization is the process of resetting the pixel values of the object and background in the image to only two values, which are 1 and 0. Through image correction using binarization, defects in the appearance of the product can be converted to be clearly visible. In addition, normalization is the process of making the pixel values concentrated in a specific part of the image evenly distributed over the entire area. Blurring can also be called smoothing, and can be used to smooth rough images or as a preprocessing process to remove the effects of noise present in the image. In addition, stretching can be used as a preprocessing method to compensate for distorted images.
[0071] According to an embodiment of the present invention, the brightness correction process (S200) may be applied to the pre-processed image, and the brightness correction process (S200) may be performed according to the needs of the user. Figure 2 , the brightness correction process (S200) may be performed when the brightness correction process is set to ON (example of S120). In the brightness correction process (S200), the average brightness of the region of interest may be calculated, and the region of interest may be corrected to a specified brightness. Here, the region of interest (ROI) may represent a region in the inspection image where actual inspection is to be performed.
[0072] In addition, the process of performing brightness correction on a color image according to an embodiment of the present invention can be implemented in two ways.
[0073] The first method is to change a color image to a black and white image, which means changing a color image to a grayscale image and setting a target intensity to correct the brightness.
[0074] The second method is to correct the brightness by setting a target brightness for each RGB channel in the color image. In other words, the target brightness can be set for the red (R) channel, the green (G) channel, and the blue (B) channel of the color image, respectively, and the brightness can be corrected for each channel. Here, the process for calculating the average brightness, calculating the gain value, and calculating the corrected brightness value of each pixel can be performed for each channel respectively.
[0075] In the defect candidate extraction process (S300), a candidate group suspected of having defects is extracted from a plurality of objects included in the inspected image. Objects with potential defect characteristics appearing in the image may be selected as candidates.
[0076] In the defect candidate extraction process (S300), the defect candidate group can be extracted using the brightness difference within the brightness-corrected region of interest (ROI). For example, the defect candidate group can be extracted by determining whether each pixel in the ROI represented by grayscale has a brightness higher than a specific threshold and distinguishing whether it is a shadow area.
[0077] Here, various techniques such as adaptive, dynamic, polar, and local threshold techniques may be used as examples of threshold techniques.
[0078] The image post-processing process (S400) is a process of extracting feature values of defect candidates, and quantitatively calculating representative features such as brightness, shape, size, etc. of the extracted defect candidates. In other words, the feature values of the defect candidate group can be values related to the intensity, shape, texture, etc. of the objects included in the image.
[0079] In more detail, the feature values of the defect candidate may include the area, width, height, circularity, rectangularity, and structure factor of the shape. Regarding the length or size of the defect, the size of the defect candidate group can be determined by the outer diameter of the largest circumscribed circle or by using the area of the defect. Generally, foreign matter or contaminants have the characteristic that the brightness appears darker than the surrounding area. Therefore, this characteristic can be used to extract the corresponding area, and the size and area of the dark area can be used to determine whether it is defective. For example, since scratches or scratches have a straight line shape, scratches or scratches can be distinguished from foreign matter such as silk threads by using a structure factor (struct actor) that quantifies the characteristics of the straight line.
[0080] In the subsequent defect determination process (S500), the extracted feature values are analyzed, and it is determined whether a defect or abnormality has occurred in a product / component associated with the object according to a predetermined inspection standard.
[0081] Figure 3 is a diagram showing a detailed process of brightness correction according to an embodiment of the present invention.
[0082] A region of interest (ROI) is extracted from the captured image, and an average brightness of pixels within the extracted ROI is calculated (S210). The average brightness of pixels within the ROI may be calculated according to Equation 1 below.
[0083] [Formula 1]
[0084]
[0085] In formula 1, I avg represents the average brightness of the pixels in the region of interest, I i represents the brightness of the i-th pixel, and n ROI Indicates the number of pixels in the ROI.
[0086] Once the average brightness of the region of interest is calculated, a correction gain value may be calculated by taking into account the target brightness (S220). The correction gain value may be calculated according to the following equation 2. Here, the target brightness I targe t can be pre-defined by the user.
[0087] [Formula 2]
[0088]
[0089] In Equation 2, φ represents the brightness correction gain, and I target Indicates the correction target brightness, which can be pre-defined by the user and reset through the user interface.
[0090] Then, image brightness correction may be performed by multiplying the original brightness value of each pixel by the correction gain value to obtain a corrected brightness value of each pixel ( S230 ).
[0091] On the other hand, when the brightness is corrected by setting the correction target brightness for each R, G, and B channel in a color image, the average brightness calculation process, the gain value calculation process, and the corrected brightness value calculation process for each pixel can be performed separately for each channel (red (R) channel, green (G) channel, blue (B) channel).
[0092] Figure 4 FIG. 1 is a diagram showing a comparison between an image obtained by brightness correction according to an embodiment of the present invention and an original image.
[0093] The object of the appearance inspection according to the present invention may be a cylindrical, pouch or square battery, in particular a cylindrical battery of various specifications. As an example, a cylindrical battery may include an electrode assembly, a battery can, a cap having a plate shape, and a terminal. A cylindrical battery may additionally include an insulating gasket, a current collector, an insulator, a sealing gasket, etc.
[0094] For the experiment, the contamination effect was obtained by photographing circular patterns of various sizes printed on the upper surface of a cylindrical battery sample. Figure 4 The image shown in .
[0095] exist Figure 4 , the three images on the left show images captured with different illumination brightnesses (i.e., a gating time of 200 μS, a gating time of 400 μS, and a gating time of 600 μS) without using the brightness correction according to the present invention (i.e., the brightness correction mode is turned off). The three images on the right show images captured at different illumination brightnesses when using the brightness correction according to the present invention (i.e., the brightness correction mode is turned on). Here, the gating time is a unit representing the time the lamp is turned on, and as the value of the gating time increases, the time the lamp is turned on increases.
[0096] The brightness of the three captured images on the left side without using the brightness correction mode is proportional to the gate time value. In other words, the three images on the left side do not use the brightness correction mode, so the brightness differences between the three images are clearly visible. On the other hand, in the case of the three images on the right side that perform brightness correction according to the present invention, the brightness differences between the three images are too small to be recognized by the naked eye.
[0097] Figure 5 is an example of providing a user interface screen for appearance inspection according to an embodiment of the present invention.
[0098] The visual inspection device according to an embodiment of the present invention may provide a user interface through which details related to the inspection may be set. The details related to the inspection may include an object / product to be inspected, whether to perform brightness correction, and the intensity of the brightness correction.
[0099] Figure 5 The appearance inspection shown in the user interface screen of is the contamination inspection of the battery can, and the user can directly set items such as whether to perform brightness correction and target intensity (grayscale correction target intensity).
[0100] Figures 6a to 6c is a graph comparing appearance inspection results using an image with brightness correction and an image without brightness correction according to an embodiment of the present invention.
[0101] Figure 6a The inspection results of the upper plane of the battery are shown. Figure 6b shows the inspection results of the lower plane of the battery, and Figure 6c The inspection results of the lateral side of the battery are shown.
[0102] The experiments show that the measurement error (unit: mm) is improved in all three cases when automatic brightness correction is performed (green graph) compared to when automatic brightness correction is not performed (red graph), which represents an average improvement of 60%.
[0103] Figure 7 Images measured and processed using various illumination intensities and various correction target brightnesses are shown in accordance with an embodiment of the present invention.
[0104] More specifically, Figure 7 The resulting images of multiple contaminants of various sizes randomly placed on the upper surface of a cylindrical battery for experiments under three illumination intensities (gating time 200μS, gating time 400μS, gating time 600μS) and different correction target brightnesses (correction mode off, correction targets 64, 128, 192) are shown.
[0105] For images without using the brightness correction mode, the gate time value is proportional to the brightness of the captured image. In the case of using the brightness correction according to the present invention, it can be understood that the brightness of the image after correction has been adjusted within a certain range.
[0106] Figure 8 is a graph showing a deviation in inspection size between a contamination size inspected by performing brightness correction according to the present invention and an inspection result through a microscope.
[0107] More specifically, Figure 8 The difference between the measurement inspection result using a microscope and the size of contamination inspected by performing brightness correction on images of a plurality of contaminations (contamination 1 to contamination 25) randomly arranged and placed to conduct an experiment according to an embodiment of the present invention is shown.
[0108] Figure 8 The example in shows the case where brightness correction using gray scale is used among the brightness correction techniques. The three graphs show the deviation of the contamination size compared with the contamination size measured by a microscope when the target brightness of the brightness correction is set to 128, 64, and 192, respectively. Figure 8 Also shown as a comparative example is the deviation in soil size when brightness correction is not used (grayscale correction is off). Figure 8 From the graph in FIG. 1 , it can be understood that when brightness correction is used, that is, when grayscale correction is used (grayscale correction is turned on), the deviation level of the size of the detected contamination is reduced. In addition, as a result of experiments conducted by setting the target brightness to various values, it can be understood that the brightness value of 64 to 192 is an appropriate range for use.
[0109] Fig. 9 is a perspective view of an imaging device according to an embodiment of the present invention, and Fig.10 is a cross-sectional view of an imaging device according to an embodiment of the present invention.
[0110] Reference Fig. 9 and Fig.10 According to an embodiment of the present invention, the imaging device 200 may include a housing 210, a first lighting unit 220, a first reflector 231, a second reflector 232 and at least one of a camera 240, a third reflector 250, a second lighting unit 260, a transmission device 270 and an inversion device 280.
[0111] exist Fig. 9 In the example of FIG. 1 , the housing 210 is disposed on one side of the battery 10 and surrounds at least the first area A1 of the battery 10. Fig. 9As shown, the battery 10 may be placed in a flat position with its side facing upward, and the case 210 may be placed above the battery 10. The shape of the case 210 is not limited to a specific shape, but the inner surface of the case 210 may have a dome shape.
[0112] The first lighting part 220 is disposed on the inner surface of the housing 210 and radiates light to the battery 10. Fig.10 , the first lighting portion 220 is shown as protruding and disposed on the inner surface of the housing 210. However, the first lighting portion 220 may be embedded in the inner surface of the housing 210 and arranged so that at least a portion of the first lighting portion is exposed. Specifically, the first lighting portion 220 may radiate light to the lateral side of the battery 10. The first lighting portion 220 may radiate light to the entire first area A1 of the battery 10. As described above, the inner surface of the housing 210 may have a dome shape, and the first lighting portion 220 disposed on the inner surface of the housing 210 may be arranged in an overall circular shape to emit light to the lateral side of the battery 10.
[0113] The first reflector 231 and the second reflector 232 may be disposed on both sides of the battery 10 to respectively reflect a portion of the first area A1 of the battery 10. Fig.10 , the first reflector 231 may be disposed on the left side of the battery 10 , and the second reflector 232 may be disposed on the right side of the battery 10 at a certain angle.
[0114] In addition, the camera 240 photographs at least a portion of the first area A1 of the battery 10, an image reflected on the first reflector 231, and an image reflected on the second reflector 232. In other words, the camera 240 photographs at least a portion of the first area A1 of the battery 10. Here, the portion of the first area A1 reflected in the first reflector 231 or the second reflector 232 includes all areas in the first area A1 that cannot be photographed by the camera 240 if either of the first reflector 231 and the second reflector 232 is not provided. Therefore, due to the presence of the first reflector 231 and the second reflector 232, the image captured by the camera 240 may include an image of the entire first area A1 of the battery 10. In this way, the imaging device 200 according to the present invention can perform a side inspection of the battery by obtaining an appearance image of the entire area of the first area A1 of more than half of the lateral side of the battery 10 at one time without rotating or rolling the battery 10.
[0115] In addition, if the camera 240 is not properly disposed to face the side 200S of the battery 10 and is sufficient to directly photograph at least a portion of the first area A1 of the battery 10, the image reflected by the first reflector 231, and the image reflected by the second reflector 232, the imaging device 200 may further include a third reflector 250. Here, the camera 240 may indirectly capture at least a portion of the first area A1, the image reflected in the first reflector 231, and the image reflected in the second reflector 232 by photographing the image reflected in the third reflector 250. In other words, the camera 240 may capture at least a portion of the first area A1 of the battery 10 reflected in the third reflector 250, the image reflected in the first reflector 231, and the image reflected in the second reflector 232.
[0116] The third reflector 250 may be disposed at an angle on the side 200S of the battery 10 so as to reflect at least a portion of the first area A1 of the battery 10, an image reflected by the first reflector 231, and an image reflected by the second reflector 232. Referring to the drawings, the third reflector 250 may be tilted and disposed to face between the Y direction (Y) and the Z direction (Z). The third reflector 250 may be arranged so that at least a portion of the first area A1 of the battery 10, an image reflected on the first reflector 231, and an image reflected on the second reflector 232 are incident and reflected at an angle of about 45°. Here, the camera 240 may be placed to face the light reflected in the third reflector 250.
[0117] Furthermore, the imaging device 200 may further include a second lighting section 260 in addition to the first lighting section 220. The second lighting section 260 may be disposed on the third reflector 250 and radiate light to the battery 10, and may be coaxial lighting.
[0118] In addition, the transfer device 270 may transfer the battery 10 in the axial direction (X) of the battery 10 so that the battery 10 passes through the housing 210. The battery 10 may be transferred by the transfer device 270, arrive at the inspection area in the housing 210, stop for a period of time, and may be photographed by the camera 240 so that a side inspection of the battery 10 may be performed. The battery 10 that has been inspected may be transferred to a subsequent process by the transfer device 270.
[0119] In addition, the reversing device 280 can flip the battery 10 that has been photographed by the camera 240. In other words, the reversing device 280 can rearrange the battery 10 to a 180° rotated state. Referring to the drawings, the reversing device 280 can flip the battery 10 upside down along the Z direction (Z). Therefore, the side inspection can be performed on the opposite side of the battery 10 where the side inspection has not been performed using the same device as the above-mentioned imaging device 200. Since the first area A1 to be inspected is more than half of the side 200S of the battery 10, some inspection areas may overlap during the first side inspection and the second side inspection.
[0120] Here, a separate imaging device 200 may be used to perform a side inspection of the opposite side of the battery 10 where the side inspection is not performed to ensure smooth progress of the process. In other words, the imaging device 200 may include a pair of imaging devices 200 for respectively inspecting both sides of the battery 10. However, in order to reduce costs, a single imaging device 200 may be used to perform a side inspection of both sides of the battery 10.
[0121] Furthermore, when inspecting the side appearance of a cylindrical battery, an image is usually obtained by rotating or rolling the battery 360°. When the battery is rotated or rolled, noise appears in the image, which reduces the image quality and the inspection capability of the inspection device. In addition, due to shadows caused by the curved surface, the farther away from the shooting center, the more difficult it is to ensure the visibility of defects.
[0122] The imaging device 200 according to the embodiment of the present invention includes a first reflector 231 and a second reflector 232, thereby obtaining the entire image of the first area A1, which is more than half of the side 200S of the battery 10, by one shot. In other words, the entire surface of the side of the battery 10 can be inspected by performing two inspections on one side and the other side of the battery 10. In addition, even in an area far from the center of the first area A1 for inspection, sufficient visibility of defects can be ensured. Thus, an imaging device capable of inspecting the side appearance of a cylindrical battery without rotating or rolling the cylindrical battery can be provided. In addition, an imaging device capable of preventing image noise and improving image quality and the inspection capability of the inspection device can be provided.
[0123] In addition, according to the reference Fig. 9 and Fig.10 The imaging device of the described embodiment has a structure suitable for inspecting the lateral side of a battery, and is shown as an example of the imaging device according to the embodiment of the present invention.
[0124] Fig.11a is a diagram showing the appearance of an imaging device according to another embodiment of the present invention, and Fig.11b is a diagram showing a multi-channel illumination configuration of an imaging device according to another embodiment of the present invention.
[0125] Fig.11a The imaging device shown has a structure suitable for obtaining images of the upper and lower surfaces of the battery (such as rivets and vents of the battery cell), and uses Fig.11b The multi-lighting device shown. Fig.11b The imaging device according to the present invention may include a structure for capturing images of various parts of a battery cell, such as the top and bottom surfaces of a battery and the side surfaces of a battery.
[0126] Fig.12 is a block diagram of a visual inspection apparatus according to an embodiment of the present invention.
[0127] The visual inspection apparatus 1000 according to the embodiment of the present invention may include at least one processor 1010 , a memory 1020 storing at least one command executed by the processor, and a transceiver device 1030 connected to a network and performing communication.
[0128] Here, at least one instruction may include: instructions for obtaining and preprocessing an appearance image of a target object; instructions for extracting a region of interest from the preprocessed image and performing brightness correction on the extracted region of interest; instructions for extracting defect candidates from the brightness corrected image; instructions for performing image post-processing on the extracted defect candidates; and instructions for determining whether the target object is defective from the post-processed image.
[0129] The appearance inspection device according to an embodiment of the present invention may be combined with an imaging device that captures the appearance of the target object, or the appearance inspection device may include the imaging device. Fig. 9 , Fig.10 , Fig.11a and Fig.11b The devices shown in are provided in the same or similar form.
[0130] Instructions for performing brightness correction on the extracted region of interest may include: instructions for calculating the average brightness of pixels within the extracted region of interest; instructions for calculating a correction gain value based on the calculated average brightness and a target brightness; and instructions for correcting the brightness of each pixel according to the correction gain value.
[0131] The instructions for calculating the correction gain value based on the calculated average brightness and the target brightness may include instructions for calculating the correction gain value by dividing the target brightness by the average brightness.
[0132] The instructions for correcting the brightness of each pixel according to the correction gain value may include instructions for multiplying the original brightness of each pixel by the correction gain value to correct the brightness of each pixel. The instructions for calculating the average brightness of the pixels within the extracted region of interest may include instructions for calculating the average brightness based on the number of pixels in the region of interest and the brightness of each pixel.
[0133] The target brightness can be determined by the user.
[0134] Furthermore, the instructions for performing brightness correction on the extracted region of interest may include instructions for changing the captured color image to a grayscale image before applying the brightness correction to the captured color image.
[0135] The instructions for performing brightness correction on the extracted region of interest may include instructions for separating the captured color image into an R channel, a G channel, and a B channel before applying the brightness correction to the captured color image.
[0136] Therefore, an instruction for calculating the average brightness of pixels, an instruction for calculating the correction gain value, and an instruction for correcting the brightness of each pixel may be executed for each of the R channel, the G channel, and the B channel.
[0137] The appearance inspection apparatus 1000 may further include an input interface device 1040 , an output interface device 1050 , a storage device 1060 , etc. The various components included in the appearance inspection apparatus 1000 may be connected through a bus 1070 and may communicate with each other.
[0138] The storage device 1060 may store at least one image generated in each step of the inspection method according to the present invention, such as a plurality of images captured by an imaging device, pre-processed images, and post-processed images. The images stored in the storage device 1060 may be provided to the at least one processor 1010 when necessary during the execution of the inspection method according to the present invention.
[0139] Here, the processor 1010 may represent a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor that executes a method according to an embodiment of the present invention. The memory (or storage device) may include at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory may include at least one of a read-only memory (ROM) and a random access memory (RAM).
[0140] The operation of the method according to an embodiment of the present invention can be implemented as a computer-readable program or code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices having data readable by a computer system stored therein. In addition, the computer-readable recording medium can be distributed in a network-connected computer system to store and execute a computer-readable program or code in a distributed manner.
[0141] Although some aspects of the present invention have been described in the context of equipment, it can also be represented according to the description of the corresponding method, wherein a block or device corresponds to a method step or a feature of a method step. Similarly, the various aspects described in the context of the method can also represent the features of the corresponding block or project or corresponding equipment. Some or all of the method steps can be performed by (or using) for example a hardware device (such as a microprocessor, a programmable computer or an electronic circuit). In some embodiments, one or more of the most important method steps can be performed by such equipment.
[0142] In the foregoing, the present invention has been described with reference to exemplary embodiments thereof, but those skilled in the art will appreciate that various corrections and changes may be made to the present invention within the scope without departing from the spirit and scope of the invention described in the appended claims.
Claims
1. A method for inspecting the appearance of a product, the method comprising: The following steps are involved: Acquire and preprocess the appearance image of the target object; extracting a region of interest from the preprocessed image and performing brightness correction on the extracted region of interest; Extracting defect candidates from the brightness-corrected image; performing image post-processing on the extracted defect candidates; as well as It is determined from the post-processed image whether the target object has defects.
2. The appearance inspection method according to claim 1, in, The step of performing brightness correction on the extracted region of interest comprises the following steps: Calculating the average brightness of pixels within the extracted region of interest; calculating a correction gain value based on the calculated average brightness and the target brightness; and The brightness of each pixel is corrected according to the correction gain value.
3. The appearance inspection method according to claim 2, in, The step of calculating the correction gain value based on the calculated average brightness and the target brightness comprises the following steps: The correction gain value is calculated by dividing the target brightness by the average brightness.
4. The appearance inspection method according to claim 2, in, The step of correcting the brightness of each pixel according to the correction gain value comprises the following steps: The original brightness of each pixel is multiplied by the correction gain value to correct the brightness of each pixel.
5. The appearance inspection method according to claim 2, in, The target brightness is determined by the user.
6. The appearance inspection method according to claim 2, in, The step of calculating the average brightness of the pixels within the extracted region of interest comprises the following steps: The average brightness is calculated based on the number of pixels in the region of interest and the brightness of each pixel.
7. The appearance inspection method according to claim 2, in, The step of performing brightness correction on the extracted region of interest comprises the following steps: Before applying brightness correction to the captured color image, the captured color image is changed to a grayscale image.
8. The appearance inspection method according to claim 2, in, The step of performing brightness correction on the extracted region of interest comprises the following steps: Before applying brightness correction to the captured color image, the color image is separated into an R channel, a G channel, and a B channel.
9. The appearance inspection method according to claim 8, in, The step of calculating the average brightness of the pixels, the step of calculating the correction gain value, and the step of correcting the brightness of each pixel are performed on each of the R channel, the G channel, and the B channel.
10. A product appearance inspection device, the appearance inspection device include: at least one processor; as well as a memory configured to store at least one instruction executed by the at least one processor, The at least one instruction includes: Instructions for acquiring and preprocessing an appearance image of a target object; instructions for extracting a region of interest from the preprocessed image and performing brightness correction on the extracted region of interest; Instructions for extracting defect candidates from a brightness-corrected image; instructions for performing image post-processing on the extracted defect candidates; and Instructions for determining whether the target object is defective from the post-processed image.
11. The appearance inspection device according to claim 10, in, The appearance inspection device cooperates with an imaging device that captures the appearance of the target object, or Wherein, the appearance inspection equipment includes the imaging device.
12. The appearance inspection device according to claim 10, in, The instructions for performing brightness correction on the extracted region of interest include: Instructions for calculating the average brightness of pixels within the extracted region of interest; instructions for calculating a correction gain value based on the calculated average brightness and the target brightness; and Instructions for correcting the brightness of each pixel according to the correction gain value.
13. The appearance inspection device according to claim 12, in, The instructions for calculating the correction gain value based on the calculated average brightness and the target brightness include: Instructions for calculating the correction gain value by dividing the target brightness by the average brightness.
14. The appearance inspection device according to claim 12, in, The instructions for correcting the brightness of each pixel according to the correction gain value include: Instructions for multiplying the original brightness of each pixel by the correction gain value to correct the brightness of each pixel.
15. The appearance inspection device according to claim 12, in, The target brightness is determined by the user.
16. The visual inspection device according to claim 12, in, The instructions for calculating the average brightness of pixels within the extracted region of interest include: Instructions for calculating the average brightness based on the number of pixels in the region of interest and the brightness of each pixel.
17. The visual inspection device according to claim 12, in, The instructions for performing brightness correction on the extracted region of interest include: Instructions for changing a captured color image to a grayscale image before applying brightness correction to the captured color image.
18. The appearance inspection device according to claim 12, in, The instructions for performing brightness correction on the extracted region of interest include: Instructions for separating a captured color image into an R channel, a G channel, and a B channel before applying brightness correction to the captured color image.
19. The appearance inspection device according to claim 18, in, An instruction for calculating the average brightness of the pixels, an instruction for calculating the correction gain value, and an instruction for correcting the brightness of each pixel are executed for each of the R channel, the G channel, and the B channel.
