Apparatus and method for inspecting appearance of product

Abstract

A method for inspecting the appearance of a product according to one embodiment of the present invention may include the steps of acquiring and preprocessing an image capturing the appearance of a target object; extracting an area to be inspected within the preprocessed image and performing brightness correction on the extracted area to be inspected; extracting a group of defect candidates from the brightness-corrected image; performing image post-processing on the extracted group of defect candidates; and determining whether or not the target object is defective from the post-processed image.

Description

[Technical field]

[0001] This application claims the benefit of the filing dates of Korean Patent Application No. 10-2022-0117571 filed with the Korean Intellectual Property Office on September 19, 2022, and Korean Patent Application No. 10-2023-0099316 filed with the Korean Intellectual Property Office on July 31, 2023, and all of the contents disclosed in the documents of said Korean patent applications 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 that processes an inspection image by adjusting the brightness of an area to be inspected within the image. [Background technology]

[0003] Secondary batteries are batteries that can be reused by charging after discharge and can be used as energy sources for small devices such as mobile phones, tablet PCs, and vacuum cleaners, as well as medium- to large-scale energy sources for personal mobility, automobiles, and smart grid ESS (Energy Storage Systems). Depending on the requirements of the system, secondary batteries are used in the form of assemblies such as battery modules in which multiple battery cells are connected in series and parallel, or battery packs in which battery modules are connected in series and parallel.

[0004] Batteries can be manufactured through processes that include an electrode process, an assembly process, a formation process, and other processes, and the manufactured battery cells or the results of each process are inspected for defects using inspection equipment. Visual inspection is a commonly used technique for inspecting defects, and visual inspection can be performed by acquiring an image of a product using an optical system and detecting defects using a detection algorithm.

[0005] However, after a specific detection algorithm is determined, the brightness of the captured image may differ from the brightness of the image originally expected due to factors such as changes in the surface color of the product or changes in lighting due to the end of the lighting's lifespan, and in this case, problems may arise in the detection power of the existing algorithm. Summary of the Invention [Problem to be solved by the invention]

[0006] In order to solve the above problems, an object of the present invention is to provide a product appearance inspection method that processes an inspection image by adjusting the brightness of an inspection target area in an image to a set value.

[0007] Another object of the present invention to solve the above problems is to provide an appearance inspection apparatus using the above-mentioned product appearance inspection method. [Means for solving the problem]

[0008] To achieve the above-mentioned object, one embodiment of the present invention provides a method for inspecting the appearance of a product, comprising the steps of acquiring and preprocessing an image capturing the appearance of a target object; extracting an area to be inspected within the preprocessed image and performing brightness correction on the extracted area to be inspected; extracting a group of defect candidates from the brightness-corrected image; performing image post-processing on the extracted group of defect candidates; and determining whether or not the target object is defective from the post-processed image.

[0009] The step of performing brightness correction on the extracted inspection area may include the steps of: calculating an average brightness of pixels in the extracted inspection area; calculating a correction gain value based on the calculated average brightness and a target brightness; and correcting the brightness of each pixel using the correction gain value.

[0010] Calculating a correction gain value based on the calculated average brightness and the target brightness may include calculating a correction gain value by dividing the target brightness by the average brightness.

[0011] The step of correcting the brightness of each pixel by the correction gain value may include the step of correcting the brightness of each pixel by multiplying the original brightness of each pixel by the correction gain value.

[0012] Also, the step of calculating an average brightness of pixels in the extracted examination area may include a step of calculating the average brightness based on the number of pixels in the examination area and the brightness of each pixel.

[0013] Here, the target brightness can be set by the user.

[0014] On the other hand, the step of performing brightness correction on the extracted inspection target region may include the step of converting the captured color image into a black and white image before applying the brightness correction to the color image.

[0015] The step of performing brightness correction on the extracted region of interest may also include separating the captured color image into R, G, and B channels before applying the brightness correction to the captured color image.

[0016] Therefore, in this case, the steps of calculating the average brightness, calculating the correction gain value, and correcting the brightness for each pixel may be performed for each of the R channel, G channel, and B channel.

[0017] In order to achieve the above-mentioned another object, an apparatus for inspecting the appearance of a product according to one embodiment of the present invention may include at least one processor; a memory for storing at least one instruction executed through the at least one processor; and the at least one instruction may include instructions for obtaining and pre-processing an image capturing an appearance of a target object; instructions for extracting an inspection target area within the pre-processed image and performing brightness correction on the extracted inspection target area; instructions for extracting a group of defect candidates from the brightness-corrected image; instructions for performing image post-processing on the extracted group of defect candidates; and instructions for determining whether or not the target object is defective from the post-processed image.

[0018] The appearance inspection apparatus according to an embodiment of the present invention may be linked to an imaging device for capturing an image of the appearance of a target object or may include such an imaging device (not shown).

[0019] The instruction to perform brightness correction on the extracted inspection area may include an instruction to calculate an average brightness of pixels in the extracted inspection area; an instruction to calculate a correction gain value based on the calculated average brightness and a target brightness; and an instruction to correct brightness for each pixel using the correction gain value.

[0020] The instructions to calculate the correction gain value may include instructions to calculate the correction gain value by dividing the target brightness by the average brightness.

[0021] The instruction to correct the brightness of each pixel by the correction gain value may include an instruction to correct the brightness of each pixel by multiplying an original brightness of each pixel by the correction gain value. The instruction to calculate an average brightness of pixels in the extracted inspection area may include an instruction to calculate the average brightness based on the number of pixels in the inspection area and the brightness of each pixel.

[0022] At this time, the target brightness can be set by the user.

[0023] On the other hand, the instruction to perform brightness correction on the extracted inspection area may include an instruction to change the captured color image to a black and white image before applying the brightness correction to the color image.

[0024] The instructions for performing brightness correction on the extracted inspection area may include instructions for separating the captured color image into R, G, and B channels before applying the brightness correction to the color image.

[0025] Thereby, the command to calculate the average brightness, the command to calculate the correction gain value, and the command to correct the brightness for each pixel may be performed for each of the R channel, G channel, and B channel. Effect of the Invention

[0026] According to the above-described embodiment of the present invention, an image with uniform brightness can be obtained even if the illumination conditions of the optical system change, in that the average brightness for the inspection area is calculated and corrected to a specified brightness.

[0027] Therefore, the accuracy of inspection for determining whether a product is defective can be improved. [Brief description of the drawings]

[0028] [Figure 1] FIG. 1 is a flow diagram of a general appearance inspection method. [Diagram 2] FIG. 2 is a flow diagram of a visual inspection method according to an embodiment of the present invention. [Diagram 3] 5A to 5C are diagrams illustrating a detailed process of brightness correction according to an embodiment of the present invention. [Figure 4]11A and 11B are diagrams illustrating a comparison between an image resulting from brightness correction performed according to an embodiment of the present invention and an original image. [Diagram 5] 13 is an example of a user interface screen provided for visual inspection according to an embodiment of the present invention. [Figure 6a] 11 is a graph comparing the results of an appearance inspection using an image that has been subjected to brightness correction according to an embodiment of the present invention and an image that has not been subjected to brightness correction. [Figure 6b] 11 is a graph comparing the results of an appearance inspection using an image that has been subjected to brightness correction according to an embodiment of the present invention and an image that has not been subjected to brightness correction. [Figure 6c] 11 is a graph comparing the results of an appearance inspection using an image that has been subjected to brightness correction according to an embodiment of the present invention and an image that has not been subjected to brightness correction. [Figure 7] 4 shows images measured and processed at different illumination intensities and different correction target brightnesses according to an embodiment of the present invention. [Figure 8] 11 is a graph showing a variation in detected size between a contamination size detected by performing brightness correction according to the present invention and an inspection result through a microscope; [Figure 9] 1 is a perspective view of an imaging device according to an embodiment of the present invention. [Figure 10] 1 is a cross-sectional view of an imaging device according to an embodiment of the present invention. [Figure 11a] FIG. 13 is a diagram showing the appearance of an imaging device according to another embodiment of the present invention. [Figure 11b] FIG. 13 is a diagram showing a multi-channel illumination configuration of an imaging device according to another embodiment of the present invention. [Figure 12] 1 is a block diagram of a visual inspection apparatus according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0029] Since the present invention can be modified in various ways and has various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, it is understood that this is not intended to limit the present invention to the specific embodiment, but includes all modifications, equivalents, and alternatives within the spirit and technical scope of the present invention. Similar reference numerals are used for similar components while describing each drawing.

[0030] Terms such as first, second, A, B, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only to distinguish one component from another. For example, a first component may be named a second component, and similarly, a second component may be named a first component, without departing from the scope of the present invention. The term "and / or" includes a combination of multiple associated listed items or any of multiple associated listed items.

[0031] When a component is referred to as being "coupled" or "connected" to another component, it should be understood that the component may be directly coupled or connected to the other component, but there may also be other components in between. In contrast, when a component is referred to as being "directly coupled" or "directly connected" to another component, it should be understood that there are no other components in between.

[0032] The terms used in this application are merely used to describe certain embodiments and are not intended to limit the present invention. A singular expression includes a plural expression unless the context clearly indicates otherwise. In this application, the terms "include" or "have" are intended to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and are not intended to preclude the presence or additional possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0033] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention belongs. Terms as defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning they have in the context of the relevant art, and should not be interpreted as having an ideal or overly formal meaning unless expressly defined in this application.

[0034] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0035] FIG. 1 is a flow diagram of a typical appearance inspection method.

[0036] A typical appearance inspection method for a part or product can broadly include image pre-processing (S11), defect candidate group extraction (S12), image post-processing (S13), and defect determination process.

[0037] The part / product to be inspected can be captured as image data through an imaging device, i.e., an optical system, and one image can include one or more objects relating to multiple parts / products.

[0038] The image pre-processing process (S11) is a process of emphasizing features of the image of the target object before inspection in order to make it easier to inspect, and methods such as binarization, normalization, etc. may be used. The image pre-processing process may further include a process of generally amplifying the brightness of the image of the target object.

[0039] In the defect candidate group extraction process (S12), a group of candidates suspected to be defective is extracted from among a plurality of objects contained in the detected image, and objects that appear in the image and have potential defect characteristics can be selected as candidates.

[0040] In the image post-processing process (S13), feature values ​​of the group of defect candidates are extracted. The feature values ​​may be values ​​related to the intensity, shape, texture, etc. of the objects contained in the image.

[0041] In the defect determination process (S14), the extracted feature values ​​are analyzed to determine whether a defect or failure has occurred in the product / part related to the object.

[0042] In the above-mentioned general appearance inspection method, the brightness correction included in the image pre-processing step is performed by arbitrarily amplifying the overall brightness of the image. According to this method, the brightness of the image may not be uniformly corrected to a desired brightness, so the brightness correction value must be adjusted differently for each image.

[0043] As a result, when the brightness is changed due to the end of the life of the lighting or when variations occur in the hue of some of the raw materials for the cells, the conventional method has the problem that the test results change and good test results cannot be obtained.

[0044] FIG. 2 is a flow diagram of the appearance inspection method according to the embodiment of the present invention.

[0045] The product appearance inspection method according to an embodiment of the present invention can broadly include image pre-processing (S100), brightness correction (S200), defect candidate group extraction (S300), image post-processing (S400), and defect presence / absence determination (S500).

[0046] An image of the part / product being inspected can be acquired through an imaging device, i.e., an optical system, and one image can contain one or more objects relating to multiple parts / products.

[0047] The image pre-processing process (S100) is a process of enhancing features of an image of a target object before inspection in order to make it easier to inspect the image, and is a process of converting an image acquired through an imaging device so that defects can be easily identified through a process of correcting or synthesizing the image. The pre-processing process may use methods such as image synthesis, binarization, normalization, blurring, stretching, etc.

[0048] Here, the image synthesis can be effectively used to express depth in an image using a multi-channel image described later, and can be particularly useful for detecting defects such as dents, scratches, etc. As an image synthesis method, photometric stereo synthesis, phase shift synthesis, etc. can be particularly used.

[0049] In addition, binarization is a process of resetting pixel values ​​of objects and backgrounds in an image to only two values, 1 and 0, and image correction through binarization can make defects in the product's appearance more visible. In addition, normalization is a process of distributing pixel values ​​concentrated in a specific part of an image evenly throughout the entire area. Blur processing, also called smoothing, can be used to soften rough-looking images or as a pre-processing process to remove the effects of noise in images. Stretching can also be used as a pre-processing method to complement distorted images.

[0050] According to the present invention, a brightness correction process (S200) can be applied to the pre-processed image, and the brightness correction process (S200) can be executed according to the needs of the user. That is, referring to FIG. 2, when the brightness correction process is set to ON (Yes in S120), the brightness correction process (S200) can be executed. In the brightness correction process (S200), the average brightness for the inspection target area is calculated, and the inspection target area can be corrected to a specified brightness. Here, the inspection target area (ROI: Region of Interest) indicates the area to be actually inspected in the inspection image.

[0051] Meanwhile, the process of performing brightness correction on a color image according to the present invention can be embodied in two forms.

[0052] The first method is to change a color image to a black and white image, that is, to change a color image to a gray image and correct the brightness by setting a target intensity.

[0053] The second method is to correct the brightness by setting a target brightness for each RGB channel in the color image. That is, the brightness can be corrected by setting a target brightness separately for the R (Red) channel, G (Green) channel, and B (Blue) channel of the color image. In this case, the calculation of the average brightness, the calculation of the gain value, and the calculation of the corrected brightness value of each pixel can be performed separately for each channel.

[0054] In the defect candidate group extraction process (S300), a group of candidates suspected to be defective is extracted from among a number of objects contained in the detected image, and objects that appear in the image and have potential defect characteristics can be selected as candidates.

[0055] In the defect candidate group extraction process (S300), the defect candidate group is extracted using the brightness difference in the brightness-corrected inspection target region (ROI). For example, the defect candidate group can be extracted by determining whether each pixel in the ROI expressed in grayscale is equal to or greater than a certain threshold and distinguishing whether there is a shaded region.

[0056] Here, as examples of the threshold technique, various techniques such as Adaptive, Dynamic, Polar, and Local may be used.

[0057] The image post-processing process (S400) is a process of extracting feature values ​​of the defective candidate group, and quantitatively calculating representative features such as brightness, shape, and size of the extracted defective candidate group. That is, the feature values ​​of the defective candidate group may be values ​​related to the brightness, shape, texture, etc. of objects included in the image.

[0058] More specifically, the feature value for the defect candidate group may include the area, width, height, circularity, rectangularity, struct factor, etc. of the shape. Mainly, the length or size of the defect may be determined by determining the size of the defect candidate group as the outer diameter of the maximum circumscribed circle or by using the width of the defect. Generally, foreign matter or contamination has a characteristic of being darker than the surrounding area, so that such a characteristic is used to extract the corresponding area, and it is possible to finally determine whether or not it is a defect using the size and width of the dark area. For example, since scratches and scuffs have a linear shape, they can be distinguished from foreign matter such as a thread using a linearity factor that quantifies linear features.

[0059] In the subsequent defect determination process (S500), the extracted feature values ​​are analyzed and it is determined whether a defect or failure has occurred in the product / part related to the corresponding object based on a preset detection criterion.

[0060] FIG. 3 is a diagram showing a detailed process of brightness correction according to an embodiment of the present invention.

[0061] A region of interest (ROI) is extracted from the captured image, and an average brightness of pixels in the extracted region of interest is calculated (S210). The average brightness of pixels in the region of interest can be calculated by the following Equation 1:

[0062]

number

[0063] In formula 1, I avg is the average brightness of the pixels in the region of interest, I i is the brightness of the i-th pixel, n ROI indicates the number of pixels in the ROI.

[0064] Once the average brightness of the inspection target area is calculated, a correction gain value is calculated in consideration of the target brightness (S220). The correction gain value can be calculated by the following Equation 2. Here, the target brightness I target can be predefined by the user.

[0065]

number

[0066] In Equation 2, φ represents the brightness correction gain (Gain), and I target indicates a correction target brightness, which can be predefined by the user or can be changed through the user interface.

[0067] Image brightness correction can then be performed by multiplying each pixel's original brightness value by the correction gain value to obtain a corrected brightness value for each pixel (S230).

[0068] Meanwhile, when correcting the brightness by setting a correction target brightness for each RGB channel in a color image, the above-mentioned average brightness calculation procedure, gain value calculation procedure, and corrected brightness value calculation procedure for each pixel may be performed separately for each channel (R (Red) channel, G (Green) channel, B (Blue) channel).

[0069] FIG. 4 is a diagram showing a comparison between an image resulting from brightness correction according to an embodiment of the present invention and an original image.

[0070] The subject of the visual inspection according to the present invention may be a cylindrical, pouch, or prismatic battery, particularly a cylindrical battery of various specifications. As an example, a cylindrical battery may include an electrode assembly, a battery can, a plate-shaped cap, and a terminal. The cylindrical battery may further include an insulating gasket, a current collector, an insulator, a sealing gasket, and the like.

[0071] The image shown in Figure 4 was acquired by photographing a cylindrical battery test piece on which circular patterns of various sizes were printed to create a contamination effect.

[0072] In Fig. 4, the three images on the left side show images captured when the brightness correction according to the present invention is not used (i.e., brightness correction mode OFF) and at different lighting brightnesses, i.e., strobe time 200μS, strobe time 400μS, and strobe time 600μS. The three images on the right side show images captured when the brightness correction according to the present invention is used (i.e., brightness correction mode ON) and at different lighting brightnesses. Here, strobe time is a unit indicating the time the light is turned on, and the larger the value, the longer the time the light is turned on.

[0073] In the three images on the left, which do not use the brightness correction mode, the strobe time value is proportional to the brightness of the captured image. That is, since the three images on the left do not use the brightness correction mode, there is a clear difference in brightness between the three images. In contrast, in the three images on the right, which have been subjected to brightness correction according to the present invention, the difference in brightness is so minute that it cannot be seen by the naked eye.

[0074] FIG. 5 is an example of a user interface screen provided for visual inspection according to an embodiment of the present invention.

[0075] The visual inspection apparatus according to the present invention may provide a user interface for setting inspection-related details, which may include an object to be inspected, whether or not brightness correction is performed, and a brightness correction strength.

[0076] The appearance inspection displayed on the user interface screen of FIG. 5 is a contamination inspection of a battery can, and the user can directly set items such as whether or not to correct brightness and a target intensity (gray correction target intensity).

[0077] 6a to 6c are graphs comparing the results of appearance inspection using an image that has been subjected to brightness correction according to an embodiment of the present invention and an image that has not been subjected to brightness correction.

[0078] FIG. 6a shows the inspection results for the upper plane of the battery, FIG. 6b shows the inspection results for the upper plane of the battery, and FIG. 6c shows the inspection results for the side of the battery.

[0079] Through experiments, it was confirmed that the measurement error (unit: mm) improved in all three cases when automatic brightness correction was performed (green graph) compared to when it was not performed (red graph), with an average improvement of 60%.

[0080] FIG. 7 shows images measured and processed at different illumination intensities and different correction target brightnesses according to an embodiment of the present invention.

[0081] More specifically, FIG. 7 shows images of a number of contaminants of various sizes that were randomly arranged on the top surface of a cylindrical battery for the experiment, and shows resultant images when three illumination intensities (strobe time 200 μS, strobe time 400 μS, strobe time 600 μS) and different correction target brightnesses (correction mode OFF, correction targets 64, 128, 192) were applied.

[0082] In the case of an image not using the brightness correction mode, the brightness of the captured image is proportional to the strobe time value. In the case of using the brightness correction according to the present invention, it can be seen that the image brightness after correction is adjusted to within a certain range.

[0083] FIG. 8 is a graph showing the variation in detected size between the contamination size detected by performing brightness correction according to the present invention and the result of inspection through a microscope.

[0084] More specifically, FIG. 8 is a graph showing the variation in detected contamination size between the results of inspection through a microscope and the contamination size detected by performing brightness correction according to the present invention on images of a number of contaminations (contaminations 1 to 25) that were arbitrarily set and arranged for the experiment.

[0085] The example of FIG. 8 shows a case where brightness correction using grayscale is used among the brightness correction techniques. Three graphs are shown showing the variation in contamination size when the target brightness of brightness correction is set to 128, 64, and 192, respectively, for the contamination size measured through a microscope. FIG. 8 also shows the variation in contamination size when brightness correction is not used (Gray Correction OFF) as a comparative example. Comparing the graphs of FIG. 8, it can be seen that the level of variation in the detected contamination size is reduced when brightness correction is used, i.e., when gray correction is used (Gray Correction ON). Also, as a result of conducting experiments with the target brightness set to various values, it was confirmed that the appropriate range of use is 64 to 192.

[0086] 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 the imaging device according to an embodiment of the present invention.

[0087] 9 and 10, an imaging device 200 according to one embodiment of the present invention may include at least one of a housing 210, a first light 220, a first mirror 231, a second mirror 232, a camera 240, a third mirror 250, a second light 260, a transport means 270, and an inversion means 280.

[0088] 9, the housing 210 is disposed on the side of the battery 10 and surrounds at least the first region (A1) of the battery 10. For example, as shown in FIG 9, the battery 10 may be disposed in a lying form with the side facing upward, and the housing 210 may be disposed on the upper part of the battery 10. The shape of the housing 210 is not particularly limited, but the inner surface of the housing 210 may have a dome shape.

[0089] The first illuminator 220 is disposed on the inner surface of the housing 210 and irradiates light to the battery 10. In FIG. 10, the first illuminator 220 is shown to be disposed protruding from the inner surface of the housing 210, but the first illuminator 220 may be disposed so as to be embedded in the inner surface of the housing 210 and at least a part of the first illuminator 220 is exposed. Specifically, the first illuminator 220 irradiates light to the side of the battery 10. The first illuminator 220 can irradiate light to the entire area of ​​the first region (A1) of the battery 10. As described above, the inner surface of the housing 210 can have a dome shape, and the first illuminator 220 disposed on the inner surface of the housing 210 can be disposed in an overall ring shape to irradiate light to the side of the battery 10.

[0090] The first mirror 231 and the second mirror 232 may be disposed on both sides of the battery 10 so as to respectively reflect a part of the first area (A1) of the battery 10. Referring to Fig. 10, the first mirror 231 may be disposed on the left side of the battery 10, and the second mirror 232 may be disposed at an angle on the right side of the battery 10.

[0091] Meanwhile, the camera 240 captures at least a part of the first area (A1) of the battery 10, an image reflected on the first mirror 231, and an image reflected on the second mirror 232. That is, the camera 240 captures at least a part of the first area (A1) of the battery 10. At this time, the part of the first area (A1) reflected on the first mirror 231 or the second mirror 232 includes any area that cannot be captured by the camera 240 if the first mirror 231 or the second mirror 232 does not exist in the first area (A1). Therefore, due to the presence of the first mirror 231 and the second mirror 232, the image captured by the camera 240 can include an image of the entire area of ​​the first area (A1) of the battery 10. Through this, the imaging device 200 according to the present invention can obtain an external image of the entire area of ​​the first area (A1), which is more than half of the side of the battery 10, at once, and perform side inspection without rotating or rolling the battery 10.

[0092] On the other hand, when the camera 240 is not disposed facing the side surface (200S) of the battery 10 so as to directly capture at least a part of the first region (A1) of the battery 10, the image reflected in the first mirror 231, and the image reflected in the second mirror 232, the imaging device 200 may further include a third mirror 250. In this case, the camera 240 captures the image reflected in the third mirror 250 to indirectly capture at least a part of the first region (A1), the image reflected in the first mirror 231, and the image reflected in the second mirror 232. That is, the camera 240 captures an image including at least a part of the first region (A1) of the battery 10 reflected in the third mirror 250, the image reflected in the first mirror 231, and the image reflected in the second mirror 232.

[0093] The third mirror 250 is disposed at an angle on the side surface (200S) of the battery 10 and reflects at least a part of the first region (A1) of the battery 10, the image reflected on the first mirror 231, and the image reflected on the second mirror 232. With reference to the drawing, the third mirror 250 may be disposed at an angle so as to face between the Y direction (Y) and the Z direction (Z). The third mirror 250 may be disposed so that at least a part of the first region (A1) of the battery 10, the image reflected on the first mirror 231, and the image reflected on the second mirror 232 are incident and reflected at an angle of about 45°. In this case, it goes without saying that the camera 240 can be disposed facing the light reflected by the third mirror 250.

[0094] Meanwhile, the imaging device 200 may include a second illuminator 260 in addition to the first illuminator 220. The second illuminator 260 is disposed on the third mirror 250 to irradiate the cell 10 with light and may be a coaxial illuminator.

[0095] In addition, the transport means 270 transports the battery 10 in the axial direction (X) of the battery 10 so that the battery 10 passes through the housing 210. After the battery 10 is transported by the transport means 270 and reaches an area to be inspected in the housing 210, it stops for a certain period of time and is photographed by the camera 240, so that a side inspection of the battery 10 can be performed. After the inspection, the battery 10 is transported again by the transport means 270 to a subsequent process.

[0096] Meanwhile, the inversion means 280 turns over the battery 10 photographed by the camera 240. That is, the inversion means 280 rearranges the battery 10 so that it is rotated 180 degrees. Referring to the drawings, the inversion means 280 can turn the battery 10 upside down in the Z direction (Z). Therefore, the side inspection of the opposite side of the battery 10 on which the side inspection has not been performed can be performed by the same device as the imaging device 200 described above. Since the first area (A1) to be inspected is more than half of the side surface (200S) of the battery 10, the areas to be inspected during the first side inspection and the second side inspection may partially overlap each other.

[0097] At this time, for a smooth flow of the process, the side inspection of the opposite side of the battery 10 on which the side inspection has not been performed may be performed by a separate imaging device 200. That is, the imaging device 200 may include a pair of imaging devices 200 for inspecting both sides of the battery 10, respectively. However, in order to reduce costs, the side inspection of both sides of the battery 10 may be performed by one imaging device 200.

[0098] Meanwhile, in general, when inspecting the side appearance of a cylindrical battery, the battery must be rotated or rolled 360 degrees to acquire an image, which creates noise in the image, lowering the image quality and the detection ability of the inspection device.In addition, the further away from the center of the image is, the more difficult it is to ensure the visibility of defects due to shadows caused by curved surfaces.

[0099] The imaging device 200 according to an embodiment of the present invention includes a first mirror 231 and a second mirror 232, and thus can obtain an entire image of a first region (A1) that is more than half of the side surface (200S) of the battery 10 through a single image capture. That is, the appearance inspection of the entire side surface area of ​​the battery 10 is possible through two inspections, one for one side surface and the other for the battery 10. In addition, sufficient visibility of defects can be ensured even in an area far from the center of the first region (A1) to be inspected. As a result, an imaging device that can perform side appearance inspection without rotating or rolling a cylindrical battery can be provided. In addition, an imaging device that can prevent noise in the image and improve the quality of the image and the detection power of the inspection device can be provided.

[0100] Meanwhile, the imaging device according to the embodiment described through FIGS. 9 and 10 has a structure suitable for inspecting the side surface of a battery, and is presented as an example of the imaging device according to the present invention.

[0101] 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 the imaging device according to the another embodiment of the present invention.

[0102] The imaging device shown in Fig. 11a is a structure suitable for capturing images of the upper and lower surfaces of a battery cell, such as the rivets and vents, and can capture various images under various lighting conditions using a multi-lighting device as shown in Fig. 11b. Here, the multi-lighting device can include, for example, a dome light, a low angle light, a coaxial light, a ring light, and a dark field light. Thus, the imaging device according to the present invention can include a structure for capturing images of various parts of a battery cell, such as the upper and lower surfaces of the battery and the side of the battery.

[0103] FIG. 12 is a block diagram of a visual inspection apparatus according to an embodiment of the present invention.

[0104] The visual inspection apparatus 1000 according to an embodiment of the present invention may include at least one processor 1010, a memory 1020 for storing at least one instruction executed by the processor, and a transceiver 1030 connected to a network for communication.

[0105] Here, the at least one instruction may include an instruction to obtain and pre-process an image capturing an external appearance of the target object; an instruction to extract an inspection target area in the pre-processed image and perform brightness correction on the extracted inspection target area; an instruction to extract a group of defect candidates from the brightness-corrected image; an instruction to perform image post-processing on the extracted group of defect candidates; and an instruction to determine whether or not the target object has a defect from the post-processed image.

[0106] The visual inspection apparatus according to the embodiment of the present invention may be coupled to or may include an imaging device for capturing an image of the appearance of a target object. The imaging device according to the present invention may be provided in the same or similar form as the apparatus shown in Figures 9, 10, 11a and 11b.

[0107] The instruction to perform brightness correction on the extracted inspection area may include an instruction to calculate an average brightness of pixels in the extracted inspection area; an instruction to calculate a correction gain value based on the calculated average brightness and a target brightness; and an instruction to correct brightness for each pixel using the correction gain value.

[0108] The instructions to calculate the correction gain value may include instructions to calculate the correction gain value by dividing the target brightness by the average brightness.

[0109] The instruction to correct the brightness of each pixel by the correction gain value may include an instruction to correct the brightness of each pixel by multiplying an original brightness of each pixel by the correction gain value. The instruction to calculate an average brightness of pixels in the extracted inspection area may include an instruction to calculate the average brightness based on the number of pixels in the inspection area and the brightness of each pixel.

[0110] At this time, the target brightness can be set by the user.

[0111] On the other hand, the instruction to perform brightness correction on the extracted inspection area may include an instruction to change the captured color image to a black and white image before applying the brightness correction to the color image.

[0112] The instructions for performing brightness correction on the extracted inspection area may include instructions for separating the captured color image into R, G, and B channels before applying the brightness correction to the color image.

[0113] Thereby, the command to calculate the average brightness, the command to calculate the correction gain value, and the command to correct the brightness for each pixel may be performed for each of the R channel, G channel, and B channel.

[0114] The visual inspection apparatus 1000 may further include an input interface device 1040, an output interface device 1050, a storage device 1060, etc. Each component included in the visual inspection apparatus 1000 may be connected by a bus 1070 to communicate with each other.

[0115] The storage device 1060 can store at least one image produced at each step in the inspection method of the present invention, such as multiple images captured by the imaging device, pre-processed images therefrom, post-processed images, etc. The images stored in the storage device 1060 can be provided to at least one processor 1010 when necessary during the execution of the inspection method of the present invention.

[0116] Here, the processor 1010 may refer to a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which the method according to the embodiment of the present invention is performed. The memory (or storage device) may be composed of at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory may be composed of at least one of a read only memory (ROM) and a random access memory (RAM).

[0117] The operation of the method according to the embodiment of the present invention can be embodied as a computer readable program or code in a computer readable recording medium. The computer readable recording medium includes all kinds of recording devices in which data that can be read by a computer system is stored. In addition, the computer readable recording medium can be distributed to computer systems connected via a network, and the computer readable program or code can be stored and executed in a distributed manner.

[0118] Some aspects of the invention have been described in the context of an apparatus, but it may also be presented in terms of a corresponding method, where a block or apparatus corresponds to a method step or a feature of a method step. Similarly, aspects described in the context of a method may be presented in terms of a corresponding block or item or feature of a corresponding apparatus. Some or all of the method steps may be performed by (or using) a hardware apparatus, such as, for example, a microprocessor, a programmable computer, or an electronic circuit. In some embodiments, one or more of the most important method steps may be performed by such an apparatus.

[0119] Although the present invention has been described with reference to preferred embodiments thereof, those skilled in the art will understand that various modifications and variations of the present invention can be made without departing from the spirit and scope of the present invention as set forth in the following claims. [Explanation of symbols]

[0120] 1000: Visual inspection equipment 1010: Processor 1020:Memory 1040: Input interface device 1050: Output interface device 1060: Storage device

Claims

1. acquiring and pre-processing an image capturing an external appearance of the target object; Extracting an inspection target area in the preprocessed image and performing brightness correction on the extracted inspection target area; extracting a group of defect candidates from the brightness-corrected image; performing image post-processing on the extracted group of defect candidates; and determining whether the target object has a defect from the post-processed image; A method for inspecting the appearance of a product, including:

2. The step of performing brightness correction on the extracted inspection target area includes: calculating an 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 correcting the brightness of each pixel according to the correction gain value. The method for visually inspecting a product according to claim 1 , comprising:

3. The step of calculating a correction gain value based on the calculated average brightness and the target brightness includes:

3. The method of claim 2, further comprising the step of calculating the correction gain value by dividing the target brightness by the average brightness.

4. The step of correcting the brightness of each pixel according to the correction gain value includes:

3. The method for inspecting the appearance of a product according to claim 2, further comprising the step of correcting the brightness of each pixel by multiplying the original brightness of each pixel by the correction gain value.

5. The method for inspecting the appearance of a product according to claim 2 , wherein the target brightness can be set by a user.

6. The step of calculating an average brightness of pixels within the extracted examination area includes:

3. The method for inspecting the appearance of a product according to claim 2, further comprising the step of calculating the average brightness based on the number of pixels in the inspection target area and the brightness of each pixel.

7. The step of performing brightness correction on the extracted inspection target area includes:

3. The method for inspecting the appearance of a product according to claim 2, further comprising the step of converting the captured color image into a black and white image before applying brightness correction to the color image.

8. The step of performing brightness correction on the extracted inspection target area includes:

3. The method for inspecting the appearance of a product according to claim 2, further comprising the step of 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.

9. 9. The method of claim 8, wherein the steps of calculating the average brightness, calculating the correction gain value, and correcting the brightness for each pixel are performed for each of the R channel, the G channel, and the B channel.

10. at least one processor; a memory for storing at least one instruction to be executed by said at least one processor; The at least one instruction: instructions for obtaining and preprocessing an image capturing an appearance of the target object; instructions for extracting an area of ​​interest within the preprocessed image and performing brightness correction on the extracted area of ​​interest; instructions for extracting defect candidates from the brightness corrected image; instructions for performing image post-processing on the extracted set of defect candidates; and and determining whether the target object has defects from the post-processed image. Including, product appearance inspection equipment.

11. The product appearance inspection apparatus according to claim 10 , wherein the appearance inspection apparatus is linked to or includes an imaging device that captures an image of the appearance of the target object.

12. The command to perform brightness correction on the extracted inspection target area includes: instructions for calculating an 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 The product appearance inspection apparatus according to claim 10 or 11, further comprising an instruction to correct brightness for each pixel by the correction gain value.

13. The instructions for calculating the correction gain value include:

13. The product visual inspection apparatus of claim 12, further comprising instructions for calculating the correction gain value by dividing the target brightness by the average brightness.

14. The command to correct the brightness of each pixel according to the correction gain value is 13. The product appearance inspection apparatus according to claim 12, further comprising instructions for multiplying an original brightness of each pixel by the correction gain value to correct the brightness of each pixel.

15. The product appearance inspection device according to claim 12 , wherein the target brightness can be set by a user.

16. The instructions for calculating an average brightness of pixels within the extracted region of interest include:

13. The product appearance inspection apparatus according to claim 12, further comprising instructions for calculating the average brightness based on a number of pixels in the inspection target area and a brightness of each pixel.

17. The command to perform brightness correction on the extracted inspection target area includes: The product appearance inspection apparatus according to claim 12 , further comprising an instruction for converting a captured color image into a black and white image before applying brightness correction to the color image.

18. The command to perform brightness correction on the extracted inspection target area includes: The visual inspection apparatus for a product according to claim 12 , further comprising 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. 20. The product appearance inspection apparatus of claim 18, wherein the instruction to calculate the average brightness, the instruction to calculate the correction gain value, and the instruction to correct the brightness for each pixel are performed for each of the R channel, the G channel, and the B channel.

Images