Foil exposure inspection device and method for improving inspection accuracy
The foil exposure inspection device and method enhance battery cell manufacturing by offering real-time transparency and adaptive parameter adjustment, addressing inefficiencies in conventional systems.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-09-04
- Publication Date
- 2026-03-12
AI Technical Summary
Conventional foil exposure inspection technologies lack transparency and efficiency in battery cell manufacturing, making it difficult to respond to over- or under-inspection situations and requiring complex parameter adjustments.
A foil exposure inspection device and method that provides real-time image preprocessing, comprehensive user interface displaying processing results and parameters, and adaptive parameter adjustment to address over- or under-inspection issues.
Enhances inspection accuracy by providing transparency and convenience in parameter adjustment, allowing immediate response to inspection anomalies and improving test reliability.
Smart Images

Figure KR2025013675_12032026_PF_FP_ABST
Abstract
Description
Foil exposure inspection device and method for improving inspection accuracy
[0001] The present disclosure relates to a foil exposure inspection device and method. More particularly, it relates to a device and method for inspecting a foil exposure area through image processing.
[0002] Battery cells, the core components of secondary batteries, consist of a cathode, anode, separator, and electrolyte. During the manufacturing process, the cathode and anode are each manufactured by coating active materials onto current collectors. Inappropriate exposure of the metal foil used as the current collectors for the cathode and anode during this process can lead to reduced battery performance or safety issues. Therefore, accurately inspecting for foil exposure during the battery cell manufacturing process is crucial for ensuring battery quality and safety.
[0003] Conventional foil exposure inspection technologies employ a basic approach of camera-based image acquisition and preprocessing to inspect for defects. These technologies are aimed at quality inspection of battery-related components and share the common characteristic of providing an automated inspection process driven by a processor or control unit. However, these conventional technologies exhibit several fundamental limitations in meeting the precision and efficiency required in actual production settings.
[0004] For example, conventional foil exposure inspection systems can suffer from a lack of transparency during the inspection process. Existing technologies simply display the final inspection results, without providing a way for operators to verify what preprocessing was performed, what parameters were used, or the basis for defect determination. This makes it difficult for operators to identify the cause of over- or under-detections, potentially leading to significant delays in taking appropriate countermeasures.
[0005] The embodiments disclosed in the present disclosure disclose a foil exposure inspection device and method that performs foil exposure inspection through preprocessing on real-time images and provides a comprehensive user interface (UI) for displaying processing results and inspection parameters at each step of the inspection process along with the inspection results.
[0006] Another embodiment disclosed in the present disclosure discloses an inspection device and method comprising a camera module and an illumination module for image acquisition to be used for foil exposure inspection.
[0007] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.
[0008] A device according to the present disclosure for achieving the above-described technical task includes a camera module for photographing a surface of an object; an illumination module for illuminating the surface of the object; and a processor for performing a process for processing an image acquired through the camera module to inspect for the presence or absence of a surface defect of the object; wherein the processor preprocesses the image based on at least one preset parameter, inspects for the presence or absence of a surface defect of the object based on the preprocessed image, and generates and outputs an inspection result screen on which the inspection result, the preprocessed image, and the at least one parameter are displayed.
[0009] Additionally, the processor may provide an adjustment function of at least one parameter through the inspection result screen so as to respond to an over-inspection or under-inspection situation of the inspection result.
[0010] Additionally, the processor may detect a reference line including at least one of an edge line, a cutting height line, an overlay line, and an insulation line in the image based on the at least one parameter, and may preprocess the detected reference line by displaying it on the image.
[0011] Additionally, the processor can detect an exposed area of the foil in the image based on the reference line, and determine whether there is a surface defect of the object based on the detection result.
[0012] In addition, the processor can generate and output a main screen that displays an image acquired in real time through the camera module, a roll map indicating the arrangement of the object, a tact time for the inspection time of the object, a dimension graph indicating the dimensions of the objects arranged on the roll map, and a table indicating the inspection results of the objects arranged on the roll map.
[0013] In addition, the above-mentioned photographing module is provided with a line scan camera and can be positioned at a preset distance from the object so as to be able to photograph the surface of the object in a vertical direction.
[0014] Additionally, the lighting modules are provided in pairs and arranged symmetrically with respect to the photographing module, and can be cooled through air fittings.
[0015] Additionally, the processor can provide a trigger signal to the camera module and the lighting module according to an encoder input signal that moves the object.
[0016] In addition, the lighting module may further include a controller that is connected in plurality and receives the trigger signal from the processor to control the plurality of lighting modules.
[0017] Meanwhile, a method according to the present disclosure includes a step of acquiring an image of a surface of an object being photographed by a device; a step of preprocessing the image based on at least one preset parameter; a step of inspecting the presence or absence of a surface defect of the object based on the preprocessed image; a step of generating and outputting an inspection result screen in which the inspection result, the preprocessed image, and the at least one parameter are displayed; and a step of adjusting the at least one parameter through the inspection result screen so as to be able to respond to an over-inspection or under-inspection situation of the inspection result.
[0018] In addition, a computer program stored in a computer-readable recording medium for executing the present disclosure may be further provided.
[0019] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.
[0020] According to the above-described problem solving means of the present disclosure, it is possible to precisely inspect foil exposure defects and simultaneously provide transparency of the inspection process and convenience of parameter adjustment.
[0021] In particular, by simultaneously displaying the test results, preprocessed images, and parameters used for the test on a single integrated screen, it is expected that the test accuracy will be improved as adaptive parameter adjustment is possible for over- or under-testing situations.
[0022] In addition, the lighting cooling structure through air fitting can be adopted to prevent over-inspection situations in advance.
[0023] Additionally, it is expected that user convenience will be improved by adaptively changing the screen configuration of the UI to suit the user environment.
[0024] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.
[0025] FIG. 1 is a conceptual diagram of a foil exposure inspection system according to one embodiment of the present disclosure.
[0026] Fig. 2 is a drawing showing the overall hardware connection configuration of the foil exposure inspection device illustrated in Fig. 1.
[0027] FIG. 3 is a drawing for explaining the physical arrangement structure of the camera module and lighting module illustrated in FIG. 2.
[0028] Figure 4 is a drawing showing an example of the lighting module illustrated in Figure 2.
[0029] Fig. 5 is a control block diagram of the foil exposure inspection device illustrated in Fig. 1.
[0030] FIG. 6 is a flowchart of a foil exposure inspection method according to one embodiment of the present disclosure.
[0031] FIG. 7 is a drawing for explaining step S200 illustrated in FIG. 6.
[0032] FIGS. 8 to 13 are drawings showing actual images according to the type of foil exposure according to the present disclosure.
[0033] Fig. 14 is a drawing showing an example of an inspection result screen according to the present disclosure.
[0034] FIG. 15 and FIG. 16 are drawings showing an example of a main screen according to the present disclosure.
[0035] FIG. 17 is a drawing for explaining the window layout function according to the present disclosure.
[0036] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.
[0037] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.
[0038] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.
[0039] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.
[0040] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.
[0041] Singular expressions include plural expressions unless the context clearly indicates otherwise.
[0042] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.
[0043] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.
[0044] As used herein, the term "device according to the present disclosure" encompasses a variety of devices capable of performing computational processing and providing results to a user. For example, the device according to the present disclosure may include a computer, a server device, and a portable terminal, or may be any one of them.
[0045] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.
[0046] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.
[0047] The above portable terminal may include, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as a PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, a smart phone, and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, contact lenses, or a head-mounted device (HMD).
[0048] The artificial intelligence-related functions according to the present disclosure are operated via a processor and memory. The processor may be comprised of one or more processors. In this case, one or more processors may be a general-purpose processor such as a CPU, an AP, a Digital Signal Processor (DSP), a graphics-only processor such as a GPU or a Vision Processing Unit (VPU), or an artificial intelligence-only processor such as an NPU. One or more processors control the processing of input data according to predefined operating rules or artificial intelligence models stored in memory. Alternatively, if one or more processors are artificial intelligence-only processors, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model.
[0049] Specific structural or functional descriptions of embodiments according to the concept of the present invention disclosed in this specification are merely illustrative for the purpose of explaining embodiments according to the concept of the present invention, and embodiments according to the concept of the present invention may be implemented in various forms and are not limited to the embodiments described in this specification.
[0050] The terms used in this specification will be briefly explained, followed by a detailed description of the present invention. The terms used in this specification have been selected from widely used, current terms, taking into account their functions in the present invention. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, in which case their meanings will be described in detail in the relevant description of the invention. Therefore, the terms used in this invention should not be defined simply based on their names, but rather based on their inherent meanings and the overall content of the present invention.
[0051] Throughout this specification, when a part is said to "include" a component, unless otherwise specifically stated, this does not exclude other components but rather implies the inclusion of other components. Furthermore, terms such as "part," "module," etc., used herein refer to a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software.
[0052] In this specification, the terms "first," "second," etc. are used only for the purpose of distinguishing one component from another component, and do not limit the order or importance of the components unless otherwise specified. Therefore, within the scope of the present invention, a "first" component in one embodiment may be referred to as a "second" component in another embodiment, and similarly, a "second" component in one embodiment may be referred to as a "first" component in another embodiment.
[0053] The present invention relates to a comprehensive inspection system that precisely inspects foil exposure defects that may occur during the battery manufacturing process, while simultaneously providing transparency in the inspection process and the convenience of parameter adjustment. Conventional foil exposure inspection systems simply determine the presence or absence of defects, making it difficult to respond in real time to over- or under-inspection situations that arise during the inspection process. Furthermore, adjusting inspection parameters requires a separate, complex setup process.
[0054] To address these issues, the present invention provides complete transparency of the inspection process by simultaneously displaying inspection results, preprocessed images, and parameters used in the inspection on a single, integrated screen. Furthermore, the present invention provides an adaptive parameter adjustment function that allows the user to immediately adjust parameters on the screen and perform a re-inspection when an over- or under-inspection situation occurs in the inspection results.
[0055] FIG. 1 is a conceptual diagram of a foil exposure inspection system according to one embodiment of the present disclosure.
[0056] Referring to FIG. 1, the foil exposure inspection system (1) of the present invention may include a foil exposure inspection device (100) and a user terminal (200).
[0057] The foil exposure inspection device (100) may include hardware components that photograph the surface of a target object and provide illumination, and software components that process the acquired image to inspect for foil exposure defects.
[0058] The user terminal (200) can provide a user interface for checking inspection results and adjusting parameters, and can be connected to the foil exposure inspection device (100) via wired or wireless communication.
[0059] Fig. 2 is a drawing showing the overall hardware connection configuration of the foil exposure inspection device illustrated in Fig. 1.
[0060] Referring to FIG. 2, a foil exposure inspection device (100) according to the present disclosure may include a processor (110), a camera module (150), and a lighting module (160).
[0061] The camera module (150) can acquire real-time image data and transmit it to the processor (110), and the processor (110) can control the camera module (150) and the lighting module (160) based on the input signal of the encoder (10).
[0062] The encoder (10) is connected to a conveyor system or transfer device that moves an object and can detect the object's movement location information in real time. In this embodiment, the object is a battery cell manufactured by roll-to-roll equipment, and may be in the form of a battery cell in which an active material is coated on the surface of a positive or negative electrode plate, and a foil for the electrode plate is processed to connect the electrode plates in cell units.
[0063] The encoder input signal generated from the encoder (10) is transmitted to the processor (110), and the processor (110) generates a trigger signal based on this signal to precisely control the operation timing of the camera module (150) and the lighting module (160).
[0064] For example, the processor (110) can analyze the encoder input signal to calculate the exact time when the target reaches the inspection position and generate a strobe output signal accordingly. This strobe output signal is transmitted to the strobe controller (170), and the strobe controller (170) can synchronize and control a plurality of lighting modules (160).
[0065] FIG. 3 is a drawing for explaining the physical arrangement structure of the camera module and lighting module illustrated in FIG. 2.
[0066] Referring to FIG. 3, the camera module (150) may be positioned at a preset distance from the object (11) so as to be able to photograph the surface of the object (11) in a vertical direction. In one embodiment of the present invention, this distance may be, for example, about 15 mm, but is not limited thereto, and may be optimized in the range of 10 mm to 25 mm depending on the focal length of the camera and the required resolution. This distance may be set as a balance point that secures an optimal resolution capable of clearly photographing even minute defects on the surface of the object, while at the same time sufficiently securing the width of the inspection area.
[0067] The lighting modules (160) may be provided as a pair and arranged symmetrically with respect to the camera module (150). This symmetrical arrangement can provide uniform illumination to the surface of the object (11) and minimize false detection due to shadows or reflections. In one embodiment of the present invention, each lighting module (160) may be arranged at an angle of, for example, about 45 degrees with respect to the camera module (150), but is not limited thereto, and may be adjusted within a range of 30 to 60 degrees depending on the surface characteristics of the object and inspection requirements. According to some other embodiments, the number of lighting modules (160) is not limited to two, and may be expanded to four, six, or more depending on the size of the inspection area or the illumination uniformity requirements.
[0068] Figure 4 is a drawing showing an example of the lighting module illustrated in Figure 2.
[0069] Referring to FIG. 4, the lighting module (160) can provide line lighting, which can enable continuous inspection through synchronization with a line scan camera. One of the key features of the present invention is that an active cooling system using air fittings is applied to the lighting module (160). In conventional lighting systems, there was a problem that the lighting temperature increased due to heat generation from the LED lighting, which caused changes in the brightness or color temperature of the lighting, thereby affecting the inspection results. To solve this problem, the present invention can actively cool the lighting module (160) by supplying compressed air through air fittings.
[0070] In one embodiment of the present invention, the pressure of the compressed air supplied through the air fitting can be adjusted within a range of 0.1 MPa to 0.5 MPa depending on the heat generation of the lighting and the required cooling effect. Furthermore, the air flow rate can be optimized, for example, within a range of 5 L / min to 20 L / min. According to some other embodiments, a feedback control system can be implemented that additionally installs a temperature sensor to monitor the temperature of the lighting module (160) in real time and automatically adjusts the air supply amount based on the temperature.
[0071] Fig. 5 is a control block diagram of the foil exposure inspection device illustrated in Fig. 1.
[0072] Referring to FIG. 5, a foil exposure inspection device (100) according to one embodiment of the present disclosure may include a processor (110), a communication module (120), a memory (130), a display (140), a camera module (150), and a lighting module (160).
[0073] The processor (110) is a component responsible for the core control and processing functions of the present invention, and may include a high-performance CPU and GPU.
[0074] The communication module (120) can handle data communication between the processor (110) and an external system. In one embodiment of the present invention, the communication module (120) can include wired communication interfaces such as Ethernet, USB, RS-232, and RS-485, as well as wireless communication interfaces such as Wi-Fi and Bluetooth. This enables linkage with an upper manufacturing execution system (MES) or quality management system, and can provide real-time transmission of inspection result data and remote monitoring functions.
[0075] The memory (130) can store software programs executed by the processor (110) and data generated during the inspection process. In one embodiment of the present invention, the memory (130) may include an SSD for storing an operating system and inspection software, and a large-capacity HDD for storing inspection images and result data. The capacity of the SSD may be, for example, about 500 GB, but is not limited thereto, and may be selected from the range of 256 GB to 1 TB depending on the complexity of the software. The capacity of the HDD may be, for example, about 2 TB, but is not limited thereto, and may be expanded from the range of 1 TB to 10 TB depending on data storage requirements.
[0076] The display (140) is a component that displays test results and a user interface, and may include a high-resolution LCD or OLED panel. In one embodiment of the present invention, the resolution of the display (140) may be, for example, 1920×1080 pixels, but is not limited thereto, and may be configured with a 4K resolution of 2560×1440 pixels or 3840×2160 pixels for more precise image display. According to some other embodiments, a multi-monitor environment may be configured by connecting multiple displays, thereby allowing the test result screen and the main screen to be displayed simultaneously.
[0077] The camera module (150) is a component that photographs the surface of an object at high resolution and may be configured as a line scan camera or an area scan camera. In one embodiment of the present invention, the camera module (150) may be configured as a line scan camera, which may be suitable for inspecting a continuously moving object in real time.
[0078] The lighting module (160) is a component that illuminates the surface of an object and may be configured as a line bar light.
[0079] At least one component may be added or deleted to correspond to the performance of the components illustrated in Figure 5. Furthermore, it will be readily apparent to those skilled in the art that the relative positions of the components may be altered to correspond to the performance or structure of the system.
[0080] Meanwhile, each component illustrated in FIG. 5 refers to software and / or hardware components such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).
[0081] FIG. 6 is a flowchart of a foil exposure inspection method according to one embodiment of the present disclosure.
[0082] Referring to FIG. 6, a foil exposure inspection method according to one embodiment of the present disclosure can be executed by the device (100) illustrated in FIG. 1.
[0083] A foil exposure inspection method according to one embodiment of the present disclosure may include a step of acquiring an image of a target object (S100), a step of inspecting the presence or absence of an image-based surface defect (S200), and a step of outputting an inspection result (S300). Each step may be executed sequentially and may be performed repeatedly as needed.
[0084] The processor (110) can capture a real-time image by taking a picture of the surface of the object (11) through the camera module (150) (S100).
[0085] At this time, the processor (110) can analyze the encoder input signal received from the encoder (10) in real time to calculate the current position and movement speed of the object (11). Based on this information, the time at which the object (11) is accurately positioned in the shooting area of the camera module (150) can be predicted, and a trigger signal can be generated at that time.
[0086] A trigger signal can be simultaneously transmitted to the camera module (150) and the lighting module (160) to ensure perfect synchronization. The camera module (150) can immediately activate the image sensor upon receiving the trigger signal to capture an image of one line or one frame. At the same time, the lighting module (160) can momentarily emit high-intensity light in response to the trigger signal to support the acquisition of a clear image. This strobe lighting method can minimize motion blur caused by the movement of the object and maximize the clarity of the image.
[0087] The processor (110) can preprocess the acquired image and inspect the preprocessed image for surface defects of the object (S200).
[0088] First, the processor (110) can perform preprocessing to detect at least one reference line from the acquired image based on at least one preset parameter. In this regard, FIG. 7 will be described as an example.
[0089] FIG. 7 is a drawing for explaining step S200 illustrated in FIG. 6.
[0090] Referring to (a) of Fig. 7, an image capturing the bottom area of the object can be confirmed, and referring to (b) of Fig. 7, an image capturing the top area of the object can be confirmed.
[0091] The processor (110) may first detect a reference line in an image based on at least one preset parameter and visually display it. At this time, the processor (110) may output a user screen for receiving input of at least one parameter from the user via the display (140). A detailed description of this will be provided later.
[0092] The reference line used in the present invention may include at least one of an edge line, a cutting height line, an overlay line, and an insulation line.
[0093] An edge line is a line indicating the boundary between the electrode portion and the insulating portion of a target object, and can be the most basic criterion in foil exposure inspection. For example, the processor (110) can detect the edge line by applying a Canny edge detection algorithm.
[0094] The cutting height line is a reference line indicating the cutting depth set in the laser cutting process and can be used to detect foil exposure due to laser cutting. For example, the processor (110) can analyze the brightness distribution of an image based on a brightness threshold parameter, find the boundary between the cut portion and the uncut portion, and detect it as the cutting height line.
[0095] The overlay line serves as a reference line for checking the alignment status between different layers and can be used to detect foil exposure due to interlayer misalignment. For example, the processor (110) can apply a template matching algorithm, calculate the similarity with a predefined pattern, and determine the position of the overlay line based on a threshold parameter.
[0096] The insulation line serves as a reference line indicating the boundary between the insulating material and the conductive material, and can be used to detect foil exposure due to defects in the insulation. For example, the processor (110) can apply a color segmentation algorithm and distinguish between the insulating material and the conductive material based on the color range in the HSV color space.
[0097] The processor (110) can display the detected reference lines in different colors over the original image in an overlay manner.
[0098] The processor (110) can detect an exposed foil area based on a preprocessed image in which reference lines are indicated. In this process, the processor (110) can determine an area that deviates from a normal range according to preset parameters based on each reference line as a foil exposure area. For example, if a pattern that should appear in the electrode portion based on the edge line is found in the insulating portion, or a conductive pattern that should not appear in the insulating portion is found, this can be determined as a foil exposure area. In this regard, FIGS. 8 to 13 will be described as examples.
[0099] FIGS. 8 to 13 are drawings showing actual images according to the type of foil exposure according to the present disclosure.
[0100] Referring to Figure 8, a burr defect at the electrode edge can be identified. This defect occurs when the edge of the electrode is unintentionally burred, exposing the foil. This defect can occur primarily during mechanical processing. For example, the processor (110) can detect such burr defects by analyzing the continuity of the electrode boundary based on the edge line.
[0101] Referring to Figure 9, a foil exposure defect caused by laser cutting can be identified. This defect occurs when the cutting depth is excessive during the laser cutting process, cutting through the foil. This defect can be detected based on a cutting height line. For example, the processor (110) can measure the depth of the cut area and determine it as a defect if it exceeds a set tolerance range.
[0102] Referring to Figure 10, an elliptical defect in the insulation can be identified. This defect is a phenomenon in which an elliptical defect occurs in the insulating material, exposing the foil, and can be detected based on the insulation line. For example, the processor (110) can apply the elliptical detection algorithm of the Hough Transform to detect an elliptical pattern in the insulation area.
[0103] Referring to Figure 11, a solid line-shaped foil exposure defect can be identified. This defect, which occurs when continuous foil exposure occurs in a straight line, can primarily be caused by mechanical damage or material defects during the manufacturing process. For example, the processor (110) can detect such solid line-shaped defects by applying a Hough transform straight line detection algorithm.
[0104] Referring to Figure 12, a directional foil exposure defect can be identified. This defect is a foil exposure with a pattern oriented in a specific direction, and may be related to the directionality of the manufacturing process or the anisotropy of the material. For example, the processor (110) can detect a pattern in a specific direction by applying a directional filter or a Gabor filter.
[0105] Referring to Figure 13, a dot-shaped foil exposure defect can be identified. This defect is a phenomenon in which localized foil exposure occurs in the form of a small dot, and can be primarily caused by foreign substances or bubbles. For example, the processor (110) can detect such dot-shaped defects by applying a blob detection algorithm.
[0106] The parameters used for detection of such foil exposure areas can be set by the user through the recipe setting screen of the UI according to the present disclosure.
[0107] Alternatively, the algorithms and parameters set by the user can be optimized based on the characteristics of the target object and inspection requirements. For example, the processor (110) can further apply machine learning or deep learning techniques to improve the accuracy of defect classification. In one embodiment of the present invention, a classification model based on a convolutional neural network (CNN) can be used, which can be trained using a large amount of training data to automatically classify each defect type.
[0108] If a foil exposure area is detected in the preprocessed image, the processor (110) determines that a surface defect of the target object exists and outputs the inspection result as defective, and if a foil exposure area is not detected, the inspection result can be output as normal (S300).
[0109] The processor (110) can output the inspection results through the inspection results screen of the UI according to the present disclosure. This will be described with reference to FIG. 14.
[0110] Fig. 14 is a drawing showing an example of an inspection result screen according to the present disclosure.
[0111] Referring to Fig. 14, the inspection results screen (20) can simultaneously display inspection results (21), preprocessed images (23), and parameters (25) on a single, integrated screen. This integrated display method provides complete transparency of the inspection process and can help users intuitively determine the reliability of the inspection results.
[0112] The inspection results (21) area may display information such as the location, size, and type of the detected foil exposure defect. In one embodiment of the present invention, the inspection results may be displayed in a table format, and may include information such as X-coordinate, Y-coordinate, width, height, area, defect type, and reliability for each defect. In addition, color coding may be applied according to the severity of the defect.
[0113] The preprocessed image (23) area may display an image with a reference line marked and an image with the detected foil exposure area highlighted. This image allows the user to visually confirm the criteria by which the inspection algorithm detected the defect. In one embodiment of the present invention, the image may provide a zoom function, allowing for a detailed observation of the area of interest using a mouse wheel or touch gestures. Furthermore, a function may be included to directly measure the size of the defect by providing a measurement tool on the image.
[0114] The parameter (25) area can display all parameter values used in the current inspection. These parameters can be categorized into image preprocessing parameters, reference line detection parameters, defect detection parameters, etc. In one embodiment of the present invention, the image preprocessing parameters can include brightness adjustment values, contrast adjustment values, gamma correction values, noise removal filter strength, etc. The reference line detection parameters can include detection threshold values for each line, detection algorithm selection, line display color, etc. The defect detection parameters can include detection sensitivity, minimum size, maximum size, reliability threshold values, etc. for each defect type.
[0115] The processor (110) can provide a real-time parameter adjustment function through the inspection result screen (20). That is, if a user discovers an over- or under-inspection situation in the inspection results, the user can immediately adjust the corresponding parameter in the parameter (25) area and perform a re-inspection. In one embodiment of the present invention, parameter adjustment can be performed through various UI controls such as a slider, spin box, or text input, and the result can be reflected and displayed in the preprocessed image (23) immediately after the parameter change.
[0116] Over-detection refers to cases where a normal part is incorrectly judged as a defect. This can occur when the detection sensitivity is set too high or noise removal is insufficient. In such cases, users can reduce over-detection by increasing the detection threshold for the corresponding defect type or increasing the strength of the noise removal filter. Under-detection refers to cases where a true defect is not detected. This can occur when the detection sensitivity is set too low or the reference line is incorrectly set. In such cases, users can reduce under-detection by lowering the detection threshold or adjusting the position of the reference line.
[0117] FIG. 15 and FIG. 16 are drawings showing an example of a main screen according to the present disclosure.
[0118] Referring to FIG. 15, the processor (110) can output the main screen (30) through the UI to provide information related to the overall inspection results.
[0119] The main screen (30) may include a real-time image (31), an inspection result table (33), a crop image (35), etc., through which the overall inspection situation can be comprehensively monitored.
[0120] The real-time image (31) area can display images acquired in real time through the camera module (150). This allows the user to check the status of the object currently being inspected in real time and monitor whether the inspection system is operating normally.
[0121] The inspection results table (33) may display the inspection results of recently inspected objects in chronological order. Each row corresponds to one object and may include information such as the object ID, inspection time, number of detected defects, distribution by defect type, and overall judgment result (good / defective).
[0122] The crop image (35) area can display enlarged images of the exposed areas detected in previous inspections. This allows the user to view the actual appearance of the detected defects in detail and verify the accuracy of the inspection algorithm.
[0123] Referring to Fig. 16, an expanded embodiment of the main screen (30) can be seen. In this embodiment, additional information such as a roll map (37), tact time (38), and dimension graph (39) can be displayed.
[0124] The roll map (37) is a map that visually represents the arrangement of objects, and can help users grasp the location and inspection status of each object on the production line at a glance. In one embodiment of the present invention, the roll map may be configured in a grid format, with each cell corresponding to a single object. Normal objects may be displayed in green, objects with detected defects in red, and objects under inspection in yellow. Furthermore, a function may be provided that allows the user to check detailed inspection results for a specific object by clicking on a specific cell.
[0125] The tact time (38) can provide information on the inspection time of an object, allowing for monitoring of production efficiency. In one embodiment of the present invention, the tact time can be displayed in real-time graph form, along with statistical information such as average tact time, maximum tact time, and minimum tact time. A function may also be included to set a target tact time and provide a warning if it is exceeded.
[0126] The dimension graph (39) can display dimensional information of objects placed on the roll map in a graph format. This can be used to monitor product dimensional changes and for quality management. In one embodiment of the present invention, the dimension graph can be displayed in various forms, such as a histogram, scatter plot, or time-series graph, and the user can select the desired form. Furthermore, a function may be included to set a dimensional tolerance range and provide separate indications for objects that fall outside this range.
[0127] In addition, the processor (110) can output a recipe setting screen through the UI to receive input from the user of parameters for inspecting the presence or absence of surface defects.
[0128] The recipe setup screen can be largely divided into a parameter input area, a preview area, and a recipe management area. The parameter input area allows for systematic entry of all the inspection parameters described above, categorized by category. In one embodiment of the present invention, parameters can be categorized into categories such as basic settings, image preprocessing, reference line detection, defect detection, and result display.
[0129] The preview area allows users to view real-time inspection results based on the currently set parameters. Users can load sample images, adjust parameters, and immediately view the results, allowing them to find the optimal parameter combination. In one embodiment of the present invention, the preview can simultaneously display the original image, preprocessed image, and defect detection result image, allowing for comparative analysis of the effects of each processing step.
[0130] The recipe management area can provide management functions for created recipes, such as saving, loading, modifying, and deleting them. Each recipe can have a unique name and description, and metadata such as creation date, modification date, and author can also be stored. In one embodiment of the present invention, recipes can be stored as files in XML or JSON format, using a standardized format to ensure portability to other systems.
[0131] Additionally, the recipe system can provide version management capabilities, allowing for tracking parameter change history and rolling back to previous versions when necessary. This can facilitate rapid recovery in the event of issues arising from changes in test conditions.
[0132] Meanwhile, the processor (110) can provide a window layout function on the inspection result screen or main screen of such UI. In this regard, FIG. 17 will be described as an example.
[0133] FIG. 17 is a drawing for explaining the window layout function according to the present disclosure.
[0134] Referring to FIG. 17, the processor (110) can provide a flexible layout adjustment function for various screens, such as the test results screen (20) and the main screen (30). This function can help configure an interface optimized for the user's work environment and preferences.
[0135] The window resizing feature allows users to freely adjust the size of each screen. The positioning feature allows users to move each screen to a desired location. This can be particularly useful in multi-monitor environments, allowing users to configure an optimized layout, such as placing the main screen on the primary monitor and the test results screen on the secondary monitor.
[0136] The independent window split feature allows users to separate individual functions from a single integrated screen into separate, independent windows. For example, only the preprocessed image (23) portion of the test results screen (20) can be separated into a separate window and displayed in a larger size. This feature can be useful in situations where focusing on specific information is necessary.
[0137] The tab merging feature allows users to merge multiple independent windows into a single tab. This can help users quickly access necessary information while efficiently utilizing screen space. In one embodiment of the present invention, tabs can be easily rearranged using drag-and-drop, and their names can also be changed by double-clicking the tab title. Meanwhile, the disclosed embodiments can be implemented in the form of a recording medium storing computer-executable instructions. The instructions can be stored in the form of program code, and when executed by a processor, they generate program modules to perform the operations of the disclosed embodiments. The recording medium can be implemented as a computer-readable recording medium.
[0138] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.
[0139] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.
Claims
1. A camera module that photographs the surface of an object; A lighting module that illuminates the surface of the object; and A processor that processes an image acquired through the camera module to perform a process for inspecting the presence or absence of a surface defect of the object; The above processor, Preprocessing the image based on at least one preset parameter, Based on the above preprocessed image, the presence or absence of surface defects of the object is inspected, A foil exposure inspection device for improving inspection accuracy, which generates and outputs an inspection result screen in which the above inspection results, the above preprocessed image, and the above at least one parameter are displayed.
2. In paragraph 1, The above processor, A foil exposure inspection device for improving inspection accuracy, which provides an adjustment function of at least one parameter through the inspection result screen so as to respond to over-inspection or under-inspection situations of the inspection results.
3. In paragraph 1, The above processor, Detecting a reference line including at least one of an edge line, a cutting height line, an overlay line, and an insulation line in the image based on at least one parameter, A foil exposure inspection device for improving inspection accuracy, which preprocesses the detected reference line by displaying it on the image.
4. In paragraph 3, The above processor, Detecting the exposed area of the foil in the image based on the above reference line, A foil exposure inspection device for improving inspection accuracy, which determines whether there is a surface defect on the target object based on the above detection results.
5. In paragraph 1, The above processor, A foil exposure inspection device for improving inspection accuracy, which generates and outputs a main screen that displays images acquired in real time through the camera module, a roll map indicating the arrangement of the object, a tact time for the inspection time of the object, a dimension graph indicating the dimensions of the objects arranged on the roll map, and a table indicating the inspection results of the objects arranged on the roll map.
6. In paragraph 1, The above shooting module, A foil exposure inspection device for improving inspection accuracy, which is equipped with a line scan camera and is positioned at a preset distance from the object so as to be able to photograph the surface of the object in a vertical direction.
7. In paragraph 6, The above lighting module, A foil exposure inspection device for improving inspection accuracy, which is provided in pairs and arranged symmetrically based on the above-mentioned photographing module and cooled through an air fitting.
8. In paragraph 1, The above processor, A foil exposure inspection device for improving inspection accuracy, which provides a trigger signal to the camera module and the lighting module according to an encoder input signal that moves the target object.
9. In paragraph 8, A foil exposure inspection device for improving inspection accuracy, further comprising a controller in which a plurality of the above lighting modules are connected and which receives the trigger signal from the processor and controls the plurality of the lighting modules.
10. In a foil exposure inspection method performed by a device, A step of acquiring an image of the surface of an object; A step of preprocessing the image based on at least one preset parameter; A step of inspecting the presence or absence of surface defects on the object based on the preprocessed image; A step of generating and outputting a test result screen in which the test result, the preprocessed image, and the at least one parameter are displayed; and A foil exposure inspection method for improving inspection accuracy, comprising: a step of adjusting at least one parameter through the inspection result screen so as to be able to respond to an over-inspection or under-inspection situation of the inspection result;
Citation Information
Patent Citations
Simulation system and method for appearance inspection
JP2001043367A
Microwave joint metal detector
KR1020220101043A
Finishing Method of Macrame
KR1020230168340A
Cap assembly, secondary battery including same, and method for manufacturing secondary battery
KR1020260031308A
Method and device for detecting defect, storage medium and electronic device
US20240202893A1