TWI761880B - Apparatus, method, computer readable medium and computer program product for inspecting substrate defect - Google Patents

Abstract

The substrate defect inspection device of the present invention comprises: a moving table to move the substrate to an inspection position; illumination, to irradiate a predetermined light to the substrate in order to obtain a photographed image; at least one line scan camera to photograph the substrate in units of predetermined lines; at least An area camera, which takes pictures of the substrate in a predetermined area; a database, which stores images used to detect defects in the substrate; a control unit, which uses a moving table to move the position of the substrate, and controls the lighting to capture and photograph the coating of the substrate by the line scan camera. Part of the obtained image and the image obtained by photographing the part of the solder resist layer, based on the obtained image, the state of the substrate is determined as one of normal, defective and re-inspection, thereby detecting the initial defect, and controlling the substrate determined to be re-inspected Lighting is performed to acquire a substrate image obtained by photographing the substrate with an area camera, and based on the acquired substrate image, the state of the substrate is judged to be either normal or defective, thereby detecting a second defect.

Description

Substrate defect inspection apparatus, method, computer-readable recording medium, and computer program product

Embodiments of the present invention relate to an apparatus and method for inspecting a substrate for defects. In more detail, it relates to a board|substrate defect inspection apparatus and method which do not need to reconfirm the defect of a board|substrate, such as a printed circuit board.

Since various types of defects may occur, various types of inspections are performed on products such as Printed Circuit Boards (PCBs) for delivery purposes. As in the related prior art document Korea Publication No. 10-2005-0103525, there is described a PCB inspection and screening device for preventing a circuit pattern formed on a lower surface and a probe between a circuit pattern and a probe before the PCB is shipped from the factory. Checked on an over-contact basis.

In order to inspect the printed circuit board, in addition to the electrical inspection as in the prior art document, a rule base inspection is performed. Such a rule inspection is an inspection in which an inspector directly applies a predetermined rule to a printed circuit board to perform inspection.

Since such rule inspection is based on the rules determined by the inspector, even if it is a foreign matter or contamination instead of a defect, it is detected as a defect, and the rules are set too strict in order to increase the probability of detecting a defect. Therefore, the error of the normal specification is also recognized as a defect. therefore, There is such a problem: in order to prevent such a situation from happening, it is also necessary to use other equipment to inspect the PCB and identify whether the status of the PCB is qualified or unqualified.

In addition, there is also a problem that since it is impossible for each operator who inspects the PCB to maintain a constant level of inspection standards, emotional errors and the like occur, resulting in a decrease in the consistency of product inspection results, thereby reducing the yield of PCB manufacturing. reduce.

Therefore, there is a need for a technique for solving the above-mentioned problems.

On the one hand, the above-mentioned background art is the technical information held by the inventor in order to obtain the present invention or the technical information obtained in the process of obtaining the present invention, rather than the conventional knowledge disclosed to the public before applying for the present invention technology.

The purpose of each embodiment disclosed in this specification is to provide a substrate defect inspection apparatus and method that automates the inspection process by an operator.

The purpose of each embodiment disclosed in this specification is to provide a substrate defect inspection apparatus and method that does not require additional equipment or additional inspection depending on the inspector.

The purpose of each embodiment disclosed in this specification is to provide a substrate defect inspection apparatus and method capable of maintaining the consistency of substrate inspection results.

The purpose of each embodiment disclosed in this specification is to provide a substrate defect inspection apparatus and method for improving product yield through automation of substrate inspection.

As a technical means for solving the technical problem, according to an embodiment, a substrate defect inspection apparatus includes: a moving table to move the substrate to an inspection position; illumination, for irradiating a predetermined light on the substrate in order to acquire a photographed image; at least one line scan camera for photographing the substrate in units of prescribed lines; at least one area camera for photographing the substrate in units of prescribed areas; a database for storing images for detecting defects of the substrate; and a control unit for moving the position of the substrate by using the moving table, and controlling the illumination to obtain images obtained by photographing the coating portion of the substrate by the line scan camera and the image obtained by photographing the solder mask portion, and based on the obtained image, the state of the substrate is determined as one of normal, defective and re-inspection, thereby detecting the initial defect, and then for the substrate determined to be re-inspected The illumination is controlled to acquire a substrate image obtained by photographing the substrate with an area camera, and based on the acquired substrate image, the state of the substrate is determined to be either normal or defective, thereby detecting a second defect.

According to another embodiment, a substrate defect inspection method performed by a substrate defect inspection apparatus includes acquiring an image obtained by photographing a plated portion of the substrate by a line scan camera and photographing a solder mask portion by controlling illumination for irradiating light to the substrate The step of obtaining the image; the step of detecting the initial defect by determining the state of the substrate as one of normal, defective and re-inspection based on the obtained image; controlling the illumination for the substrate determined to be re-inspected, A step of acquiring a substrate image obtained by photographing the substrate with an area camera; a step of detecting a second defect by judging the state of the substrate as one of normal and defective based on the acquired substrate image.

According to yet another embodiment, there is provided a computer-readable recording medium for recording a program capable of executing a substrate defect inspection method, the substrate defect inspection method being executed by a substrate defect inspection apparatus, and comprising: through control for irradiating light to the substrate The steps of obtaining the image obtained by photographing the coating part of the substrate by the line scan camera and the image obtained by photographing the solder mask layer part; based on the obtained image, the state of the substrate is judged as one of normal, defective and re-inspection , the first defect is detected; the illumination is controlled for the substrate determined to be re-inspected, and the substrate image obtained by photographing the substrate with the area camera is obtained; based on the acquired substrate image, the state of the substrate is determined to be normal and one of the defects, thereby detecting the step of re-defect.

According to yet another embodiment, there is provided a computer program executed by a substrate defect inspection apparatus and stored in a medium for executing a substrate defect inspection method, the substrate defect inspection method being executed by the substrate defect inspection apparatus, and comprising: controlling for The steps of irradiating light to the illumination of the substrate, obtaining an image obtained by photographing the coating portion of the substrate by a line scan camera and an image obtained by photographing the solder mask portion; based on the obtained image, the state of the substrate is judged as normal, defective and One of the steps of re-inspection, whereby the initial defect is detected; the step of acquiring a substrate image obtained by photographing the substrate with an area camera by controlling the illumination for the substrate determined to be re-inspected; based on the acquired substrate image, the substrate image The state is judged to be one of normal and defective, thereby detecting the step of re-defect.

According to any one of the means for solving the problem of the present invention described above, it is possible to provide a substrate defect inspection apparatus and method that automate the inspection process by an operator.

According to any of the means for solving the problem of the present invention, it is possible to provide a substrate defect inspection apparatus and method that do not require additional equipment or additional inspection depending on the inspector.

According to any one of the means for solving the problem of the present invention, it is possible to provide a substrate defect inspection apparatus and method capable of maintaining the consistency of substrate inspection results.

According to any one of the means for solving the problem of the present invention, it is possible to provide a substrate defect inspection apparatus and method for improving the yield of products through automation of substrate inspection.

The effects obtainable in the present invention are not limited to the above-mentioned effects, and other various effects not mentioned can be clearly understood by those skilled in the art from the contents described below.

100: Substrate defect inspection device

110: Mobile Workbench

120: Lighting

130:Database

140: Adjusting the camera

150: Line scan camera

160: Area Camera

170: Input and output section

180: Control Department

FIG. 1 is a block diagram showing a substrate defect inspection apparatus according to an embodiment.

2 is a cross-sectional view showing a substrate defect inspection apparatus according to an embodiment.

FIG. 3 is a schematic diagram for explaining a state in which a substrate is photographed using a line scan camera according to an embodiment.

FIG. 4 is a schematic diagram for explaining a situation in which a substrate is photographed using an area camera according to an embodiment.

FIG. 5 is a flowchart for explaining a substrate defect inspection operation performed by the substrate defect inspection apparatus according to the embodiment.

FIG. 6 is a flowchart for explaining an operation of determining a defect using an image captured by a line scan camera according to an embodiment.

7 is a flowchart for explaining an operation of determining a defect using an image captured by an area camera according to an embodiment.

Hereinafter, each embodiment will be described in detail with reference to the drawings. The respective embodiments described below can be modified and implemented in various forms. In order to explain the features of the embodiments more clearly, detailed descriptions of matters well known to those skilled in the art to which the embodiments pertain below are omitted. In addition, parts irrelevant to the description of each embodiment are omitted in the drawings, and similar parts are denoted by similar reference numerals throughout the specification.

Throughout the specification, when a certain structure is "connected" to another structure, it includes not only the case of "direct connection" but also the case of "connected with other structures in between". In addition, when a certain structure "includes" a certain structure, unless specifically stated to the contrary, it means that other structures may also be included, rather than excluding other structures.

Hereinafter, each embodiment will be described in detail with reference to the drawings.

However, prior to these descriptions, the meaning of each term used below will be defined.

A "substrate" is a substrate in which circuit wiring for connecting circuit components is formed on an insulator in the form of electrical conductors based on circuit design. Printed circuit board (FPCB: Flexible Printed Circuit Board). The substrate refers to an object or an object to be inspected by a substrate defect inspection apparatus to be described later. Therefore, the substrate can be a display panel, a PCB panel, a liquid crystal display (LCD: Liquid Crystal Display), an organic light emitting diode (OLED: Organic Light Emitting Diodes), a solar panel, a fabric or metal, etc. Any other product that can acquire images to perform inspections instead.

FIG. 1 is a block diagram showing a substrate defect inspection apparatus according to an embodiment.

As shown in FIG. 1 , the substrate defect inspection apparatus 100 may include a moving table 110 , an illumination 120 , a database 130 , an adjustment camera 140 , a line scan camera 150 , an area camera 160 , an input/output unit 170 and a control unit 180 .

The moving table 110 is used to move the substrate to the inspection position. The moving table 110 may include a boat for mounting the substrate to be inspected and a guide rail to which the boat is coupled and moved. In addition, at the upper end of the conveyance tank, a fixing strip for fixing the substrate may be provided.

The moving table 110 may include a flipper, which is used to flip the substrate when both sides of the substrate need to be inspected according to requirements. The mobile station 110 may include a storage tray for sorting and storing inspected substrates.

Around a camera such as a line scan camera 150 or an area camera 160 for capturing images of substrates to be inspected, more than one illumination 120 may be provided that can illuminate the substrates located on the transfer chute. Therefore, as the number of line scan cameras 150 and area cameras 160 for inspection increases, the number of illuminations 120 also increases. Illumination 120 can be controlled by controlling the illuminance value By adjusting the brightness, various images can be created by adjusting the brightness. When photographing the substrate, more than two illuminations 120 may be used simultaneously to acquire an image. When the illumination 120 corresponds to the area camera 160, it may have a prescribed illuminance value (or prescribed brightness) that enables classification based on defect characteristics of the substrate.

The database 130 may be used to install and store various types of data such as files or programs. The control unit 180 described later may access and use the data stored in the database 130 , or the control unit 180 may store new data in the database 130 . In addition, the database 130 may store programs executable by the control unit 180 .

Database 130 may be used to store information about defective substrates. For example, the database 130 may store images of defective substrates for determining defective substrates. At this time, the defective substrate images stored in the database 130 may be data learned through artificial intelligence, and may be used for inspection of defective substrates.

The database 130 may store files for inspecting defective substrates. The database 130 may store programs that classify defective substrates and also detect defect types of the classified defective substrates. In particular, the database 130 can store a specific computer program capable of realizing such artificial intelligence (AI): in order to inspect the defective substrate, the defect image data is learned through deep learning, and the learned defect image data is used for processing. Used in defect image inspection.

The camera 140 is adjusted to photograph the substrate to be inspected. The adjustment camera 140 can provide the captured image to the control unit 180 . The adjustment camera 140 may be positioned within a specified distance relative to the line scan camera 150 and the area camera 160 . As a result, the camera 140 is adjusted to capture a specific image that is required to register images captured by the line scan camera 150 or the area camera 160 for inspection.

The line scan camera 150 is a camera that uses a linear image sensor to image a substrate in units of lines of a predetermined length. The line scan camera 150 can provide the shooting data to the control unit 180, to determine the defect of the photographed substrate. Since the line scan camera 150 captures images in a linear manner, it is possible to capture images even when the substrate is in a moving state.

The area camera 160 is a camera that captures images of substrates in units of areas within a predetermined range. The area camera 160 can photograph the substrate and provide the photographic data to the control unit 180 to determine the defect of the photographed substrate.

The adjustment camera 140, the line scan camera 150, and the area camera 160 are mounted on a part of the fixed structure of the substrate defect inspection apparatus 100, etc., and may include or be mounted with motors that move in the directions of the X-axis, Y-axis, and Z-axis that are perpendicular to each other. . For example, when the X-axis is lateral, the Y-axis may be longitudinal, and the Z-axis may be the depth direction of the substrate (ie, the direction toward or away from the substrate). Here, the X axis and the Y axis may be directions parallel to the ground, and the Z axis may be the direction perpendicular to the ground. The adjustment camera 140 , the line scan camera 150 and the area camera 160 can adjust the positions of the cameras based on these three axes to capture images of the substrate for inspection.

As a result, the control unit 180 can control the adjustment camera 140, the line scan camera 150 and the area camera 160 to be respectively set to predetermined magnifications for capturing the image of the substrate, for example, it can be set to even 5 μm (um) to 15 μm. A magnification that can detect even small and small defects.

The input/output unit 170 may include an input unit for receiving input information input by a user, ie, an inspector, and an output unit for displaying information such as an execution result of an operation or a state of the substrate defect inspection apparatus 100 . For example, the input/output unit 170 may include an operation panel for receiving user input information, a display panel for displaying a screen, and the like.

Specifically, the input portion may include devices capable of receiving various types of user input information, such as keyboards, mechanical buttons, touch screens, cameras, or microphones. In addition, the output section can be Including display panels or speakers, etc. However, it is not limited to this, and the input/output part 170 may include a structure supporting various types of input/output.

The control unit 180 controls the overall operation of the substrate defect inspection apparatus 100, and may include a processor such as a CPU. The control unit 180 can control other components included in the substrate defect inspection apparatus 100 so as to perform operations corresponding to the user input information received by the input/output unit 170 .

The control section 180 can control the moving table 110 so that the substrates inserted into the substrate defect inspection apparatus 100 can be moved to inspection positions, respectively.

The control part 180 may control the illumination 120 corresponding to the line scan camera 150 in order to detect defects. For example, the control part 180 may adjust the brightness of the lighting 120 in two stages. At this time, the control unit 180 may control the illumination 120 with the illuminance value for inspecting the portion where the circuit is generated, and may control the illumination 120 with the illuminance value for inspecting the plating portion. As described above, the control unit 180 may control the illumination 120 corresponding to the line scan camera 150 twice.

The control unit 180 can control the line scan camera 150 to adjust the brightness of the illumination 120 in two stages to capture images of the plating portion of the substrate and the portion where the circuit is generated (eg, the solder resist (SR: Solder-resist) portion). . Here, the images obtained by photographing the plating portion and the solder resist portion are luminance images. Thus, the control unit 180 performs registration on the image obtained by photographing the plating layer portion and the image obtained by photographing the solder resist layer portion, and determines the state of the substrate as normal, defective (true defect) based on the image obtained through the registration ) and recheck either. Additionally, the line scan camera 150 may be a color line scan camera capable of acquiring color images.

Since the resolution of the line scan camera 150 is lower than that of the area camera 160 , for defects smaller than a predetermined size (length or area), the control unit 180 may need to perform an accurate inspection in order to determine the defect. As described above, the control unit 180 may determine a defect smaller than a predetermined size to be re-inspected check. Moreover, the control part 180 determines these defects as a re-inspection, when it is necessary to classify|categorize a defect determination more precisely.

The control unit 180 can use the image acquired by the line scan camera 150 to detect the defects of the substrate for the first time. For the substrate determined to be a defect, that is, a true defect, the control unit 180 may further determine the type of the defect. For example, it can be judged by distinguishing between circuit defects and plating defects. Here, the circuit defects may include circuit open circuit, circuit short circuit, upper surface scratches, lower surface scratches, foreign matter, metal foreign matter, solder mask (SR) peeling, automated optical inspection (AOI: Automated Optical Inspection) defects, unetched, Specific defects related to solder resist (SR) residues, cracks, discoloration, lift, and chromatic aberration. Additionally, plating defects may include plating cracks, plating shorts, plating build-up, scratches, foreign objects, nicks, indentations, holes, solder resist (SR) residues, discoloration, nickel (Ni) leakage, copper (Cu) exposure , protrusions and defects and other specific defects. Therefore, for the substrate determined to be a true defect, the control section 180 may determine one of a circuit defect and a plating defect, and may also determine the types of specific defects corresponding to the circuit defect and the plating defect, respectively.

The control unit 180 may use an algorithm based on deep learning for detecting an abnormal defect occurrence position or the like. The control unit 180 uses a deep learning algorithm, and can be classified into one of about 30 kinds of defects related to the above-mentioned circuit defects and plating defects according to the type of defects.

After that, the control unit 180 may perform defect detection on the substrate determined to be re-inspected. The control unit 180 may adjust the brightness of the illumination 120 corresponding to the area camera 160 in order to detect defects. For example, the control part 180 may adjust the brightness of the lighting 120 in three stages. At this time, the control unit 180 may control the illumination 120 with an illuminance value for inspecting the portion where the circuit is generated, control the illumination 120 with an illuminance value for performing inspection based on defect characteristics, and control the illumination 120 with an illuminance value for inspecting height deviation or in Defects that occur at each layer The lighting value to control the lighting 120. As described above, the control part 180 may control the lighting corresponding to the area camera 160 in three divisions.

The control unit 180 can control the area camera 160 to adjust the brightness of the lighting 120 in three stages to capture three images. The control unit 180 may register the three images acquired by the area camera 160 into one image to determine the defect. The control unit 180 can determine whether the state of the substrate is normal or defective (true defect) based on the image obtained by the registration. Additionally, the area camera 160 may be a color area camera capable of acquiring color images.

The control unit 180 can use the image acquired by the area camera 160 to detect the defects of the substrate again. For example, the control unit 180 can determine, based on the acquired image, that the state of the substrate in which foreign matter, dust, and defects tolerable according to the defect specification are present is normal.

The control unit 180 can use an algorithm based on deep learning for high-speed defect determination and high-speed object classification. The control unit 180 may determine defects using a deep learning algorithm.

As described above, the substrate defect inspection apparatus 100 can be divided into two stages of initial inspection and re-inspection to detect defects of the substrate, thereby enabling automation of the substrate inspection process. Thereby, the board|substrate defect inspection apparatus 100 can automatically inspect the defect of a board|substrate, even if an administrator does not continuously monitor.

The substrate defect inspection apparatus 100 does not require additional equipment or additional inspection depending on the inspector, and since the substrate is inspected using artificial intelligence, the consistency of substrate inspection results can be maintained. In addition, the substrate defect inspection apparatus 100 can improve the yield of products due to the automation of substrate inspection.

FIG. 2 is a diagram showing a cross section of a substrate defect inspection apparatus according to an embodiment.

As shown in FIG. 2 , the substrate defect inspection apparatus 100 may include a moving table composed of guide rails 210 , 220 , 230 , 240 , 250 , 260 and 270 .

The first guide rail 210 may include a stacker 211 on which the substrate to be inspected is located. The first guide rail 210 can move the substrate set on the stacker 211 in the direction of the No. 1 arrow to move it to the conveyance slot 221 located on the second guide rail 220 .

A cleaner 222 for processing the surface of the substrate may be provided on the second guide rail 220 . Around the second guide rail 220, a camera moving structure 223 for capturing an image for inspecting the substrate may be provided. The line scan camera 224 and the adjustment camera 225 may be integrated or arranged in the camera moving structure 223 . At this time, the camera moving structure 223 can move the camera along the X-axis, Y-axis and Z-axis directions. Here, the X-axis, the Y-axis, and the Z-axis are directions orthogonal to each other, and in the drawings, the left-right direction is the X-axis, and the up-down direction is the Y-axis. On the other hand, the depth direction of the drawing is the Z axis. In particular, when the camera moving structure 223 moves in the depth direction, the camera moving structure 223 can perform a function of adjusting the magnification of the camera, so that even fine defects smaller than a predetermined size can be detected by adjusting the magnification.

When the conveying slot 221 provided with the substrate moves in the direction of the 2nd arrow on the second guide rail 220, the line scan camera 224 and the adjustment camera 225 can adjust the position to capture the image of the substrate. Therefore, the first inspection is performed using the image captured on the second guide rail 220 .

After the image capturing of the substrate on the second guide rail 220 is completed, it can move along the first guide rail 210 . At this time, if it is necessary to wait for inspection, the substrate can be set on the buffer 212 located on the first guide rail 210 and wait for the inspection on the third guide rail 230 .

On the third rail 230, the adjustment camera 231 and the area camera 232 can use the moving structure to photograph the substrate. The re-inspection may be performed using the image captured on the third rail 230 . The substrates judged to be normal or defective on the second guide rail 220 can be moved to the fourth guide rail 240 without taking an image on the third guide rail 230 for inspecting the substrate.

The fourth guide rail 240 may include a flipper for flipping the upper and lower surfaces of the substrate. The inverter can invert the substrate in the direction of the 5th arrow and is provided in the transport slot on the fifth guide rail 250 .

A cleaner 251 is provided on the fifth guide rail 250 for wiping the surface of the substrate. When the conveying chute provided with the substrate moves in the direction of the arrow No. 6 on the fifth guide rail 250 , the adjustment camera 252 and the line scan camera 253 can adjust the position to capture the image of the substrate.

The sixth guide rail 260 moves the substrates in the direction of the arrow No. 7, places the substrates determined to be in a normal state on the normal substrate loading portion 261, and places the substrates determined to be in a defective state on the defective substrate loading portion 262, and re-inspects the substrates determined to be in a defective state. The substrates are placed in the re-inspection substrate loading section 263.

The re-inspection substrate can be placed on the transport slot on the seventh rail 270 . The position of the area camera 271 and the adjustment camera 272 can be adjusted to capture images of the substrate while moving the substrate in the direction of the 8th arrow by using the transport slot on the seventh guide rail 270 .

When the inspection on the seventh guide rail 270 is completed, the substrate is moved on the sixth guide rail 260 in the direction of the arrow No. 9, and the substrate for which the defect determination has been completed is placed on the normal substrate loading portion 261 and the defective substrate loading portion 262, and the inspection is performed again. Substrate loading unit 263 .

The substrate defect inspection apparatus 100 can directly inspect the substrate for defects without additional work by the operator 10, and although the substrate defect inspection apparatus 100 in the form of inspecting both sides of the substrate is exemplarily described, only one side of the substrate may be inspected. In this case, the substrate defect inspection apparatus 100 may not include the components corresponding to the arrows 5, 6, 8, and 9.

FIG. 3 is a diagram for explaining a state in which a substrate is photographed using a line scan camera according to an embodiment.

As shown in FIG. 3 , in a, the base plate 321 is provided at the upper end of the conveyance slot 320 on the guide rail 310 .

In b, the transport chute 320 located on the guide rail 310 can be moved around the line scan camera 330 and the adjustment camera 340 for inspection.

In c, d, and e, the line scan camera 330 and the adjustment camera 340 can move along the X-axis, Y-axis, and Z-axis directions and capture images. At this time, the conveyance tank 320 may be moved together.

Secondly, after changing the lighting, you can perform steps f, g, h, and i similar to actions b, c, d, and e to capture other images after adjusting the lighting. When the image capturing is completed, as shown in j, the conveyance tank is returned to the original position, and the substrate can be moved to the next inspection position.

FIG. 4 is a diagram for explaining a state in which a substrate is photographed using an area camera according to an embodiment.

As shown in FIG. 4 , in a, the base plate 421 is provided at the upper end of the conveyance slot 420 on the guide rail 410 .

In b, the transport slot 420 located on the guide rail 410 can be moved around the line scan camera 430 and the adjustment camera 440 for inspection.

In c, the line scan camera 430 and the adjustment camera 440 can move along the X-axis, Y-axis and Z-axis directions and capture images. At this time, the conveyance tank 420 may be moved together.

After changing the illumination, in d and e, the camera 440 can be adjusted to move along the X-axis, Y-axis, and Z-axis directions to capture images. At this time, the conveyance tank 420 may be moved together.

After the image capturing is completed, as shown in f, after the conveyance tank 420 returns to the original position, the substrate can be moved to the next inspection position.

FIG. 5 is a flowchart for explaining a substrate defect inspection operation performed by the substrate defect inspection apparatus according to the embodiment.

As shown in FIG. 5 , the substrate defect inspection apparatus 100 may control illumination and capture images using a line scan camera ( S510 ). At this time, the substrate defect inspection apparatus 100 can distinguish and photograph the plating layer portion and the solder resist layer portion by controlling the illumination.

The substrate defect inspection apparatus 100 can determine the defect of the substrate by using the image obtained by imaging. The substrate defect inspection apparatus 100 may determine the state of the substrate as normal, defective and re-inspected (S520). At this time, the substrate defect inspection apparatus 100 can use the defect image data obtained by deep learning stored in the database, and can determine the defect by comparing the captured image with the corresponding defect image data.

The substrate defect inspection apparatus 100 determines whether the substrate needs to be re-inspected through defect determination (S530).

As a result of the confirmation in step S530, the substrate is judged to be normal or defective through the defect judgment, so re-inspection is not required, then the substrate defect inspection apparatus 100 proceeds to step S560.

As a result of the confirmation in step S530, that the substrate needs to be re-inspected based on the defect determination, the substrate defect inspection apparatus 100 proceeds to step S540.

When re-inspection is required based on the defect determination, the substrate defect inspection apparatus 100 may control illumination and capture an image using an area camera ( S540 ). At this time, the substrate defect inspection apparatus 100 acquires the coordinate value of the part that needs to be re-inspected, and the acquired coordinate value can be used to determine the defect of the substrate to be re-inspected.

The substrate defect inspection apparatus 100 may use the image captured by the area camera to determine the defect of the object substrate to be re-inspected (S550). At this time, the substrate defect inspection apparatus 100 may finally determine that the re-inspected object substrate is normal or defective. At this time, the substrate defect inspection apparatus 100 may use the storage There are defect image data obtained by deep learning in the database, and defects can be determined by comparing the captured image with the corresponding defect image data.

The substrate defect inspection apparatus 100 may output the defect determination result for the substrate (S560). The substrate defect inspection apparatus 100 can detect whether the substrate of the inspection object is defective, and can also detect information about the type of the defect.

The substrate defect inspection apparatus 100 may learn the defect image data stored in the database through deep learning (S570).

The substrate defect inspection apparatus 100 determines whether or not the inspection is to be terminated (S580). The determination result in step S580 is that the inspection is terminated, and the operation of the substrate defect inspection apparatus 100 is terminated. However, if the result of determination in step S580 is that the inspection is not to be terminated, the substrate defect inspection apparatus 100 proceeds to step S510 to inspect the next substrate for defects.

FIG. 6 is a flowchart for explaining an operation of determining a defect using an image captured by a line scan camera according to an embodiment.

As shown in FIG. 6 , the substrate defect inspection apparatus 100 may acquire the normal images stored in the database ( S611 ). Here, the normal image is an image corresponding to a normal substrate without defects, and may also be referred to as a master image. At this time, the substrate defect inspection apparatus 100 can simultaneously acquire parameters for inspecting defects from the database. On the one hand, the substrate defect inspection apparatus 100 can also acquire normal images or parameters before the images are captured by the line scan camera.

The substrate defect inspection apparatus 100 may convert the image captured by the line scan camera into an image of the same coordinate system as the normal image ( S613 ).

The substrate defect inspection apparatus 100 may divide the inspection section area from the image captured by the line scan camera (S615). The substrate defect inspection apparatus 100 divides the image captured by the line scan camera into a plurality of sections for inspection.

The substrate defect inspection apparatus 100 may generate a difference image from the image captured by the line scan camera based on the normal image ( S617 ).

The substrate defect inspection apparatus 100 may register the two images acquired by controlling the illumination (S619).

The substrate defect inspection apparatus 100 performs defect inspection on the substrate using the registered image (S621). The substrate defect inspection apparatus 100 may use artificial intelligence based on deep learning to inspect the defects of the substrate, and may also use the difference image acquired in step S617 at the same time.

The substrate defect inspection apparatus 100 can detect a suspected defect region (S623). For example, the substrate defect inspection apparatus 100 may crop (crop) a suspected defective area, extract only information of the suspected defective part, or may remove other parts except the suspected defective part.

The substrate defect inspection apparatus 100 may re-inspect the area of the suspected defect for defects ( S625 ). The substrate defect inspection apparatus 100 may re-inspect the substrate for defects using artificial intelligence based on deep learning. The first artificial intelligence in step S621 and the second artificial intelligence in step S625 may be composed of mutually different algorithms, the first artificial intelligence may have a function specially suitable for detection, and the second artificial intelligence may have a function specially suitable for judgment .

The substrate defect inspection apparatus 100 determines the defect of the substrate as one of normal, defective, and re-inspection, and proceeds to step S530 (S627).

7 is a flowchart for explaining an operation of determining a defect using an image captured by an area camera according to an embodiment.

As shown in FIG. 7 , the substrate defect inspection apparatus 100 may acquire the normal images stored in the database ( S611 ). Here, the normal image is an image corresponding to a normal substrate without defects. At this time, the substrate defect inspection apparatus 100 can simultaneously acquire parameters for inspecting defects from the database. On the one hand, the substrate defect inspection apparatus 100 may also acquire normal images or parameters before the images are captured by the area scanning camera.

The substrate defect inspection apparatus 100 can detect a defective portion (S713). For example, the substrate defect inspection apparatus 100 may crop (crop) a suspected defective area, extract only information of the suspected defective part, or may remove other parts except the suspected defective part.

The substrate defect inspection apparatus 100 may convert the image captured by the area camera into an image of the same coordinate system as the normal image (S715).

The substrate defect inspection apparatus 100 may generate a difference image from the image captured by the area camera based on the normal image ( S717 ).

The substrate defect inspection apparatus 100 may register the three video images captured by controlling the illumination (S719).

The substrate defect inspection apparatus 100 performs defect inspection on the substrate using the registered image (S721). The substrate defect inspection apparatus 100 may use artificial intelligence based on deep learning to inspect the defects of the substrate, and may also use the difference image acquired in step S717 at the same time. Here, the substrate defect inspection apparatus 100 may inspect defects using artificial intelligence used in step S621 in FIG. 6 .

The substrate defect inspection apparatus 100 may determine a defect based on the defect inspection result (S723). The substrate defect inspection apparatus 100 can determine the defect as one of normal, defect, and re-inspection.

The substrate defect inspection apparatus 100 may confirm whether the substrate is determined to be re-inspected based on the defect determination result ( S725 ).

If the result of determination in step S725 is that it is not determined to be re-inspection, the substrate defect inspection apparatus 100 may proceed to step S560 to output the inspection result of the substrate.

If the result of the determination in step S725 is that it is determined to be re-inspection, the substrate defect inspection apparatus 100 may proceed to step S727.

The substrate defect inspection apparatus 100 can classify and filter the types of defects using the parameters for setting inspection results (S727).

The substrate defect inspection apparatus 100 may confirm whether there is a defect through measurement and perform defect judgment (S729). The substrate defect inspection apparatus 100 may perform step S560 to output the determination result.

The term "... section" used in this embodiment refers to software or a hardware element such as an FPGA (field programmable gate array) or an ASIC, and the "... section" performs certain functions. However, "..." is not limited to software or hardware. The "section" may be configured in an addressable storage medium, or may cause one or more processors to operate. Thus, as an example, "..." includes elements such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subprograms, code segments, drivers, firmware, Microcode, circuits, data, databases, data structures, tables, arrays, and variables.

The functions provided within the elements and "sections" may be combined into a smaller number of elements and "sections", or separate from other elements and "sections" provided separately.

In addition, components and "sections" that enable one or more CPUs within a device or secure multimedia card to operate.

In addition, the substrate defect inspection method according to the embodiment of the present invention can be implemented by means of a computer program (or a computer program product) including computer-executable instructions. The computer program includes programmable machine instructions processable by a processor and can be implemented in a High-level Programming Language, an Object-oriented Programming Language, an assembly language or a machine language . In addition, the computer program can also be recorded on a tangible computer-readable recording medium (eg, a memory, a hard disk, a magnetic/optical medium, or an SSD (Solid-State Drive), etc.).

Therefore, the substrate defect inspection method according to an embodiment of the present invention can be implemented by executing the above computer program by a computing device. The computing device may include at least a portion of a processor, memory, storage, a high-speed interface connected to the memory and high-speed expansion ports, and a low-speed interface connected to a low-speed bus and the storage device. These components are connected to each other with various bus bars, and can be mounted on the same motherboard or mounted on the same motherboard in other suitable ways.

Here, the processor is capable of processing instructions in the computing device, such instructions may be, for example, to display graphic information for providing a GUI (Graphic User Interface) to an external input or output device such as a display connected to a high-speed interface, storing Instructions in memory or storage devices. As another example, multiple processors and/or multiple buses may be used in combination with multiple memories and memory forms as appropriate. In addition, the processor may be implemented by a chip set consisting of a chip including a separate plurality of analog and/or digital word processors.

Additionally, memory is used within computing devices to store information. As an example, memory may be composed of volatile memory cells or a collection thereof. As another example, the memory may be composed of non-volatile storage cells or a collection thereof. In addition, the memory may also be other types of computer-readable media, such as magnetic disks or optical disks.

The storage device can provide a large capacity storage space for the computing device. The storage device may be a computer-readable medium or a structure including such a medium, and may also include, for example, a device in a SAN (Storage Area Network) or other structures, which may be a floppy disk device, a hard disk device, an optical disk device or a tape device, a fast Flash memory, other semiconductor storage devices like it, or device adjustments.

The above description of the present invention is only an example, and those of ordinary skill in the art to which the present invention pertains can understand that the present invention can be easily transformed into other specific forms without changing the technical spirit or basic features of the present invention . Therefore, it should be understood that the above-described embodiments are only examples in all respects and should not be regarded as limiting. For example, elements described as a single form can be implemented in a discrete form, and likewise elements described as a discrete form can also be implemented in a combined form.

What is disclosed in this case is a preferred embodiment, and any partial changes or modifications that originate from the technical ideas of this case and are easily inferred by those who are familiar with the art are within the scope of the patent right of this case.

To sum up, in terms of purpose, means and efficacy, this case is showing its technical characteristics that are completely different from those of the prior art, and its first invention is suitable for practical use, and it also meets the requirements of a patent for invention. Granting a patent as soon as possible will benefit the society, and it will be a real sense of virtue.

100: Substrate defect inspection device

110: Mobile Workbench

120: Lighting

130:Database

140: Adjusting the camera

150: Line scan camera

160: Area Camera

170: Input and output section

180: Control Department

Claims (11)

A substrate defect inspection device, comprising: a moving table for moving a substrate to an inspection position; an illuminator set to acquire a photographed image to irradiate prescribed light onto the substrate; at least one line scan a camera, which is set to photograph the substrate in units of prescribed lines; at least one area camera, which is set to photograph the substrate in units of prescribed areas; a database, which stores images for detecting defects of the substrate; and a control unit that uses the moving table to move the position of the substrate, and controls the illumination to obtain an image obtained by photographing a coating portion of the substrate and an image obtained by photographing a solder resist portion by the line scan camera , based on the acquired images, determine the state of the substrate as one of normal, defective and re-inspection, thereby detecting the initial defect, and then adjust the illumination for the substrate determined to be re-inspected to obtain the The camera shoots a substrate image obtained by the substrate, and based on the acquired substrate image, the state of the substrate is determined as one of normal and defective, thereby detecting a second defect; wherein, the control unit is determined to be re-inspected. The substrate controls the illumination multiple times, and controls the illumination multiple times to photograph the substrate multiple times to acquire a plurality of images of the substrate, and performs registration on the images of the substrate to detect the re-defect, Thereby, the state of the substrate is judged to be normal or defective. The substrate defect inspection apparatus according to claim 1, wherein, Also includes at least one adjustment camera, the at least one adjustment camera is located at a position within a prescribed distance from the line scan camera and the area camera, and captures the image of the substrate used for adjustment of the position, the control part uses the adjustment camera. image, and adjust the position of at least one of the line scan camera, the area camera, and the substrate. The substrate defect inspection apparatus according to claim 1, wherein the control unit uses a defect image data stored in the database and obtained through deep learning in order to inspect the primary defect and the secondary defect. The substrate defect inspection apparatus according to claim 3, wherein the control unit learns the defect image data using the image of the substrate determined to be defective when the first defect or the second defect is detected. A substrate defect inspection method, executed by a substrate defect inspection device, comprises: by controlling an illumination for irradiating light to a substrate, acquiring an image obtained by photographing a coating portion of a substrate by a line scanning camera, and photographing a solder mask The step of obtaining an image of the layer part; based on the obtained images, the state of the substrate is judged as one of normal, defective and re-inspection, thereby detecting the initial defect; The substrate adjusts the illumination, and acquires a substrate image obtained by photographing the substrate by an area camera; based on the acquired substrate image, the state of the substrate is determined as one of normal and defective, thereby detecting a second defect wherein, the step of detecting the re-defect includes controlling the illumination in multiple times for the substrate determined to be re-inspected, and photographing the substrate in multiple times by controlling the illumination in multiple times, In order to acquire a plurality of images of the substrate, and register the images of the substrate to detect the second defect, the state of the substrate is judged to be normal or defective. The substrate defect inspection method according to claim 5, wherein the steps of acquiring the image of the coating portion obtained by photographing the substrate and the image obtained by photographing the solder mask portion include: photographing and obtaining the image for an adjustment position The step of adjusting the position of at least one of the line scan camera and the substrate using the image of the substrate and using the captured image. The substrate defect inspection method according to claim 5, wherein the step of acquiring an image of the substrate obtained by photographing the substrate comprises: photographing an image of the substrate for adjusting a position, and using the photographed image, The step of adjusting the position of at least one of the area camera and the substrate. The substrate defect inspection method according to claim 5, wherein in the step of detecting the first defect and the step of detecting the second defect, a defect image data stored in a database and obtained through deep learning is used. The substrate defect inspection method according to claim 8, wherein, after the step of detecting the first defect and the step of detecting the second defect, further comprising: a step of learning the defect image data using the image of the substrate determined to be defective . A computer-readable recording medium for recording a program capable of executing the method described in any one of claims 5 to 9. A computer program product, which is stored in a recording medium and executed by a substrate defect inspection apparatus, is used to execute the method according to any one of claims 5 to 9.

Images