KR102252592B1 - Apparatus and method for inspecting substrate defect - Google Patents

Abstract

A substrate defect inspection apparatus according to an embodiment of the present invention includes a moving worktable for moving a substrate to a position for inspection, a lighting for irradiating a predetermined light onto a substrate to obtain a photographed image, and at least one for photographing the substrate in units of a predetermined line. The position of the substrate is moved using one line scan camera, at least one area camera for photographing the substrate in a predetermined area unit, a database storing an image for detecting defects from the substrate, and the moving worktable, By controlling the illumination, an image of a plated portion of the substrate and an image of a solder resist portion are acquired from the line scan camera, and the state of the substrate is determined as one of normal, defective, and re-inspection from the acquired image. The first defect is detected, the illumination is controlled for the substrate determined by the re-inspection to obtain a substrate image photographed with an area camera, and the state of the substrate as either normal or defective from the obtained substrate image. And a control unit for determining the second defect and detecting the second defect.

Description

Board defect inspection apparatus and method {APPARATUS AND METHOD FOR INSPECTING SUBSTRATE DEFECT}

Embodiments disclosed herein relate to an apparatus and method for inspecting a defect of a substrate. More specifically, the present invention relates to an apparatus and method for inspecting defects in substrates that do not require reconfirmation of defects in substrates such as printed circuit boards.

Products such as printed circuit boards (PCBs) are subject to various types of defects for shipment, so various types of inspections are performed. Relatedly, as described in Korean Patent Publication No. 10-2005-0103525, which is a prior art document, a PCB inspection and selection device for inspecting by preventing excessive contact between the pattern formed on the lower surface of the PCB and probe pins before shipment is described.

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

Since the rule-based inspection is performed by a rule determined by the inspector, even foreign matter or contamination that is not defective is detected as defective, and errors of normal specifications are recognized as defective by excessively setting rules to increase the probability of detecting defects. It is also detected. In order to prevent such a situation, there is a problem of additionally identifying whether the state of the PCB is normal or defective by using additional equipment for PCB inspection.

In addition, since it is not possible to maintain a certain level of inspection standards for each operator for PCB inspection, there is a problem in that sensitivity defects and the like occur, resulting in lower consistency of product inspection results, and lowering the yield of PCB manufacturing.

Therefore, there is a need for a technique for solving the above-described problem.

On the other hand, the above-described background technology is technical information that the inventor possessed for derivation of the present invention or acquired during the derivation process of the present invention, and is not necessarily a known technology disclosed to the general public prior to filing the present invention. .

The embodiments disclosed in the present specification aim to provide an apparatus and method for inspecting substrate defects that automate an inspection process by an operator.

The embodiments disclosed in the present specification aim to provide an apparatus and method for inspecting substrate defects that do not require additional equipment or additional inspection by an inspector.

An object of the embodiments disclosed in the present specification is to provide a substrate defect inspection apparatus and method capable of maintaining consistency of a substrate inspection result.

The embodiments disclosed in the present specification aim to provide a substrate defect inspection apparatus and method capable of improving the yield of a product due to automation of the substrate inspection.

As a technical means for achieving the above-described technical problem, according to an embodiment, a substrate defect inspection apparatus includes a moving worktable that moves a substrate to a position for inspection, and irradiates a predetermined light onto the substrate to obtain a photographed image. Illumination, at least one line scan camera that photographs the substrate in a predetermined line unit, at least one area camera that photographs the substrate in a predetermined area unit, a database storing an image for detecting defects from the substrate, and the movement Move the position of the substrate using a worktable, and control the illumination to obtain an image of the plated portion of the substrate and an image of the solder resist portion from the line scan camera, and normal from the obtained image, The first defect is detected by determining the state of the substrate as one of defect and re-inspection, and the illumination is controlled for the substrate determined by the re-inspection to obtain a substrate image photographed with an area camera, and the obtained And a controller configured to detect a second defect by determining a state of the substrate as one of normal and defective from the substrate image.

According to another embodiment, the substrate defect inspection method performed by the substrate defect inspection apparatus includes an image of a plated portion of a substrate and an image of a solder resist portion by controlling illumination to irradiate light onto the substrate. Acquiring the first defect by determining the state of the substrate as one of normal, defective, and re-inspection from the acquired image, controlling illumination for the substrate determined by re-inspection, and photographing the substrate with an area camera Acquiring a substrate image, and determining a state of the substrate as one of normal and defective from the obtained substrate image to detect a second defect.

According to another embodiment, a computer-readable recording medium in which a program for performing a substrate defect inspection method is recorded, wherein the substrate defect inspection method comprises: a substrate defect inspection method performed by a substrate defect inspection apparatus, wherein light is applied to a substrate. Controlling the irradiated light to obtain an image of the plated portion of the substrate and an image of the solder resist portion by a line scan camera, and determine the state of the substrate as one of normal, defective, and re-inspection from the obtained image. Detecting the first defect, controlling illumination for the substrate determined by re-inspection to obtain a substrate image photographed with an area camera, and determining the state of the substrate as either normal or defective from the obtained substrate image And detecting the second defect.

According to another embodiment, a computer program performed by a substrate defect inspection apparatus and stored in a medium to perform a substrate defect inspection method, wherein the substrate defect inspection method is a substrate defect inspection method performed by the substrate defect inspection apparatus. Silver, the step of acquiring an image of a plated portion of the substrate and an image of a solder resist portion with a line scan camera by controlling illumination to irradiate light on the substrate, and the obtained image is one of normal, defective, and re-inspection. Determining the state of the substrate to detect the first defect, controlling the illumination of the substrate determined by re-inspection to obtain a substrate image photographed with an area camera, and one of normal and defective from the obtained substrate image. And determining the state of the substrate to detect a second defect.

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

According to any one of the problem solving means of the present invention, it is possible to provide an apparatus and method for inspecting substrate defects that do not require additional equipment or additional inspection by an inspector.

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

According to any one of the problem solving means of the present invention, an object of the present invention is to provide a substrate defect inspection apparatus and method capable of improving the yield of a product due to automation of the substrate inspection.

The effects that can be obtained in the present invention are not limited to the above-mentioned effects, and other effects not mentioned can be clearly understood by those of ordinary skill in the art from the following description. will be.

1 is a block diagram illustrating an apparatus for inspecting a substrate defect according to an exemplary embodiment.
2 is a diagram illustrating a cross section of a substrate defect inspection apparatus according to an exemplary embodiment.
3 is a diagram for describing a photographing of a substrate using a line scan camera according to an exemplary embodiment.
4 is a diagram for describing a photographing of a substrate using an area camera according to an exemplary embodiment.
5 is a flowchart illustrating a substrate defect inspection operation performed by the substrate defect inspection apparatus according to an exemplary embodiment.
6 is a flowchart illustrating an operation of determining a defect using an image captured by a line scan camera according to an exemplary embodiment.
7 is a flowchart illustrating an operation of determining a defect using an image captured by an area camera according to an exemplary embodiment.

Hereinafter, various embodiments will be described in detail with reference to the accompanying drawings. The embodiments described below may be modified and implemented in various different forms. In order to more clearly describe the features of the embodiments, detailed descriptions of matters widely known to those of ordinary skill in the art to which the following embodiments pertain are omitted. In addition, parts not related to the description of the embodiments are omitted in the drawings, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a configuration is said to be "connected" with another configuration, this includes not only a case of being'directly connected' but also a case of being'connected with another configuration in between'. In addition, when a certain configuration "includes" a certain configuration, it means that other configurations may be further included rather than excluding other configurations unless otherwise specified.

Hereinafter, exemplary embodiments will be described in detail with reference to the accompanying drawings.

However, before describing this, the meaning of the terms used below is first defined.

A'board' is a board in which the electrical wiring connecting circuit components is reproduced in the form of an electrical conductor on an insulator based on the circuit design. For example, a printed circuit board (hereinafter referred to as'PCB') ), may include a flexible printed circuit board (FPCB). The substrate refers to an object or object to be inspected by a substrate defect inspection apparatus described later. Therefore, the substrate is a display panel, a PCB panel, a liquid crystal display (LCD), organic light emitting diodes (OLED), solar panels, fabrics, metal, etc. that can be inspected by acquiring an image. Images can be acquired and replaced with all inspectable products.

1 is a block diagram illustrating an apparatus for inspecting a substrate defect according to an exemplary embodiment.

As shown in FIG. 1, the substrate defect inspection apparatus 100 includes a mobile worktable 110, a lighting 120, a database 130, an alignment camera 140, a line scan camera 150, and an area camera 160. , An input/output unit 170, and a control unit 180 may be included.

The moving worktable 110 moves the substrate to a position for inspection. The mobile worktable 110 may include a boat on which a substrate for inspection is mounted, and a rail through which the boat is coupled and moved. In addition, a strip for fixing the substrate may be positioned on the top of the boat.

The mobile worktable 110 may include a flipper or the like to reverse the substrate when inspecting both sides of the substrate as necessary. The mobile worktable 110 may include a storage tray for sorting and storing the inspected substrates.

One or more lights 120 may be located around a camera that acquires an image of a substrate for inspection, for example, a line scan camera 150 or an area camera 160, and is located on a substrate located on a boat. Lights can be illuminated. Accordingly, when the number of line scan cameras 150 and area cameras 160 for inspection increases, the number of lights 120 may also increase. The lighting 120 may adjust the brightness through control of the lighting value, and may generate various images by adjusting the brightness. When the substrate is photographed, two or more lights 120 may be used at the same time to acquire one image. When the illumination 120 corresponds to the area camera 160, the illumination 120 may have a predetermined illumination value (or predetermined brightness) capable of classification according to the defect characteristics of the substrate.

Various types of data such as files or programs may be installed and stored in the database 130. Data stored in the database 130 may be accessed and used by the controller 180 to be described later, or new data may be stored by the controller 180. In addition, the database 130 may store programs that can be executed by the controller 180.

The database 130 may store data on a defective substrate. For example, the database 130 may store an image of a defective substrate for determining a defective substrate. In this case, the defective substrate image stored in the database 130 is data learned using artificial intelligence, and may be used for inspection of the defective substrate.

The database 130 may store a file for inspection of a defective substrate. The database 130 may store a program capable of classifying defective substrates and detecting even types of defects of the classified defective substrates. In particular, the database 130 may store a computer program implementing artificial intelligence (AI) that learns defective image data by performing deep learning for inspection of defective substrates, and uses the learned defective image data to detect defective images. have.

The alignment camera 140 photographs a substrate to be inspected. The alignment camera 140 may provide the captured image to the controller 180. The alignment camera 140 may be positioned within a predetermined distance with respect to each of the line scan camera 150 and the area camera 160. Through this, the alignment camera 140 captures an image required for alignment of the image captured by the line scan camera 150 or the area camera 160 for inspection.

The line scan camera 150 is a camera that photographs a substrate in units of lines of a predetermined length using a line-shaped image sensor. The line scan camera 150 may provide photographing data to the controller 180 to determine a defect of the photographed substrate. Since the line scan camera 150 photographs an image in the form of a line, it is possible to photograph even when the substrate is moving.

The area camera 160 is a camera that photographs a substrate in units of a predetermined range. The area camera 160 may photograph a substrate, and may provide photographing data to the controller 180 to determine a defect of the photographed substrate.

The alignment camera 140, the line scan camera 150, and the area camera 160 are attached to a fixed structure of a part of the substrate defect inspection apparatus 100 and move in the X-axis, Y-axis and Z-axis directions perpendicular to each other. It may include or be attached to a motor or the like. For example, when the X-axis is a horizontal direction, the Y-axis is a vertical direction, and the Z-axis may be a depth direction to the substrate (ie, a direction closer to or away from the substrate). Here, the X-axis and the Y-axis may be in a direction parallel to the ground, and the Z-axis may be a direction perpendicular to the ground. The alignment camera 140, the line scan camera 150, and the area camera 160 adjust the position of the camera based on three axes, and may take an image of a substrate for inspection.

Through this, each of the alignment camera 140, the line scan camera 150, and the area camera 160 may be set to a predetermined magnification for photographing an image of the substrate under the control of the controller 180, for example , The magnification may be set to detect even minute defects having a size of 5 micrometers (um) to 15 μm.

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

Specifically, the input unit may include devices capable of receiving various types of user input, such as a keyboard, a physical button, a touch screen, a camera, or a microphone. In addition, the output unit may include a display panel or a speaker. However, the present invention is not limited thereto, and the input/output unit 170 may include a component supporting various input/output.

The controller 180 controls the overall operation of the substrate defect inspection apparatus 100 and may include a processor such as a CPU or the like. The controller 180 may control other components included in the substrate defect inspection apparatus 100 to perform an operation corresponding to a user input received through the input/output unit 170.

The controller 180 may control the moving worktable 110 to move the substrate inserted into the substrate defect inspection apparatus 100 to each position for inspection.

The controller 180 may control the lighting 120 corresponding to the line scan camera 150 to detect a defect. For example, the controller 180 may adjust the brightness of the lighting 120 in two steps. In this case, the controller 180 may control the lighting 120 as an illumination value for inspection of a portion where a circuit is generated, and control the illumination 120 as an illumination value for inspection of a portion on the plating side. In this way, the controller 180 may control the lighting 120 corresponding to the line scan camera 150 twice.

The controller 180 adjusts the brightness of the illumination 120 in two steps to capture an image of a plated portion of the substrate and an image of a portion where a circuit is generated (for example, a solder-resist (SR) portion). The line scan camera 150 may be controlled so as to be performed. Here, the image of the plating portion and the solder resist portion is a brightness image. Through this, the controller 180 may match the image of the plating portion and the image of the solder resist portion, and determine the state of the substrate as one of normal, defective (intrinsic defect), and re-inspection of the matched image. . Also, the line scan camera 150 may be a color line scan camera capable of acquiring a color image.

Since the resolution of the line scan camera 150 is lower than the resolution of the area camera 160, an accurate inspection may be required for defects of less than a predetermined size (length or area) set in advance. In this way, the controller 180 may determine a defect less than a predetermined size as a re-inspection. In addition, the control unit 180 may determine a defect determined to be necessary to more accurately classify the defect determination by re-inspection.

The controller 180 may first detect a defect in the substrate by using the image acquired through the line scan camera 150. The control unit 180 may determine the type of the defect for the substrate determined to be defective, that is, an intrinsic defect. For example, it can be determined by dividing into circuit defects and plating defects. Here, circuit defects include open circuit, short circuit, upper scratch, lower scratch, foreign matter, metallic foreign matter, solder resist (SR) peeling, Automated Optical Insepection (AOI) defect, unnicknamed, SR residue, crack, discoloration. , Lift, and speckle. In addition, defects in plating include detailed defects such as plating open, plating short, plating clumping, scratches, foreign matter, stamping, pressing, holes, SR residues, discoloration, nickel (Ni) visible, copper (Cu) exposure, protrusions, and defects. Can include. Accordingly, the controller 180 can determine one of a circuit defect and a plating defect for the substrate determined as an intrinsic defect, and determine a type of a detailed defect corresponding to each of the circuit defect and the plating defect.

The controller 180 may use a deep learning-based algorithm that detects the location of a defect that occurs atypically. The controller 180 may classify into about 30 types of defects for the above-described circuit defects and plating defects according to the type of defects using a deep learning algorithm.

Thereafter, the controller 180 may detect a defect for the substrate determined to be retested. The controller 180 may adjust the brightness of the illumination 120 corresponding to the area camera 160 to detect a defect. For example, the controller 180 may adjust the brightness of the lighting 120 in three steps. At this time, the controller 180 controls the lighting 120 as an illumination value for inspection of the part where the circuit is generated, controls the illumination 120 as an illumination value for inspection according to the defect characteristics, and controls the height deviation or layer by layer. The lighting 120 may be controlled as an illumination value for inspection of a defect that occurs. In this way, the controller 180 may control the lighting corresponding to the area camera 160 three times.

The controller 180 may control the area camera 160 to capture three images by adjusting the brightness of the lighting 120 in three steps. The controller 180 may determine a defect by matching the three images acquired from the area camera 160 into one image. The controller 180 may determine the state of the substrate as either normal or defective (intrinsic defect) by using the matched image. Also, the area camera 160 may be a color area camera capable of acquiring a color image.

The controller 180 may secondarily detect a defect in the substrate using the image acquired using the area camera 160. For example, the controller 180 may determine a state of a corresponding substrate in which foreign matter, dust, and defects that may be acceptable as defective specifications in the acquired image are present.

The controller 180 may use a deep learning-based algorithm for high-speed defect determination and high-speed object classification. The controller 180 may determine a defect using a deep learning algorithm.

In this way, the substrate defect inspection apparatus 100 may automate a substrate inspection process by detecting a defect of a substrate in two steps classified into a primary inspection and a secondary inspection. Through this, the substrate defect inspection apparatus 100 can automatically inspect the defect of the substrate without continuous monitoring by the manager.

The substrate defect inspection apparatus 100 does not require additional equipment or inspection by the inspector, and can maintain the consistency of the inspection results of the substrate by inspecting the substrate using artificial intelligence. In addition, the substrate defect inspection apparatus 100 may improve a product yield due to automation of the substrate inspection.

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

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

The first rail 210 may include a stacker 211 on which a substrate waiting to be inspected is located. The first rail 210 may move the substrate located on the stacker 211 in the direction of arrow 1 to be positioned on the boat 221 located on the second rail 220.

A cleaner 222 for treating the surface of the substrate may be positioned on the second rail 220. A camera moving structure 223 for photographing an image for inspection of a substrate may be positioned around the second rail 220. A line scan camera 224 and an alignment camera 225 may be coupled or attached to the camera moving structure 223. In this case, the camera moving structure 223 may move the camera in the X-axis, Y-axis, and Z-axis directions. Here, the X-axis, Y-axis, and Z-axis are directions orthogonal to each other, the left-right direction is the X-axis, and the vertical direction is the Y-axis. On the other hand, in the drawing, the depth direction is the Z axis. In particular, the camera moving structure 223 may function to adjust the magnification of the camera when it is moved in the depth direction, and thus even minute defects less than a predetermined size can be detected through the adjustment of the magnification.

When the boat 221 on which the substrate is located on the second rail 220 moves in the direction of arrow 2, the line scan camera 224 and the alignment camera 225 adjust the position and take an image of the substrate. Accordingly, the first inspection can be performed using the image captured on the second rail 220.

When the image capturing of the substrate is completed on the second rail 220, it can be moved through the first rail 210. In this case, when it is necessary to wait for the inspection, the substrate may be placed on the buffer 212 located on the first rail 210 to wait for the inspection on the third rail 230.

On the third rail 230, an alignment camera 231 and an area camera 232 may photograph a substrate using a moving structure. The secondary inspection may be performed using the image captured on the third rail 230. For the substrate determined as normal or defective in the second rail 220, an image for inspection of the substrate may not be photographed on the third rail 230, but may be moved to the fourth rail 240.

The fourth rail 240 may include a flipper that reverses the front and rear surfaces of the substrate. The flipper may be positioned on the boat on the fifth rail 250 by turning the substrate in the direction of arrow 5.

A cleaner 251 is positioned on the fifth rail 250 to clean the surface of the substrate. When the boat on which the substrate is located on the fifth rail 250 moves in the direction of arrow 6, the alignment camera 252 and the line scan camera 253 adjust the position and take an image of the substrate.

The sixth rail 260 places the substrate determined to be in a normal state on the normal substrate loading unit 261 while moving the substrate in the direction of the arrow number 7, and places the substrate determined as a defective state on the defective substrate loading unit 262. And the re-inspection determined substrate may be placed on the re-inspection substrate mounting portion 263.

The retest substrate may be positioned on the boat on the seventh rail 270. While moving the substrate in the direction of arrow 8 using the boat of the seventh rail 270, the area camera 271 and the alignment camera 272 may adjust the position and take an image of the substrate.

When the inspection is completed on the seventh rail 270, the substrate is moved in the direction of the ninth arrow on the sixth rail 260, and the defective substrate is placed in the normal substrate loading section 261 and the defective substrate loading section. (262), it can be located in the re-inspection substrate mounting portion 263.

The substrate defect inspection apparatus 100 can directly inspect the defect of the substrate without a separate operation by the operator 10, and the substrate defect inspection apparatus 100 in the form of inspecting both sides of the substrate is illustratively described. , It may be implemented to inspect only one side of the substrate. In this case, the substrate defect inspection apparatus 100 may not include components corresponding to arrows 5, 6, 8, and 9.

3 is a diagram for describing a photographing of a substrate using a line scan camera according to an exemplary embodiment.

As shown in FIG. 3, in (a), a substrate 321 is positioned on the top of the boat 320 located on the rail 310.

In (b), the boat 320 located on the rail 310 may be moved to the vicinity where the line scan camera 330 and the alignment camera 340 are located for inspection.

In (c), (d), and (e), the line scan camera 330 and the alignment camera 340 may capture an image while moving in the X-axis, Y-axis, and Z-axis directions. At this time, the boat 320 may also move together.

Next, after changing the lighting, perform steps (f), (g), (h), and (i) which are the same operations as in (b), (c), (d), and (e). Other adjusted videos can be taken. When image capturing is completed, the boat can return to its original position and move the substrate to the next inspection position as in (j).

4 is a diagram for describing a photographing of a substrate using an area camera according to an exemplary embodiment.

As shown in FIG. 4, in (a), the substrate 421 is positioned on the top of the boat 420 located on the rail 410.

In (b), the boat 420 located on the rail 410 may move to the vicinity where the line scan camera 430 and the alignment camera 440 are located for inspection.

In (c), the line scan camera 430 and the alignment camera 440 may capture an image while moving in the X-axis, Y-axis, and Z-axis directions. At this time, the boat 420 may also move together.

After changing the lighting, in (d) and (e), the alignment camera 440 may take an image while moving in the X-axis, Y-axis, and Z-axis directions. At this time, the boat 420 may also move together.

When the image capturing is completed, as in (f), the boat 420 may return to its original position and move the substrate to the next inspection position.

5 is a flowchart illustrating a substrate defect inspection operation performed by the substrate defect inspection apparatus according to an exemplary embodiment.

As shown in FIG. 5, the substrate defect inspection apparatus 100 may control lighting to capture an image with a line scan camera (S510). In this case, the substrate defect inspection apparatus 100 may control lighting to separate the plated portion and the solder resist portion for photographing.

The substrate defect inspection apparatus 100 may determine a defect of the substrate using the photographed image. The substrate defect inspection apparatus 100 may determine the state of the substrate as normal, defective, and re-inspection (S520). In this case, the substrate defect inspection apparatus 100 may use deep-learned defective image data stored in the database, and may determine a defect by comparing the captured image with the corresponding defective image data.

The substrate defect inspection apparatus 100 checks whether a re-inspection of the corresponding substrate is necessary according to the defect determination (S530).

As a result of the check in step S530, if the corresponding substrate is determined to be normal or defective according to the determination of defects and retesting is not necessary, the substrate defect inspection apparatus 100 proceeds to step S560.

As a result of the confirmation in step S530, if re-inspection of the corresponding substrate is required according to the determination of the defect, the substrate defect inspection apparatus 100 proceeds to step S540.

The substrate defect inspection apparatus 100 may control lighting to take an image with an area camera when re-inspection according to the defect determination is required (S540). In this case, the substrate defect inspection apparatus 100 may obtain a coordinate value for a portion requiring re-inspection, and use the obtained coordinate value to determine a defect of a substrate to be re-inspected.

The substrate defect inspection apparatus 100 may determine a defect of a substrate to be re-inspected using an image photographed by an area camera (S550). In this case, the substrate defect inspection apparatus 100 may finally determine the substrate to be re-inspected as normal or defective. In this case, the substrate defect inspection apparatus 100 may use deep-learned defective image data stored in the database, and may determine a defect by comparing the captured image with the corresponding defective image data.

The substrate defect inspection apparatus 100 may output a result of determining the defect of the substrate (S560). The substrate defect inspection apparatus 100 may detect whether or not a substrate to be inspected is defective, as well as information on the type of defect.

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

The substrate defect inspection apparatus 100 determines whether to end the inspection (S580). As a result of the determination in step S580, when the inspection is terminated, the substrate defect inspection apparatus 100 ends the operation. However, as a result of the determination in step S580, if the inspection is not finished, the substrate defect inspection apparatus 100 may proceed to step S510 to inspect the next substrate for defects.

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

As shown in FIG. 6, the substrate defect inspection apparatus 100 may acquire a normal image stored in a database (S611). Here, the normal image is an image corresponding to a normal substrate without defects and may be referred to as a master image. In this case, the substrate defect inspection apparatus 100 may also obtain a parameter for inspection of the defect from the database. Meanwhile, the substrate defect inspection apparatus 100 may acquire a normal image or parameter before capturing an image by a line scan camera.

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

The substrate defect inspection apparatus 100 may divide an inspection section region from an image captured by a line scan camera (S615). The substrate defect inspection apparatus 100 divides an image captured by a 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 match the two images acquired according to the lighting control (S619).

The substrate defect inspection apparatus 100 performs a defect inspection of the substrate using the matched image (S621). The substrate defect inspection apparatus 100 may utilize deep learning-based artificial intelligence for defect inspection of the substrate, and may use the difference image acquired in step S617 together.

The substrate defect inspection apparatus 100 may detect a region in which defects are suspected (S623). For example, the substrate defect inspection apparatus 100 may crop an area suspected of defect to extract only information on a portion suspected of defect detection, or may remove the remaining portions of which defect detection is not suspected.

The substrate defect inspection apparatus 100 may perform a defect re-inspection on an area where defects are suspected (S625). The substrate defect inspection apparatus 100 may utilize artificial intelligence based on deep learning to re-inspect the defect of the substrate. The first artificial intelligence in step S621 and the second artificial intelligence in step S625 can be composed of different algorithms, and the first artificial intelligence has a function specialized for detection, and the second artificial intelligence can have a function specialized in judgment. have.

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

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

As shown in FIG. 7, the substrate defect inspection apparatus 100 may acquire a normal image stored in a database (S711). Again, the normal image is an image corresponding to a normal substrate without defects. In this case, the substrate defect inspection apparatus 100 may also obtain a parameter for inspection of the defect from the database. Meanwhile, the substrate defect inspection apparatus 100 may acquire a normal image or parameter before capturing an image by an area scan camera.

The substrate defect inspection apparatus 100 may detect a defective portion (S713). For example, the substrate defect inspection apparatus 100 may crop an area suspected of defect to extract only information on a portion suspected of defect detection, or may remove the remaining portions of which defect detection is not suspected.

The substrate defect inspection apparatus 100 may convert the image captured by the area camera into 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 match three image images captured according to illumination control (S719).

The substrate defect inspection apparatus 100 performs a defect inspection of the substrate using the matched image (S721). The substrate defect inspection apparatus 100 may utilize deep learning-based artificial intelligence for defect inspection of the substrate, and may use the difference image acquired in step S717 together. Here, the substrate defect inspection apparatus 100 may perform a defect inspection using the artificial intelligence used in step S621 of FIG. 6.

The substrate defect inspection apparatus 100 may determine a defect according to the defect inspection (S723). The substrate defect inspection apparatus 100 may determine a defect in one of normal, defective, and re-inspection.

The substrate defect inspection apparatus 100 may check whether the substrate according to the defect determination is determined to be reinspected (S725).

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

If the determination result of step S725 is determined to be retested, the substrate defect inspection apparatus 100 may proceed to step S727.

The substrate defect inspection apparatus 100 may classify and filter the types of defects using a parameter that sets the inspection result (S727).

The substrate defect inspection apparatus 100 may determine whether or not there is a defect through measurement (S729). The substrate defect inspection apparatus 100 may proceed to step S560 to output the determined result.

The term'~ unit' used in this embodiment means software or hardware components such as field programmable gate array (FPGA) or ASIC, and'~ unit' performs certain roles. However,'~ part' is not limited to software or hardware. The'~ unit' may be configured to be in an addressable storage medium, or may be configured to reproduce one or more processors. Thus, as an example,'~ unit' refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, procedures , Subroutines, segments of program patent code, drivers, firmware, microcode, circuitry, data, database, data structures, tables, arrays, and variables.

The components and functions provided within the'~ units' may be combined into a smaller number of elements and'~ units', or may be separated from the additional elements and'~ units'.

In addition, components and'~ units' may be implemented to play one or more CPUs in a device or a security multimedia card.

In addition, the method for inspecting a substrate defect according to an embodiment of the present invention may be implemented as a computer program (or a computer program product) including instructions executable by a computer. The computer program includes programmable machine instructions processed by a processor, and may be implemented in a high-level programming language, an object-oriented programming language, an assembly language, or a machine language. . Further, the computer program may be recorded on a tangible computer-readable recording medium (eg, a memory, a hard disk, a magnetic/optical medium or a solid-state drive (SSD), etc.).

Accordingly, the method of inspecting a substrate defect according to an embodiment of the present invention may be implemented by executing the computer program as described above by the computing device. The computing device may include at least some of a processor, a memory, a storage device, a high-speed interface connected to the memory and a high-speed expansion port, and a low-speed interface connected to the low-speed bus and the storage device. Each of these components is connected to each other using a variety of buses, and can be mounted on a common motherboard or in other suitable manner.

Here, the processor can process commands within the computing device. Such commands include, for example, to display graphic information for providing a GUI (Graphic User Interface) on an external input or output device, such as a display connected to a high-speed interface. This could be a command stored in memory or a storage device. As another embodiment, multiple processors and/or multiple buses may be utilized with multiple memories and memory types as appropriate. In addition, the processor may be implemented as a chipset formed by chips including a plurality of independent analog and/or digital processors.

The memory also stores information within the computing device. As an example, the memory may be composed of volatile memory units or a set of them. As another example, the memory may be composed of a nonvolatile memory unit or a set of them. Also, the memory may be another type of computer-readable medium such as a magnetic or optical disk.

In addition, the storage device may provide a large-capacity storage space to the computing device. The storage device may be a computer-readable medium or a configuration including such a medium, for example, devices in a storage area network (SAN) or other configurations, a floppy disk device, a hard disk device, an optical disk device, Alternatively, it may be a tape device, a flash memory, or another semiconductor memory device or device array similar thereto.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that other specific forms can be easily modified without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

100: board defect inspection device 110: mobile worktable
120: lighting 130: database
140: alignment camera 150: line scan camera
160: area scan camera 170: input/output unit
180: control unit

Claims (13)

A moving worktable for moving the substrate to a position for inspection;
Illumination for irradiating a predetermined light onto the substrate to obtain a photographed image;
At least one line scan camera for photographing the substrate in units of a predetermined line;
At least one area camera having a resolution different from that of the line scan camera and photographing the substrate in a predetermined area unit;
A database storing an image for detecting defects from the substrate; And
The position of the substrate is moved using the mobile worktable, and an image photographed of the plated portion of the substrate and an image photographed of the solder resist portion are obtained from the line scan camera by controlling the illumination, and from the obtained image The first defect is detected by determining the state of the substrate as one of normal, defective, and re-inspection, and the illumination is changed for the substrate determined by the re-inspection to obtain a substrate image photographing the substrate with an area camera, A control unit for detecting a second defect by determining a state of the substrate as one of normal and defective from the obtained substrate image,
The control unit,
The lighting is controlled a plurality of times for the substrate determined by the re-inspection to obtain a substrate image obtained by photographing the substrate multiple times, and by matching a plurality of obtained substrate images, the state of the substrate is determined as either normal or defective, and the second A board defect inspection device that detects vehicle defects. The method of claim 1,
At least one alignment camera positioned within a predetermined distance from the line scan camera and the area camera, and further comprising at least one alignment camera for photographing an image for aligning the position of the substrate,
The control unit is a substrate defect inspection apparatus for adjusting the position of at least one of the line scan camera, the area camera, and the substrate by using the image acquired from the alignment camera. The method of claim 1,
The control unit,
A substrate defect inspection apparatus using deep-learned defect image data stored in the database for inspection of the first defect and the second defect. The method of claim 3,
The control unit,
A substrate defect inspection apparatus configured to learn the defective image data by using an image of a substrate determined to be defective when the first defect is detected or the second defect is detected. delete In the substrate defect inspection method performed by the substrate defect inspection apparatus,
Controlling illumination to irradiate light onto the substrate to obtain an image photographing a plated portion of the substrate and an image photographing a solder resist portion with a line scan camera;
Detecting a first defect by determining a state of the substrate as one of normal, defective, and re-inspection from the acquired image;
Changing illumination of the substrate determined by re-inspection, and obtaining a substrate image obtained by photographing the substrate with an area camera having a resolution different from that of the line scan camera;
Including the step of detecting a second defect by determining the state of the substrate as one of normal and defective from the obtained substrate image,
Acquiring a substrate image photographing the substrate,
Controlling the illumination a plurality of times for the substrate determined to be retested to obtain a substrate image obtained by photographing the substrate a plurality of times,
The step of detecting the second defect,
And detecting a second defect by determining a state of the substrate as one of normal and defective by matching a plurality of acquired substrate images. The method of claim 6,
Acquiring an image photographing a plating portion of the substrate and an image photographing a solder resist portion,
And taking an image for aligning the position of the substrate, and adjusting the position of at least one of the line scan camera and the substrate using the captured image. The method of claim 6,
Acquiring a substrate image photographing the substrate,
And photographing an image for aligning the position of the substrate, and adjusting the position of at least one of the area camera and the substrate using the photographed image. The method of claim 6,
The step of detecting the first defect and the step of detecting the second defect,
A board defect inspection method using deep-learned defect image data stored in a database. The method of claim 9,
After the step of detecting the first defect and the second defect,
And learning the defective image data by using the image of the substrate determined to be defective. delete A computer-readable recording medium on which a program for performing the method according to claim 6 is recorded. A computer program performed by a substrate defect inspection apparatus and stored in a recording medium to perform the method according to claim 6.

Images