TW201908719A - Defect inspection system and defect inspection method - Google Patents

Abstract

The present invention provides a defect inspection system and a defect inspection method. A defect inspection system (1) includes a light source (2), an imaging unit (3), a conveying unit (4) and an image processing unit (5), wherein the image processing unit (5) identifies the type of defects contained in a series of two-dimensional images (F) taken at each discrete time by the imaging unit (3), based on data accumulating the result of machine learning relating to the identification of the type of defects contained in the two-dimensional images (F), and therefore identification accuracy is improved because the machine learning is applied to the two-dimensional image (F) for each discrete time, and in addition the two-dimensional image (F) whose brightness changes in a direction consistent with the conveying direction (X) in the two-dimensional image (F) is captured by the imaging unit (3), and hence the machine learning is applied to the two-dimensional image (F) whose brightness changes at each part along the conveying direction (X) in the two-dimensional image (F) for each discrete time, and thereby the identification accuracy of defect (D) can be improved.

Description

   Defect inspection system and method   

The invention relates to a defect inspection system and a defect inspection method.

As a defect inspection system for inspecting defects of an inspection object based on a captured image of the inspection object, for example, defect inspection for detecting defects such as optical films such as a polarizing film and a retardation film, and laminated films used for battery separators is known. system. This defect inspection system conveys the film along the conveyance direction, captures a two-dimensional image of the film in discrete time, and performs defect inspection based on the captured two-dimensional image. For example, the system of Japanese Patent No. 4726983 generates a column segmented image. The column segmented image is obtained by dividing a two-dimensional image into a plurality of columns arranged along a conveying direction, and The columns of the same position in each of the two-dimensional images are arranged in time series. The column-divided image is processed into a defect-enhanced processed image in which a change in brightness is enhanced. By processing the image with defect enhancement, it is easy to determine the presence or absence of a film defect and the position of the film defect.

In addition, even if a two-dimensional image of an inspection object is processed into a defect enhancement processed image as in the above-mentioned technology, the defect is finally identified by human-based judgment, and there is still room for improvement in the accuracy of defect recognition.

Accordingly, an object of the present invention is to provide a defect inspection system and a defect inspection method capable of improving the accuracy of defect recognition.

The invention is a defect inspection system, which includes: a light source that irradiates light to an inspection object; and an imaging unit that captures a two-dimensional image at discrete times, the two-dimensional image is based on irradiating the inspection object from the light source and passing through the inspection object or the inspection object. It is formed by the light reflected on the inspection object; the conveying unit is used to convey the inspection object relative to the light source and the imaging unit in the conveying direction; and the image processing unit is a diagram of a two-dimensional image captured by the imaging unit. The image data is processed. The imaging unit captures a two-dimensional image whose brightness changes in a direction that is consistent with the conveying direction. The image processing unit is related to the recognition of the type of the defect contained in the two-dimensional image. The data obtained by the accumulation of the results of the mechanical learning are used to identify the types of defects contained in a series of two-dimensional images captured by the camera in discrete time.

According to this configuration, the defect inspection system includes: a light source that irradiates light to an inspection object; and an imaging unit that captures a two-dimensional image at discrete times based on the illumination from the light source to the inspection object and passing through the inspection object or during inspection It is formed by the light reflected on the object; the conveying part conveys the inspection object relative to the light source and the imaging part along the conveying direction; and the image processing part is an image of the two-dimensional image captured by the imaging part The data is processed, and the image processing unit recognizes a series of discrete-time images taken by the imaging unit based on the data obtained by accumulating the results of mechanical learning related to the identification of the types of defects included in the two-dimensional image. The type of defects contained in the two-dimensional image is improved by applying mechanical learning to the two-dimensional image taken at discrete time to improve the recognition accuracy. In addition, the two-dimensional image is taken by the imaging unit. The two-dimensional image whose brightness changes in a direction that is consistent with the conveying direction. Therefore, mechanical learning is applied to the two-dimensional image taken in discrete time. The two-dimensional image where the brightness changes at each part in the conveying direction can improve the recognition accuracy of the defect.

In this case, it is preferable that the defect inspection system further includes a light-shielding body which is located between the light source and the inspection object, and shields a part of the light radiated from the light source to the inspection object, so that the imaging unit performs discrete time measurement. A light part and a dark part are formed on the captured two-dimensional image, and the conveying part relatively conveys the inspection object with respect to the light source, the light-shielding body, and the imaging part along a conveying direction that intersects the boundary between the light part and the dark part.

According to this configuration, a part of the light irradiated from the light source to the inspection object is blocked by the light-shielding body located between the light source and the inspection object, thereby forming a bright part and a dark part on a two-dimensional image captured by the imaging unit at discrete times. The conveying part relatively conveys the inspection object with respect to the light source, the light-shielding body, and the imaging part along the conveying direction that intersects the boundary between the light part and the dark part. Therefore, in a series of two-dimensional images taken in discrete time, Each part of the inspection object enters both the bright part and the dark part, and the presentation mode of each part of the inspection object in a series of two-dimensional images changes more widely in discrete time, so the defect recognition accuracy can be improved.

On the other hand, the present invention is a defect inspection method comprising: an irradiation process of irradiating light from a light source of a defect inspection system to an inspection object; and an imaging process of capturing a two-dimensional image in discrete time by an imaging unit of the defect inspection system, wherein: The two-dimensional image is formed based on the light irradiated from the light source to the inspection object and transmitted through the inspection object or reflected on the inspection object during the irradiation process; the inspection object is transported along the inspection source with respect to the light source and the imaging unit by the transport unit of the defect inspection system. A conveying process in which the directions are relatively conveyed; and an image processing process in which the image processing unit of the defect inspection system processes image data of the two-dimensional image captured in the image capturing process, and in the image capturing process, the image is captured in two dimensions The two-dimensional image whose brightness changes in a direction that is consistent with the conveying direction of the image is obtained by accumulating the results of mechanical learning related to the identification of the types of defects included in the two-dimensional image in the image processing step. Data to identify the types of defects contained in a series of two-dimensional images taken at discrete times during the imaging process .

In this case, it is preferable that in the irradiation process, the light-shielding body of the defect inspection system is used to form a bright part and a dark part on a two-dimensional image captured by the imaging process at discrete times, wherein the light-shielding body is located between the light source and the inspection. Between the objects, a part of the light irradiated from the light source to the inspection object is blocked. In the transportation process, the inspection object is transported along the boundary line between the light part and the dark part with respect to the light source, the light-shielding body and the imaging part. Relatively.

1‧‧‧ Defect inspection system

2‧‧‧ light source

3‧‧‧ Camera Department

4‧‧‧ Conveying Department

5‧‧‧Image Processing Department

6‧‧‧ shade body

7‧‧‧ Parallel Light Lens

8‧‧‧ display device

b‧‧‧ dividing line

D‧‧‧ Defect

d‧‧‧ dark

F‧‧‧ 2D image

l‧‧‧ Mingbei

R‧‧‧ Error Reverse

T‧‧‧Inspection

X‧‧‧ Conveying direction

Y‧‧‧Width direction

100‧‧‧ Convolutional Neural Network

110‧‧‧input layer

120‧‧‧ Hidden layer

121, 123‧‧‧ Convolutional layer

122‧‧‧pooling layer

124‧‧‧Fully connected layer

130‧‧‧ output layer

FIG. 1 is a perspective view showing a defect inspection system according to the embodiment.

FIG. 2 is a diagram showing the arrangement of a light source, an imaging unit, a light shielding body, and an inspection object in the defect inspection system of FIG.

Fig. 3 is a flowchart showing the steps of the defect inspection method according to the embodiment.

FIG. 4 is a diagram showing a two-dimensional image captured by the imaging unit.

Fig. 5 is a diagram showing a convolutional neural network.

Hereinafter, preferred embodiments of the defect inspection system and the defect inspection method of the present invention will be described in detail with reference to the drawings.

As shown in FIGS. 1 and 2, the defect inspection system 1 according to the embodiment of the present invention includes a light source 2, an imaging unit 3, a transport unit 4, an image processing unit 5, a light shielding body 6, a parallel light lens 7, and a display device 8. . The defect inspection system of this embodiment uses an optical film such as a polarizing film and a retardation film, and a film such as a laminated film used for a battery separator as an inspection object T to detect a defect of the inspection object T. The inspection object T extends along the conveying direction X of the conveying section 4 and has a predetermined width in a width direction Y orthogonal to the conveying direction X. The defect generated in the inspection object T refers to a state different from the desired state, and examples include foreign matter, scratches, bubbles (bubbles generated during molding, etc.), foreign object bubbles (bubbles generated by the incorporation of foreign matter, etc.) ), Scars, cracks (cracks due to polyline marks, etc.), and stripes (stripes due to differences in thickness, etc.). The defect inspection system 1 recognizes the types of these defects.

As shown in FIGS. 1 and 2, the light source 2 irradiates light to the inspection object T. The light source 2 is arranged to irradiate linear light parallel to the width direction Y. The light source 2 is not particularly limited as long as it is a lamp that irradiates light that does not affect the composition and properties of the film as the inspection object T, such as a metal halide lamp, a halogen transfer lamp, or a fluorescent lamp.

The imaging unit 3 captures a two-dimensional image at discrete times, and the two-dimensional image is formed based on light irradiated from the light source 2 to the inspection object T and transmitted through the inspection object T or reflected on the inspection object T. The imaging unit 3 includes a plurality of optical members and a photoelectric conversion element. The optical member includes an optical lens, a shutter, and the like, and images the light that has passed through the film as the inspection target T on the surface of the photoelectric conversion element. The photoelectric conversion element is a surface sensor composed of an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal-Oxide Semiconductor) that captures two-dimensional images. The imaging unit 3 may be a member that captures either a two-dimensional image without color or a two-dimensional image with color.

The transport unit 4 transports the inspection object T relative to the light source 2 and the imaging unit 3 in the transport direction X. The transporting unit 4 includes, for example, a sending roller and a receiving roller that transports a film to be inspected T in the transporting direction X, and measures a transporting distance by a rotary encoder or the like. In this embodiment, the conveyance speed at which the conveyance unit 4 conveys the inspection object T is set to a level of 2 to 100 m / min along the conveyance direction X. The conveying speed of the conveying section 4 is set and controlled by the image processing section 5 and the like.

The image processing unit 5 processes image data of a two-dimensional image captured by the imaging unit 3. The image processing unit 5 recognizes a series of two-dimensional images captured by the imaging unit 3 at discrete times based on data obtained by accumulating mechanical learning results related to the identification of the types of defects included in the two-dimensional image. The category of defects included. The image processing unit 5 is not particularly limited as long as it is a component that performs image processing of two-dimensional image data. For example, a PC (personal computer) with image processing software installed, and an FPGA (Field Programmable Gate) with an image processing circuit mounted thereon can be applied. Array, field programmable gate array) image acquisition card. The data obtained by accumulating the results of the mechanical learning is stored in a storage device such as a hard disk of the PC including the image processing unit 5 and is updated along with the results of the mechanical learning.

It should be noted that, in this embodiment, the data obtained by accumulating the results of the mechanical learning related to the identification of the category of the defects included in the two-dimensional image is in addition to the data related to the internal parts of the defect inspection system 1. The imaging unit 3 accumulates the results of mechanical learning related to the identification of the types of defects included in a series of two-dimensional images captured in discrete time, and also includes data generated separately from the outside of the defect inspection system 1 The two-dimensional image contains data obtained by accumulating the results of mechanical learning related to the identification of the types of defects. That is, in this embodiment, in addition to a scheme for identifying the type of a defect in a state where mechanical learning has been performed inside the defect inspection system 1, it also includes a scheme based on a state where mechanical learning has not been performed in the defect inspection system 1. The data obtained by accumulating the results of the mechanical learning generated outside the defect inspection system 1 to identify the type of the defect.

The light-shielding body 6 is located between the light source 2 and the inspection object T, and blocks a part of the light irradiated from the light source 2 to the inspection object T, so that the two-dimensional image captured by the imaging unit 3 in discrete time is captured. Form bright and dark parts. With the light-shielding body 6, the imaging unit 3 captures a two-dimensional image in which the brightness changes in a direction that coincides with the transport direction X of the two-dimensional image. More specifically, the conveyance unit 4 relatively conveys the inspection object T with respect to the light source 2, the parallel light lens 7, the light-shielding body 6, and the imaging unit 3 along the conveyance direction X that intersects the boundary between the bright portion and the dark portion. In this embodiment, the dividing line is parallel to the width direction Y that is perpendicular to the conveying direction X. It should be noted that the imaging unit 3 only needs to be able to capture a two-dimensional image whose brightness changes in a direction that coincides with the conveyance direction X, and may not include the light-shielding body 6. The collimator lens 7 makes the traveling direction of the light irradiated from the light source 2 to the inspection object T and the light-shielding body 6 parallel. The collimator lens 7 may be configured by a telecentric optical system, for example.

The display device 8 connected to the image processing unit 5 is composed of, for example, a PC (personal computer) or the like, and displays the type of the defect recognized by the image processing unit 5 on an LC (Liquid Crystal) display panel, a plasma display panel, an EL (Electro Luminescence) display panel, etc. It should be noted that the video processing unit 5 may include a display device that displays a processed image.

The defect inspection method of this embodiment will be described below. As shown in FIG. 3, an irradiation step of irradiating light from the light source 2 of the defect inspection system 1 to the inspection object T is performed (S1). As shown in FIG. 4, in the irradiation process, the light shielding body 6 of the defect inspection system 1 located between the light source 2 and the inspection object T and shielding a part of the light radiated from the light source 2 to the inspection object T is used for imaging. The two-dimensional image F photographed at discrete times in the step is formed with a bright portion l and a dark portion d.

As shown in FIG. 3, the imaging process (S2) is performed by the imaging unit 3 of the defect inspection system 1. In this imaging process, a two-dimensional image is captured at discrete times. The two-dimensional image is based on the light source from the light source during the irradiation process. 2 It is formed by irradiating the inspection object T and transmitting the light reflected by the inspection object T or the inspection object T. As shown in FIG. 4, in the imaging process, a part of the light irradiated from the light source 2 to the inspection object T is blocked by the light shielding body 6. Therefore, the two-dimensional image F is captured in a direction that coincides with the transport direction X. Changing two-dimensional image F.

In addition, as shown in FIG. 3, the conveyance step of conveying the inspection object T relative to the light source 2 and the imaging unit 3 in the conveyance direction X is performed by the conveyance section 4 of the defect inspection system 1 (S3). As shown in FIG. 4, in the conveying step, the inspection object T is conveyed in a direction in which the inspection object T intersects the boundary line b between the bright portion 1 and the dark portion d with respect to the light source 2, the parallel light lens 7, the light shielding body 6, and the imaging unit 3. X is delivered relatively. In this embodiment, the boundary line b is parallel to the width direction Y orthogonal to the conveyance direction X, but the angle formed by the boundary line b and the conveyance direction X may be an angle other than 90 °. In addition, the boundary line b is not necessarily a strict boundary line, and the boundary line b is the middle of the part where the two-dimensional image F including the bright part l has the highest brightness and the part where the two-dimensional image F including the dark part d has the smallest brightness. line.

As shown in FIG. 3, the image processing unit 5 of the defect inspection system 1 performs an image processing step of processing image data of the two-dimensional image F captured in the imaging step (S4). In the image processing step, a series of images taken at discrete times in the imaging step are identified based on data obtained by accumulating the results of mechanical learning related to the recognition of the category of the defect D included in the two-dimensional image F. The type of the defect D included in the two-dimensional image F. Mechanical learning is performed, for example, by a convolutional neural network. It should be noted that, as long as the category of the defect can be identified through mechanical learning, a neural network other than a convolutional neural network or other methods may be used.

As shown in FIG. 5, the convolutional neural network 100 includes an input layer 110, a hidden layer 120, and an output layer 130. The image processing unit 5 of the defect inspection system 1 inputs a series of two-dimensional images F captured at discrete times in the imaging process to the input layer 110. The hidden layer 120 has convolutional layers 121 and 123 that perform image processing based on a weight filter, a pooling layer 122 that performs processing to reduce the two-dimensional array output from the convolutional layers 121 and 123 horizontally and horizontally while leaving valid values, and The fully connected layer 124 with the weight coefficient n of each layer is updated. In the output layer 130, a recognition result of the class of the defect D by the mechanical learning is output. In the convolutional neural network 100, the error of the output recognition result and the positive solution value is back-propagated in the backward direction R to learn the weight of each layer.

For example, a plurality of two-dimensional images F are inputted in advance to the image processing unit 5 together with a positive solution for identifying the type of the defect D, and the image processing unit 5 learns, thereby sequentially identifying a series of two-dimensional images newly input. Whether the category included in F is the category of a specific defect D, and the recognition result is output in order. The recognition results and the error of the positive solution that are output in order propagate back to R, and the weighting coefficients n of each layer are sequentially updated and accumulated as data. In the state where the weights of the phases are sequentially updated, it is further recognized in sequence whether the categories included in the newly inputted series of two-dimensional images F are specific defect categories, and the recognition results are output sequentially, and based on the sequentially output recognition results The weighting coefficient n of each layer is sequentially updated with the error from the positive solution and accumulated as data. Repeatedly, the error between the recognition result and the positive solution becomes smaller, and the accuracy of the classification of the defect D is improved.

According to the present embodiment, the defect inspection system 1 includes a light source 2 that irradiates light to the inspection object T, and an imaging unit 3 that captures a two-dimensional image F at discrete times. The two-dimensional image F is based on the light source 2 toward the inspection object. T is formed by irradiating and passing through the inspection object T or light reflected on the inspection object T; the conveying unit 4 conveys the inspection object T relative to the light source 2 and the imaging unit 3 in the conveying direction X; and the image processing unit 5. Processing the image data of the two-dimensional image F captured by the imaging unit 3, wherein the image processing unit 5 is based on mechanical learning related to the recognition of the category of the defect D included in the two-dimensional image F. As a result, the accumulated data are used to identify the type of the defect D contained in a series of two-dimensional images F captured by the camera 3 in discrete time. Therefore, mechanical learning is applied to the two images captured in discrete time. The two-dimensional image F improves recognition accuracy. In addition, a two-dimensional image F whose brightness is changed in a direction that coincides with the conveyance direction X is captured by the imaging unit 3, and therefore, mechanical learning is applied. For shooting in discrete time X at each part of the two-dimensional image in the conveying direction F of the two-dimensional image F luminance variation occurs, thereby improving the recognition accuracy of the defect D.

In addition, in this embodiment, a part of the light irradiated from the light source 2 to the inspection object T is shielded by the light shielding body 6 located between the light source 2 and the inspection object T, so that the image captured by the imaging unit 3 in discrete time is captured. The two-dimensional image F has a light portion 1 and a dark portion d, and the inspection object T is conveyed by the conveying portion 4 with respect to the light source 2, the light shielding body 6, and the imaging portion 3 along the boundary line b that intersects the light portion 1 and the dark portion d. The direction X is conveyed relatively, so each part of the inspection object T in a series of two-dimensional images F taken in discrete time enters both the bright part l and the dark part d. Since the presentation mode of each part of the inspection object T changes more widely in discrete time, the recognition accuracy of the defect D can be improved.

As mentioned above, although embodiment of this invention was described, this invention is not limited to the said embodiment, It can implement in various aspects. For example, in the embodiment described above, the case where the inspection object is a film has been mainly described, but the defect inspection system and the defect inspection method of the present invention can be applied to, for example, a production line inspection of the filling amount of a liquid filled in a container. With the defect inspection system 1 and the defect inspection method according to the present embodiment, it is possible to inspect defects such as whether the liquid does not reach a desired position in the container, or whether the liquid does not exceed the desired position in the container.

In addition, the defect inspection system 1 and the defect inspection method of the present embodiment can be applied to appearance inspections such as cracks and flaws of glass products in a production line. When lighting is applied to a glass product for shooting, if there is a defect in a part of the captured image, the defect can be extracted by using a case where the brightness is higher than other parts.

Claims (4)

    A defect inspection system includes: a light source that irradiates light to an inspection object; and an imaging unit that captures a two-dimensional image at discrete times based on the illumination from the light source to the inspection object and passing through the inspection object or The light reflected on the inspection object is formed; the transport unit transports the inspection object relative to the light source and the imaging unit along the transportation direction; and the image processing unit acquires the image from the imaging unit. The image data of the two-dimensional image is processed, the imaging unit captures the two-dimensional image whose brightness changes in a direction that is consistent with the conveying direction of the two-dimensional image, and the image processing unit is based on Data accumulated from the results of mechanical learning related to the identification of the category of defects contained in the two-dimensional image to identify the defects contained in the series of two-dimensional images captured by the imaging unit at discrete times. category.         The defect inspection system according to item 1 of the scope of patent application, wherein the defect inspection system further includes a light shielding body located between the light source and the inspection object, and the light source irradiates the inspection object from the light source to the inspection object. A part of the light is blocked to form a light portion and a dark portion on the two-dimensional image captured by the imaging unit in discrete time, and the conveying unit moves the inspection object along the light source, the light-shielding body, and the imaging unit. The transportation direction that intersects the boundary between the bright portion and the dark portion is transported relatively.         A defect inspection method includes: an irradiation step of irradiating light to an inspection object from a light source of a defect inspection system; and an imaging step of capturing a two-dimensional image at discrete times by an imaging unit of the defect inspection system, wherein the two-dimensional image The image is formed based on the light that is irradiated from the light source to the inspection object and transmitted through the inspection object or reflected on the inspection object in the irradiation process; the transport process is performed by the transport unit of the defect inspection system to inspect the inspection The object is relatively conveyed along the conveying direction with respect to the light source and the imaging section; and an image processing step is an image data of the two-dimensional image captured in the imaging step by the image processing section of the defect inspection system. Performing processing, in the imaging step, capturing the two-dimensional image in which the brightness changes in a direction that is consistent with the conveying direction of the two-dimensional image, and in the image processing step, based on the comparison with the two-dimensional image Accumulate the results of machine learning related to the identification of the types of defects included Expected to recognize the type of the photographing by the imaging discrete time step in a series of two-dimensional image containing the defect.         The defect inspection method according to item 3 of the scope of patent application, wherein in the irradiation step, a light-shielding body of the defect inspection system is used to form a clear image on the two-dimensional image captured by the imaging process at discrete times. And a dark portion, wherein the light shielding body is located between the light source and the inspection object, and shields a part of the light radiated from the light source to the inspection object, and in the transporting step, the inspection object is relative to the inspection object. The light source, the light-shielding body, and the imaging unit are transported opposite to each other along the transport direction that intersects the boundary between the bright portion and the dark portion.