CN113933296A

CN113933296A - Method, device and system for detecting optical film

Info

Publication number: CN113933296A
Application number: CN202111056750.7A
Authority: CN
Inventors: 吴精文; 陈重宇; 吴省贤
Original assignee: Sumika Technology Co Ltd
Current assignee: Sumika Technology Co Ltd
Priority date: 2021-03-15
Filing date: 2021-09-09
Publication date: 2022-01-14
Also published as: TWI785535B; TW202238116A

Abstract

The present disclosure provides a method, an apparatus, and a system for inspecting an optical film, the method for inspecting the optical film comprising: shooting an image to be detected of an optical film to be detected placed on a platform at three angles through an optical sensor; receiving the image to be detected transmitted by the optical sensor; and detecting the image to be detected by using the identification model to judge the attribute of the optical film to be detected.

Description

Method, device and system for detecting optical film

Technical Field

The present disclosure relates to a method, an apparatus, and a system for inspecting an optical film, and more particularly, to a method, an apparatus, and a system for inspecting an optical film using a neural network technology.

Background

Since the cutting mechanism in the process of manufacturing the optical film does not have the function of distinguishing the surface protection film and the release film of the optical film, after the optical film is cut, a production line personnel needs to spend a lot of time to check and classify in a manual visual inspection mode.

However, manual visual inspection of optical films and sorting them is prone to error.

Therefore, there is a need for a method, an apparatus and a system for inspecting an optical film to distinguish a surface protection film from a release film by a manual visual inspection method, so as to improve productivity.

Disclosure of Invention

The following disclosure is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features, other aspects, embodiments, and features will be apparent from consideration of the drawings and from the detailed description below. That is, the following disclosure is provided to introduce concepts, points, benefits and novel and non-obvious technical advantages described herein. Selected, but not all, embodiments are described in further detail below. Thus, the following disclosure is not intended to identify essential features of the claimed subject matter, nor is it intended to be used in determining the scope of the claimed subject matter.

It is therefore one of the objectives of the present disclosure to provide a method, apparatus and system for inspecting an optical film to improve the above-mentioned disadvantages.

The present disclosure provides a system for inspecting an optical film, comprising: a platform; the optical sensor shoots an optical film to be detected, and the optical film is placed on the surface of the platform at three angles to generate three images to be detected; and a computing device that performs: receiving the image to be detected transmitted by the optical sensor; and detecting the image to be detected by utilizing an identification model so as to judge the attribute of the optical film to be detected.

The present disclosure provides a method for detecting an optical film, comprising: shooting an image to be detected of an optical film to be detected placed on a platform at three angles through an optical sensor; receiving the image to be detected transmitted by the optical sensor; and detecting the image to be detected by utilizing an identification model so as to judge the attribute of the optical film to be detected.

The present disclosure provides an apparatus for detecting an optical film, comprising: at least one graphics processor; and at least one computer storage medium storing computer readable instructions, wherein the graphics processor uses the computer storage medium to perform: receiving an image to be detected, which is shot by an optical sensor and is placed on a platform at three angles, of an optical film to be detected; and detecting the image to be detected by utilizing an identification model so as to judge the attribute of the optical film to be detected.

Drawings

FIG. 1 is a schematic diagram showing the composition of an optical film;

FIG. 2 shows images of the surface protective film or the release film of the optical film taken at different angles;

FIG. 3 is an exemplary diagram illustrating a system for inspecting an optical film in accordance with one embodiment of the present disclosure;

FIG. 4 is a flowchart illustrating a method for inspecting an optical film according to an embodiment of the present disclosure;

FIG. 5 is a flowchart illustrating a method for determining properties of an optical film to be inspected by using an identification model according to an embodiment of the present disclosure;

FIG. 6 is a table showing data identifying properties of an optical film according to an embodiment of the present disclosure;

FIG. 7 illustrates an exemplary operating environment for implementing embodiments of the present disclosure.

[ notation ] to show

100 optical film

102 surface protective film

104 protective layer

106 polarizing base

108 protective layer

110 adhesive layer

112 release film

300 system

310 stage

320 recognition device

322 input device

324 graphic processor

326 neural network

328 memory

3282 procedure

330 optical sensor

332 lens

340 network

350 optical film

400 method

S405, S410, S415, S420

500 method

S505, S510, S515, S520, S525 steps

700 computing device

710 bus

712 memory

714 graphic processor

716 display element

718I/O ports

720I/O element

722 power supply

Detailed Description

Aspects of the present disclosure are described more fully hereinafter with reference to the accompanying drawings. This disclosure may, however, be embodied in many different forms and should not be construed as limited to any specific structure or function presented throughout this disclosure. Rather, these aspects are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Based on the teachings herein one skilled in the art should appreciate that the scope of the present disclosure is intended to cover any aspect disclosed herein, whether alone or in combination with any other aspect of the present disclosure to achieve any aspect disclosed herein. For example, it may be implemented using any number of the apparatus or performing methods set forth herein. In addition, the scope of the present disclosure is intended to cover apparatuses or methods implemented using other structure, functionality, or structure and functionality in addition to or other than the various aspects of the present disclosure set forth herein. It should be understood that any aspect disclosed herein may be embodied by one or more elements of a claim.

The word "exemplary" is used herein to mean "serving as an example, instance, or illustration. Any aspect of the present disclosure or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects of the present disclosure or design. Moreover, like numerals refer to like elements throughout the several views, and the articles "a" and "an" include plural references unless otherwise specified in the description.

It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. In contrast, when an element is referred to as being "directly connected" or "directly coupled" to another element, there are no intervening elements present. Other words used to describe the relationship between elements should be interpreted in a similar manner (e.g., "between …" versus "directly between …," "adjacent" versus "directly adjacent," etc.).

The optical film 100 is composed of a surface protection film 102, a protection layer 104, a polarizing substrate 106, a protection layer 108, an adhesive layer 110, and a release film 112, as shown in fig. 1. In one embodiment, an adhesive layer (not shown) is included between the surface passivation layer 102 and the passivation layer 104.

In some embodiments, the material of the polarizing substrate 106 may be a polyvinyl alcohol (PVA) resin film, which may be made by saponifying a polyvinyl acetate resin. Examples of the polyvinyl acetate resin include a homopolymer of vinyl acetate, i.e., polyvinyl acetate, and a copolymer of vinyl acetate and other monomers copolymerizable with vinyl acetate.

In some embodiments, polyvinyl alcohol (PVA) may be used as the polarizing substrate 106 after being treated. The aforementioned treatment comprises preparing a staining solution; soaking polyethylene in dyeing liquor; stretching the polyvinyl alcohol; and drying.

In some embodiments, the

protective layers

104 and 108 may include films that facilitate optical gain, alignment, compensation, turning, orthogonalization, diffusion, protection, anti-sticking, scratch resistance, anti-glare, reflection suppression, high refractive index, and the like. In some embodiments, the passivation layer 104 and the passivation layer 108 may be a single layer or a multi-layer structure. The material of the

protective layers

104 and 108 may be, for example, a thermoplastic resin having excellent transparency, mechanical strength, thermal stability, moisture barrier property, and the like. The thermoplastic resin may include a cellulose resin (e.g., TAC, diacetate cellulose, dactylcellulose), an acrylic resin (e.g., polymethyl methacrylate (PMMA)), a polyester resin (e.g., polyethylene terephthalate (PET), polyethylene naphthalate), an olefin resin, a polycarbonate resin, a cyclic olefin resin, an oriented-stretched polypropylene (OPP), a Polyethylene (PE), a polypropylene (PP), a Cyclic Olefin Polymer (COP), a Cyclic Olefin Copolymer (COC), or any combination thereof.

In some embodiments, the adhesive layer 110 includes a Pressure Sensitive Adhesive (PSA), a heat sensitive adhesive, a solvent volatile adhesive, and a UV curable adhesive, and is not limited thereto. In some embodiments, the pressure sensitive adhesive comprises natural rubber, synthetic rubber, styrenic block copolymers, (meth) acrylic block copolymers, polyvinyl ethers, polyolefins, and poly (meth) acrylates. In some embodiments, (meth) acrylic (or acrylate) refers to both acrylic and methacrylic. In other embodiments, the pressure sensitive adhesive comprises (meth) acrylates, rubbers, thermoplastic elastomers, silicones, urethanes, and combinations thereof. In some embodiments, the pressure sensitive adhesive is based on a (meth) acrylic pressure sensitive adhesive or on at least one poly (meth) acrylate.

In some embodiments, the material of the surface protection film 102 and the release film 112 may be polyethylene terephthalate (PET), polybutylene terephthalate, polycarbonate, polyarylate, polyester resin, olefin resin, cellulose acetate resin, acrylic resin, Polyethylene (PE), polypropylene (PP), cyclic olefin resin, silicone, or a combination thereof.

Fig. 2 shows images of the optical film, which are captured at different horizontal rotation angles on two surfaces of the surface protection film and the release film. As shown in fig. 2, the optical film is placed on a platform, after the surface of the surface protection film or the surface of the release film faces upward, the optical sensor is used to photograph a first image vertical to the surface of the surface protection film or the surface of the release film to set the image as 0 degree, then the optical film is horizontally rotated 45 degrees on the platform to photograph a second image to set the image as 45 degrees, and finally the optical film is horizontally rotated 45 degrees on the platform to photograph a third image to set the image as 90 degrees (i.e. the third image is horizontally rotated 90 degrees from the initial placement angle). In one embodiment, the images captured by the present disclosure include a complete image of the optical film 100. In one embodiment, the images captured by the present disclosure include images of at least three boundaries of the rectangular optical film 100. As shown in fig. 2, it is not easy to distinguish the difference of the images of the surface protective film at 0 degrees, 45 degrees and 90 degrees, and the release film at 0 degrees, 45 degrees and 90 degrees, respectively, based on the visual angle of human eyes.

In order to reduce errors and reduce the cost of judging errors and rework, embodiments of the present disclosure provide a method, an apparatus and a system for inspecting an optical film, which utilize a neural network technology to further solve the problem of errors occurring in the process of producing the optical film.

FIG. 3 is an exemplary diagram illustrating a system 300 for inspecting an optical film according to one embodiment of the present disclosure. The system 300 may comprise a platform 310, an identification device 320, and an optical sensor 330.

The platform 310 may include a backlight for placement of an optical film 350. In one embodiment, the platform 310 may also have a rotation mechanism for rotating the optical film 350, which can rotate the optical film horizontally. In one embodiment, if the platform 310 has no rotation mechanism, the optical film 350 can be manually rotated horizontally. In one embodiment, the platform 310 rotates the optical film 350 horizontally by 0 degrees, 45 degrees, and 90 degrees.

In an embodiment, the structure and material of the optical film 350 are the same as those of the optical film 100, and are not described in detail.

The optical sensor 330 is capable of receiving the optical signal, converting the optical signal into electrical signals such as pixels, and transmitting the electrical signals to the identification device for operation. For example, the optical sensor 330 may include an Active Pixel Sensor (APS), a CMOS image sensor, a photosensitive coupled device (CCD), an infrared sensor, a photo transistor, or various optical lenses. Furthermore, the optical sensor may be a two-dimensional photosensitive element, that is, the optical sensor 330 cooperates with other devices, mechanisms or equipment to sequentially obtain partial sub-images of the surface of the optical film 350 to be detected in a two-dimensional manner, and finally, all partial sub-images are collected to obtain a complete surface image of the optical film 350 to be detected. In one embodiment, the optical sensor 330 has a larger image capture range, and can obtain a complete surface image of the optical film 350 to be detected at one time.

In some embodiments, the optical sensor 330 comprises a lens 332, wherein the lens 332 can be selectively installed with a polarizer (not shown) for capturing images of the surface of the optical film 350 placed on the platform 310 at various angles. In some embodiments, the optical sensor 330 is used to capture images of the surface of the optical film 350 placed on the stage 310 at three angles, for example, at 0 degrees, 45 degrees, and 90 degrees. The methods for obtaining the 0 degree, 45 degree and 90 degree images are the same as those described in the previous paragraph, and are not described in detail.

In some embodiments, the optical sensor 330 is a color optical sensor and includes a lens 332 with a polarizer (not shown) mounted thereon.

The recognition device 320 may include an input device 322, wherein the input device 322 is configured to receive input data from a variety of sources. For example, the recognition device 320 can receive the image transmitted by the optical sensor 330 through a network 340. The recognition device 320 may also receive a training image including the optical film and train a recognizer configured to recognize properties of the optical film based on the received training image.

The recognition device 320 further includes a graphics processor 324, a Neural Network 326, and a memory 328 that can store a program 3282. In addition, the image may be stored in the memory 328 or in the neural network 326. In one embodiment, the neural network 326 may be implemented by the graphics processor 324. In another embodiment, the identification device 320 may be used with other components, systems, subsystems, and/or devices than those described herein.

The types of identification devices 320 range from small handheld devices (e.g., mobile phones/portable computers) to large mainframe systems (e.g., mainframe computers). Examples of portable computers include Personal Digital Assistants (PDAs), notebook computers, and like devices. Network 340 may include, but is not limited to, one or more Local Area Networks (LANs) and/or Wide Area Networks (WANs).

It should be understood that the recognition device 320 shown in FIG. 3 is an example of the architecture of a system 300 for detecting optical films. The identifying means 320 shown in fig. 3 may be implemented via any type of computing device, such as the computing device 700 described with reference to fig. 7, as shown in fig. 7.

FIG. 4 is a flowchart illustrating a method 400 of inspecting an optical film according to an embodiment of the disclosure. This method may be performed in the graphics processor 324 of the recognition device 320 as shown in FIG. 3.

It is noted that, as used herein, the term "training" is used to identify objects used to train a recognition model. Thus, the training image refers to an image used for training the recognition model.

In step S405, the recognition device receives a plurality of training images of a plurality of optical films placed on a platform with a backlight function at three angles, wherein the three angles include 0 degree, 45 degrees and 90 degrees, and the training images are captured by an optical sensor. More specifically, the optical sensor needs to capture images of two surfaces (surface protection film surface and release film surface) of the optical film at three angles respectively to obtain training images of the surface protection film surface and the release film surface at the three angles.

Next, in step S410, the recognition device trains a recognition model to classify the attribute of the optical film in the training image, wherein the attribute is a surface protection film or a release film.

In step S415, the recognition device receives the to-be-detected images captured by the optical sensor from the to-be-detected optical film at the three angles. In step S420, the recognition device uses the recognition model to detect the image to be detected so as to determine the property of the optical film to be detected.

In one embodiment, the recognition model trained in step S410 by the recognition device is based on a Convolutional Neural Network (CNN) model. Common CNN model architectures are LeNet, AlexNet, VGG, GoogleLeNet, ResNet, and the like.

In another embodiment, the platform may include a rotation mechanism for horizontally rotating the optical film for training and the optical film to be inspected, so as to obtain multiple surface images.

In step S420, how the recognition device detects the image to be detected by using the recognition model to determine the property of the optical film to be detected will be described in detail below.

FIG. 5 is a flowchart illustrating a method 500 for determining properties of an optical film to be detected by using an identification model according to an embodiment of the present disclosure. This method may be performed in the graphics processor 324 of the recognition device 320 as shown in FIG. 3.

Before the process is started, the recognition device is trained with a recognition model for recognizing the properties of the optical film. In step S505, the recognition device receives the to-be-detected image captured by the optical sensor at three angles to an optical film to be detected. Next, in step S510, the recognition device obtains similarity ratios of the to-be-detected image corresponding to different attributes at the three angles by using the recognition model. In more detail, after the recognition device has trained the recognition model, the recognition model can receive Training Input (e.g., optical film images) and generate Output (Output) through a series of application layers. The output is a similarity ratio of the optical film corresponding to an attribute.

In step S515, the identification device determines whether two or more similarity ratios corresponding to an attribute are greater than a threshold. When two or more similarity ratios corresponding to an attribute are larger than the threshold value (yes in step S515), in step S520, the identification device determines the attribute of the optical film to be detected based on the similarity ratios.

When the similarity ratio between two or more optical films that do not have a corresponding attribute is greater than the threshold value (no in step S515), in step S525, the identification device transmits an error message to notify a user that the optical film to be detected is abnormal, wherein the identification device can use a related user interface (e.g., a display, a Light Emitting Diode (LED), a Liquid Crystal Display (LCD), a microphone, a Buzzer (Buzzer), etc.) to remind the user that the optical film to be detected is abnormal. After receiving the error information, the user can judge the attribute of the optical film to be detected in a manual mode.

FIG. 6 is a table showing data identifying properties of an optical film according to an embodiment of the present disclosure, which is detected according to a collected image to be detected. As shown in the table, the identification device identifies the optical film to be detected as the surface protection film with the similarity ratios of 0 degree, 45 degree and 90 degree of 8%, 93.2% and 84.5%, respectively, and identifies the optical film to be detected as the release film with the similarity ratios of 0 degree, 45 degree and 90 degree of 92%, 6.8% and 15.5%, respectively. In this embodiment, the threshold is defined to be 0.4 (i.e., the similarity ratio is 40%). Therefore, the identification device determines whether the number of the surface protection film or the release film of the optical film to be detected exceeds 2 when the similarity ratio of 0 degree, 45 degrees and 90 degrees is greater than the threshold value 0.4. As shown in the table, the ratio of 45 degree and 90 degree similarity of the surface protection film of the optical film to be detected is greater than the threshold value of 0.4, so the identification device will determine that the optical film to be detected is the surface protection film.

It is noted that although the threshold value of fig. 6 is 0.4 as an example, the disclosure is not limited to the embodiment shown in fig. 6, i.e., the training results of the visual shot images of the disclosure define other threshold values.

In addition, the graphics processor 324 in the recognition device 320 can also execute the program 3282 in the memory 328 to present the actions and steps described in the above embodiments, or other descriptions in the specification.

Therefore, the method, the device and the system for detecting the optical film can effectively avoid errors caused by manual detection of the optical film. After the automatic identification is introduced, the production line can reduce corresponding manpower, and the distribution condition of the optical film defects of the production line is provided, so that the yield is improved. In addition, the production and detection cost can be saved, the risk of misjudgment of the optical film is further reduced, and more credit and reputation can be won from the quality perspective.

For the described embodiments of the present disclosure, an exemplary operating environment in which embodiments of the present disclosure may be implemented is described below. With specific reference to FIG. 7, FIG. 7 illustrates an exemplary operating environment for implementing embodiments of the present disclosure that may be generally considered a computing device 700. The computing device 700 is only one example of a suitable computing environment and is not intended to suggest any limitation as to the scope of use or functionality of the disclosure. Neither should the computing device 700 be interpreted as having any dependency or requirement relating to any one or combination of components illustrated.

The present disclosure may be implemented in computer program code or machine-useable instructions, such as computer-executable instructions of a program module, executed by a computer or other machine, such as a personal digital assistant or other portable device. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform particular tasks or implement particular abstract data types. The present disclosure may be implemented in a variety of system configurations, including portable devices, consumer electronics, general-purpose computers, more specialized computing devices, and the like. The present disclosure may also be implemented in a distributed computing environment, where devices connected by a communication network are processed.

Refer to fig. 7. Computing device 700 includes a bus 710 that directly or indirectly couples the following devices, memory 712, a graphics processor 714 included in one or more processors (not shown), one or more display elements 716, input/output (I/O) ports 718, input/output (I/O) elements 720, and an illustrative power supply 722. Bus 710 represents what may be one or more busses (e.g., an address bus, data bus, or combination thereof). Although the blocks of FIG. 7 are illustrated with lines for simplicity, in practice, the boundaries of the various elements are not specific, e.g., the presentation elements of the display device may be considered to be I/O elements; the graphics processor may have memory. Computing device 700 typically includes a variety of computer-readable media. In addition, the graphics processor 714 in the computing device 700 may also execute the programs and instructions in the memory 712 to perform the actions and steps described in the above embodiments, or other descriptions in the specification.

Any particular order or hierarchy of steps for processes disclosed herein is purely exemplary. Based upon design preferences, it should be understood that any specific order or hierarchy of steps in the processes may be rearranged within the scope of the disclosure. The accompanying method claims present elements of the various steps in a sample order, and are therefore not to be limited to the specific order or hierarchy presented.

The use of ordinal terms such as "first," "second," "third," etc., in the claims to modify an element does not by itself connote any priority, precedence, order of various elements, or order of steps performed by the method, but are used merely as labels to distinguish one element from another element having a same name (but for use of a different ordinal term).

Although the present disclosure has been described with reference to exemplary embodiments, it should be understood that various changes and modifications can be made by those skilled in the art without departing from the spirit and scope of the disclosure, and therefore, the scope of the disclosure should be limited only by the appended claims.

Claims

1. A system for inspecting an optical film, comprising:

a platform;

the optical sensor shoots an optical film to be detected, and the optical film is placed on the surface of the platform at three angles to generate three images to be detected; and

a computing device that performs:

receiving the image to be detected transmitted by the optical sensor; and

and detecting the image to be detected by utilizing an identification model to judge the attribute of the optical film to be detected.

2. The system for inspecting an optical film according to claim 1, wherein before the computing device receives the image to be inspected, the computing device further receives a plurality of training images of the optical sensor, wherein a plurality of optical films are placed on the platform at the three angles, and the recognition model is trained to classify the attributes of the optical films in the training images.

3. The system for inspecting an optical film according to claim 1, wherein the step of inspecting the image to be inspected by using the identification model to determine the property of the optical film to be inspected further comprises:

obtaining the similarity proportion of the image to be detected corresponding to different attributes at the three angles by using the identification model;

judging whether more than two similarity ratios corresponding to an attribute are larger than a threshold value; and

and when more than two similarity ratios corresponding to one attribute are larger than the threshold value, judging the attribute of the optical film to be detected according to the similarity ratios.

4. The system for detecting an optical film as recited in claim 3, wherein the method further comprises:

and when more than two similarity ratios which do not correspond to one attribute are larger than the threshold value, transmitting an error message to inform that the optical film to be detected is abnormal.

5. The system of claim 1, wherein the optical sensor is a color optical sensor and comprises a lens, wherein the lens is mounted with a polarizer.

6. The system for inspecting an optical film according to claim 1, wherein the platform further comprises a backlight and/or a rotation mechanism for rotating the optical film to be inspected.

7. The system for detecting an optical film as claimed in claim 1, wherein the three angles include 0 degrees, 45 degrees and 90 degrees.

8. The system for inspecting an optical film according to claim 1, wherein the property is a surface protective film or a release film.

9. A method of inspecting an optical film, comprising:

shooting an image to be detected of an optical film to be detected placed on a platform at three angles through an optical sensor;

receiving the image to be detected transmitted by the optical sensor; and

10. The method for inspecting an optical film according to claim 9, wherein prior to receiving the image to be inspected, the method further comprises:

receiving a plurality of training images of a plurality of optical films placed on the platform at the three angles and shot by the optical sensor, and training the recognition model to classify the attributes of the optical films in the training images.

11. The method for inspecting an optical film according to claim 9, wherein the step of inspecting the image to be inspected by using the recognition model to determine the property of the optical film to be inspected further comprises:

12. The method of detecting an optical film according to claim 11, further comprising:

13. The method according to claim 9, wherein the optical sensor is a color optical sensor and comprises a lens, wherein the lens is mounted with a polarizer.

14. The method of inspecting an optical film according to claim 9, wherein the platform further comprises a backlight and/or a rotating mechanism for rotating the optical film to be inspected.

15. The method of detecting an optical film according to claim 9, wherein the three angles comprise 0 degrees, 45 degrees, and 90 degrees.

16. The method of inspecting an optical film according to claim 9, wherein the property is a surface protective film or a release film.

17. An apparatus for inspecting an optical film, comprising:

at least one graphics processor; and

at least one computer storage medium storing computer readable instructions, wherein the graphics processor uses the computer storage medium to perform:

receiving an image to be detected, which is shot by an optical sensor and is placed on a platform at three angles, of an optical film to be detected; and

18. The apparatus according to claim 17, wherein the optical sensor is a color optical sensor and comprises a lens, wherein the lens is mounted with a polarizer.

19. The apparatus for inspecting an optical film according to claim 17, wherein the platform further comprises a backlight and/or a rotating mechanism for rotating the optical film to be inspected.

20. The apparatus for inspecting an optical film according to claim 17, wherein the property is a surface protective film or a release film.