KR101206290B1 - Quality test equipment using fabric pattern algorithm and method for controlling thereof - Google Patents

Abstract

PURPOSE: A product quality testing apparatus through fabric pattern algorithm and a method for controlling the same are provided to integrate an intelligent learning process, a line scan camera, and a dedicated controller and to ensure uniform and high product quality. CONSTITUTION: A product quality testing apparatus comprises: a user input part for inputting a standard image; a scan camera for serially acquiring a first image for one or more objects; and a control unit which determines damage of the objects using the standard image and first image according to the preset algorithm. The scan camera comprises a plurality of cameras. The control unit controls operation timing of the plurality of cameras and a synchronous light. [Reference numerals] (AA) Camera; (BB) LED lighting device

Description

QUALITY TEST EQUIPMENT USING FABRIC PATTERN ALGORITHM AND METHOD FOR CONTROLLING THEREOF

The present invention relates to a quality inspection apparatus and its control method by applying the fabric pattern algorithm.

The textile industry is divided into units from raw materials to spinning and processing, weaving and knitting, dyeing processing, design, sewing and marketing, so that the structure of a multi-supply chain creates added value through close exchange. Have

In addition, due to the increase in domestic production costs, the price competitiveness of the textile industry has reached a limit compared to competitors, and thus, differentiation factors, that is, quality of products are required. Quality problems can occur at every stage of production, but the quality of raw materials will have the greatest influence on the competitiveness of the final product. Therefore, in order to secure high quality of finished products, in the production and dyeing process Quality control is very important.

However, most of the quality evaluations are dependent on the quality inspectors' proficiency, and they are limited to sensory inspections such as visual inspections, which makes it difficult to achieve uniform quality evaluations. It is a situation.

In addition, in order to solve the problem of visual (sensation) inspection, each unit examines the automated inspection device, but there is a problem that it is difficult to introduce and spread the related industry because it is composed of expensive independent inspection devices regardless of domestic and foreign systems. Therefore, the situation is required to improve the solution to solve this.

The present invention is to provide a quality inspection system with a low introduction cost by designing an add-on quality inspection system to be easily applied to existing equipment.

In addition, the present invention is to maximize user convenience through a quality inspection system integrating an intelligent learning process (Intelligent Learning Process).

In addition, the present invention is to provide a user with uniformity and ease of quality control by integrating an intelligent learning process, a line scan camera and a dedicated controller.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of the invention, unless further departing from the spirit and scope of the invention as defined by the appended claims. It will be possible.

According to an aspect of the present invention, there is provided a quality inspection apparatus according to an embodiment of the present invention. The apparatus may include a user input unit for receiving a reference image, a scan camera for continuously acquiring a first image of at least one object, and a preset algorithm. And a controller configured to determine whether there is damage to the at least one object by using a reference image and a first image. When a result of comparing the reference image with the first image exceeds a preset range, the controller The controller may control the first image to be changed and set as the reference image.

In addition, the scan camera includes a plurality of cameras, and further includes a synchronous lighting for supporting the acquisition of the first image of each of the plurality of cameras, the control unit is the operation of the plurality of cameras and synchronous lighting Timing can be controlled.

In addition, the preset algorithm uses a brightness change of a predetermined region included in the reference image and the first image, and the preset algorithm is a fractal dimensional technique, a threshold binarization technique, a block averaging technique, and morphological operations. ) At least one of the techniques.

The preset algorithm uses a frequency change of a predetermined region included in the reference image and the first image, and the preset algorithm includes at least one of a binary Fourier transform technique, a local Fourier transform technique, and a Gabor filter mask technique. can do.

The controller may convert the first image into a grayscale image and compare the converted grayscale image with the reference image in pixel units to determine whether the at least one object is damaged. can do.

The controller may further include a memory, and when the at least one object is damaged, the controller detects the damage related information in pixel units, and detects the information detected in pixel units in line units. The calculation may be performed such that the information stored in the line unit is continuously stored in the memory.

The controller may extract area unit information by combining a plurality of line unit information continuously stored in the memory.

The display apparatus may further include a display unit, and the controller may control the area unit information to be displayed on a predetermined region of the display unit.

The apparatus may further include a wireless communication unit, and the controller may control the area unit information to be transmitted through the wireless communication unit to an external device designated through the user input unit.

On the other hand, the control method of the quality inspection apparatus according to an embodiment of the present invention for realizing the above-mentioned problem is a step of receiving a reference image, continuously obtaining a first image for at least one object, according to a predetermined algorithm Determining whether the at least one object is damaged by using the reference image and the first image, and when a result of comparing the reference image with the first image exceeds a preset range, the first image The method may include controlling to change the reference image to be set.

In addition, the preset algorithm uses a brightness change of a predetermined region included in the reference image and the first image, and the preset algorithm is a fractal dimensional technique, a threshold binarization technique, a block averaging technique, and morphological operations. ) At least one of the techniques.

The preset algorithm uses a frequency change of a predetermined region included in the reference image and the first image, and the preset algorithm includes at least one of a binary Fourier transform technique, a local Fourier transform technique, and a Gabor filter mask technique. can do.

The determining of whether the at least one object is damaged may include converting the first image into a grayscale image and comparing the converted grayscale image with the reference image in pixel units. Method can be used.

In addition, when the at least one object is damaged, detecting the damage-related information in the pixel unit, calculating the information detected in the pixel unit in the line unit and in the line unit The method may further include controlling the stored information to be continuously stored in the memory.

The method may further include extracting area unit information by combining a plurality of line unit information continuously stored in the memory.

The quality inspection apparatus according to at least one embodiment of the present invention configured as described above is designed in an add-on type so as to be easily applied to an existing facility, thereby ensuring the effect of lowering the introduction cost.

In addition, the quality inspection apparatus according to at least one embodiment of the present invention may provide a user with uniform and easy quality control by integrating an intelligent learning process, a line scan camera, and a dedicated controller. There is an effect.

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

1 is a block diagram of a mobile terminal according to an embodiment of the present invention.
2 is a front perspective view of a mobile terminal according to an embodiment of the present invention.
3 is a block diagram showing the flow of fabric pattern matching in connection with the present invention.
4 is a diagram illustrating an example of a camera structure diagram according to an embodiment of the present invention.
FIG. 5 is a block diagram showing an example of operation of hardware in which a line scan camera and an inspection-only controller are integrated in accordance with the present invention.
6 is a diagram illustrating an example of a line scan camera according to an embodiment of the present invention.
7 is a view showing an example of the type of failure of fabric in connection with the present invention.
8 is a view for explaining a method using a Sobel operator of the fabric damage detection method of the present invention.
9 is a view for explaining a method using an average filter of the fabric damage detection method of the present invention.
Fig. 10 is a diagram showing an example of fabric damage detection results by edge detection in connection with the present invention.
11 is a view showing an example of the fabric damage detection results by morphological calculations in connection with the present invention.
12 is a view showing another example of the fabric damage detection result by the morphological calculation in connection with the present invention.
It is a figure which shows an example of the fabric damage detection result by an average value filter with respect to this invention.
It is a figure which shows another example of the fabric damage detection result by an average value filter with respect to this invention.
15 is a view showing an example relating to the frequency characteristics of an intact textile image in relation to the present invention.
16 is a view showing an example relating to the frequency characteristics of a damaged textile image in connection with the present invention.
It is a figure which shows an example of the fabric damage detection result using a Gabor filter with respect to this invention.
18 is a diagram illustrating an example of a fabric inspection technique flow in accordance with an embodiment of the present invention.
19 is a diagram illustrating an example related to a process of connecting and creating a damaged area according to an embodiment of the present invention.
20 is a view showing an example of a quality inspection apparatus by applying a fabric pattern algorithm according to an embodiment of the present invention.

Hereinafter, the image display apparatus applicable to the present invention will be described in more detail with reference to the accompanying drawings. The suffix "module" and " part "for the components used in the following description are given or mixed in consideration of ease of specification, and do not have their own meaning or role.

It is assumed that the image display device described herein is a mobile terminal. The mobile terminal may include a mobile phone, a smart phone, a laptop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), navigation, and the like. However, it will be readily apparent to those skilled in the art that the configuration according to the embodiments described herein may also be applied to fixed terminals such as digital TVs, desktop computers, digital media players, etc., except when applicable only to mobile terminals. will be.

Overall configuration

1 is a block diagram of a mobile terminal according to an embodiment of the present invention.

The mobile terminal 100 includes a wireless communication unit 110, an audio / video input unit 120, a user input unit 130, a sensing unit 140, an output unit 150, a memory 160, A controller 170, a controller 180, a power supply 190, and the like. The components shown in FIG. 1 are not essential, and a mobile terminal having more or fewer components may be implemented.

Hereinafter, the components will be described in order.

The wireless communication unit 110 may include one or more modules for enabling wireless communication between the mobile terminal 100 and the wireless communication system or between the mobile terminal 100 and the network in which the mobile terminal 100 is located. For example, the wireless communication unit 110 may include a broadcast receiving module 111, a mobile communication module 112, a wireless Internet module 113, a short range communication module 114, and a location information module 115 .

The broadcast receiving module 111 receives a broadcast signal and / or broadcast related information from an external broadcast management server through a broadcast channel.

The broadcast channel may include a satellite channel and a terrestrial channel. The broadcast management server may refer to a server for generating and transmitting broadcast signals and / or broadcast related information, or a server for receiving broadcast signals and / or broadcast related information generated by the broadcast management server and transmitting the generated broadcast signals and / or broadcast related information. The broadcast signal may include a TV broadcast signal, a radio broadcast signal, a data broadcast signal, and a broadcast signal in which a data broadcast signal is combined with a TV broadcast signal or a radio broadcast signal.

The broadcast-related information may refer to a broadcast channel, a broadcast program, or information related to a broadcast service provider. The broadcast related information may also be provided through a mobile communication network. In this case, it may be received by the mobile communication module 112.

The broadcast related information may exist in various forms. For example, it may exist in the form of Electronic Program Guide (EPG) of Digital Multimedia Broadcasting (DMB) or Electronic Service Guide (ESG) of Digital Video Broadcast-Handheld (DVB-H).

The broadcast receiving module 111 may include, for example, Digital Multimedia Broadcasting-Terrestrial (DMB-T), Digital Multimedia Broadcasting-Satellite (DMB-S), Media Forward Link Only (MediaFLO), and Digital Video Broadcast (DVB-H). Digital broadcast signals can be received using digital broadcasting systems such as Handheld and Integrated Services Digital Broadcast-Terrestrial (ISDB-T). Of course, the broadcast receiving module 111 may be adapted to other broadcasting systems as well as the digital broadcasting system described above.

The broadcast signal and / or broadcast related information received through the broadcast receiving module 111 may be stored in the memory 160.

The mobile communication module 112 transmits and receives radio signals to at least one of a base station, an external terminal, and a server on a mobile communication network. The wireless signal may include various types of data depending on a voice call signal, a video call signal or a text / multimedia message transmission / reception.

The wireless Internet module 113 is a module for wireless Internet access, and may be built in or externally attached to the mobile terminal 100. Wireless Internet technologies may include Wireless LAN (Wi-Fi), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed Downlink Packet Access (HSDPA), and the like.

The short range communication module 114 refers to a module for short range communication. Bluetooth, Radio Frequency Identification (RFID), infrared data association (IrDA), Ultra Wideband (UWB), ZigBee, and the like can be used as a short range communication technology.

The position information module 115 is a module for obtaining the position of the mobile terminal, and a representative example thereof is a Global Position System (GPS) module.

Referring to FIG. 1, an A / V (Audio / Video) input unit 120 is for inputting an audio signal or a video signal, and may include a camera 121 and a microphone 122. The camera 121 processes image frames such as still images or moving images obtained by the image sensor in the video call mode or the photographing mode. The processed image frame can be displayed on the display unit 151. [

The image frame processed by the camera 121 may be stored in the memory 160 or transmitted to the outside through the wireless communication unit 110. [ Two or more cameras 121 may be provided depending on the use environment.

The microphone 122 receives an external sound signal through a microphone in a communication mode, a recording mode, a voice recognition mode, or the like, and processes it as electrical voice data. The processed voice data can be converted into a form that can be transmitted to the mobile communication base station through the mobile communication module 112 when the voice data is in the call mode, and output. Various noise reduction algorithms may be implemented in the microphone 122 to remove noise generated in receiving an external sound signal.

The user input unit 130 generates input data for a user to control the operation of the terminal. The user input unit 130 may include a key pad dome switch, a touch pad (static pressure / capacitance), a jog wheel, a jog switch, and the like.

The sensing unit 140 senses the current state of the mobile terminal 100 such as the open / close state of the mobile terminal 100, the position of the mobile terminal 100, the presence or absence of user contact, the orientation of the mobile terminal, And generates a sensing signal for controlling the operation of the mobile terminal 100. For example, when the mobile terminal 100 is in the form of a slide phone, it may sense whether the slide phone is opened or closed. In addition, whether the power supply unit 190 is supplied with power, whether the interface unit 170 is coupled to the external device may be sensed. The sensing unit 140 may include a proximity sensor 141.

The output unit 150 is for generating an output relating to visual, auditory or tactile sense and includes a display unit 151, an acoustic output module 152, an alarm unit 153, a haptic module 154, 155, and the like.

The display unit 151 displays (outputs) information processed by the mobile terminal 100. For example, when the mobile terminal is in the call mode, a UI (User Interface) or a GUI (Graphic User Interface) associated with a call is displayed. When the mobile terminal 100 is in the video communication mode or the photographing mode, the photographed and / or received video or UI and GUI are displayed.

The display unit 151 includes a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), and a flexible display (flexible). and at least one of a 3D display.

Some of these displays may be transparent or light transmissive so that they can be seen through. This can be referred to as a transparent display, and a typical example of the transparent display is TOLED (Transparent OLED) and the like. The rear structure of the display unit 151 may also be of a light transmission type. With this structure, the user can see an object located behind the terminal body through the area occupied by the display unit 151 of the terminal body.

There may be two or more display units 151 according to the embodiment of the mobile terminal 100. For example, in the mobile terminal 100, a plurality of display portions may be spaced apart from one another, or may be disposed integrally with one another, and may be disposed on different surfaces, respectively.

When the display unit 151 and a sensor for detecting a touch operation (hereinafter, referred to as a touch sensor) form a mutual layer structure (hereinafter referred to as a touch screen), the display unit 151 may be configured in addition to an output device. Can also be used as an input device. The touch sensor may have the form of, for example, a touch film, a touch sheet, a touch pad, or the like.

The touch sensor may be configured to convert a change in a pressure applied to a specific portion of the display unit 151 or a capacitance generated in a specific portion of the display unit 151 into an electrical input signal. The touch sensor can be configured to detect not only the position and area to be touched but also the pressure at the time of touch.

If there is a touch input to the touch sensor, the corresponding signal (s) is sent to the touch controller. The touch controller processes the signal (s) and transmits the corresponding data to the controller 180. As a result, the controller 180 can know which area of the display unit 151 is touched.

The proximity sensor 141 may be disposed in an inner region of the mobile terminal or in the vicinity of the touch screen, which is enclosed by the touch screen. The proximity sensor refers to a sensor that detects the presence or absence of an object approaching a predetermined detection surface or a nearby object without mechanical contact using the force of an electromagnetic field or infrared rays. The proximity sensor has a longer life span than the contact sensor and its utilization is also high.

Examples of the proximity sensor include a transmission photoelectric sensor, a direct reflection photoelectric sensor, a mirror reflection photoelectric sensor, a high frequency oscillation proximity sensor, a capacitive proximity sensor, a magnetic proximity sensor, and an infrared proximity sensor. And to detect the proximity of the pointer by the change of the electric field along the proximity of the pointer when the touch screen is electrostatic. In this case, the touch screen (touch sensor) may be classified as a proximity sensor.

Hereinafter, for convenience of explanation, the act of allowing the pointer to be recognized without being in contact with the touch screen so that the pointer is located on the touch screen is referred to as a "proximity touch", and the touch The act of actually touching the pointer on the screen is called "contact touch." The position where the pointer is proximately touched on the touch screen means a position where the pointer is vertically corresponding to the touch screen when the pointer is touched.

The proximity sensor detects a proximity touch and a proximity touch pattern (e.g., a proximity touch distance, a proximity touch direction, a proximity touch speed, a proximity touch time, a proximity touch position, a proximity touch movement state, and the like). Information corresponding to the detected proximity touch operation and the proximity touch pattern may be output on the touch screen.

The sound output module 152 may output audio data received from the wireless communication unit 110 or stored in the memory 160 in a call signal reception, a call mode or a recording mode, a voice recognition mode, a broadcast reception mode, and the like. The sound output module 152 also outputs sound signals related to functions (e.g., call signal reception sound, message reception sound, etc.) performed in the mobile terminal 100. [ The audio output module 152 may include a receiver, a speaker, a buzzer, and the like.

The alarm unit 153 outputs a signal for notifying the occurrence of an event of the mobile terminal 100. Examples of events that occur in the mobile terminal include call signal reception, message reception, key signal input, touch input, and the like. The alarm unit 153 may output a signal for notifying the occurrence of an event in a form other than the video signal or the audio signal, for example, vibration. The video signal or the audio signal may be output through the display unit 151 or the audio output module 152 so that they may be classified as a part of the alarm unit 153.

The haptic module 154 generates various tactile effects that the user can feel. Vibration is a representative example of the haptic effect generated by the haptic module 154. The intensity and pattern of vibration generated by the haptic module 154 can be controlled. For example, different vibrations may be synthesized and output or sequentially output.

In addition to vibration, the haptic module 154 may be configured to provide a pin array that vertically moves with respect to the contact skin surface, a jetting force or suction force of air through an injection or inlet port, grazing to the skin surface, contact of an electrode, electrostatic force, and the like. Various tactile effects can be generated, such as effects by the endothermic and the reproduction of a sense of cold using the elements capable of endotherm or heat generation.

The haptic module 154 can be implemented not only to transmit the tactile effect through the direct contact but also to allow the user to feel the tactile effect through the muscular sensation of the finger or arm. The haptic module 154 may include two or more haptic modules 154 according to the configuration of the portable terminal 100.

The projector module 155 is a component for performing an image project function using the mobile terminal 100 and is similar to the image displayed on the display unit 151 in accordance with a control signal of the controller 180 Or at least partly display another image on an external screen or wall.

Specifically, the projector module 155 includes a light source (not shown) that generates light (for example, laser light) for outputting an image to the outside, a light source And a lens (not shown) for enlarging and outputting the image at a predetermined focal distance to the outside. Further, the projector module 155 may include a device (not shown) capable of mechanically moving the lens or the entire module to adjust the image projection direction.

The projector module 155 can be divided into a CRT (Cathode Ray Tube) module, an LCD (Liquid Crystal Display) module and a DLP (Digital Light Processing) module according to the type of the display means. In particular, the DLP module may be advantageous for miniaturization of the projector module 151 by enlarging and projecting an image generated by reflecting light generated from a light source on a DMD (Digital Micromirror Device) chip.

Preferably, the projector module 155 may be provided longitudinally on the side, front or back side of the mobile terminal 100. It goes without saying that the projector module 155 may be provided at any position of the mobile terminal 100 as occasion demands.

The memory unit 160 may store a program for processing and controlling the control unit 180 and temporarily store the input / output data (e.g., telephone directory, message, audio, For example. The memory unit 160 may also store the frequency of use of each of the data (for example, each telephone number, each message, and frequency of use for each multimedia). In addition, the memory unit 160 may store data on vibration and sound of various patterns output when the touch is input on the touch screen.

The memory 160 may be a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory), a RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM A disk, and / or an optical disk. The mobile terminal 100 may operate in association with a web storage that performs a storage function of the memory 160 on the Internet.

The interface unit 170 serves as a path for communication with all external devices connected to the mobile terminal 100. The interface unit 170 receives data from an external device or supplies power to each component in the mobile terminal 100 or transmits data to the external device. For example, a wired / wireless headset port, an external charger port, a wired / wireless data port, a memory card port, a port for connecting a device having an identification module, an audio I / O port, A video input / output (I / O) port, an earphone port, and the like may be included in the interface unit 170.

The identification module is a chip for storing various information for authenticating the use right of the mobile terminal 100 and includes a user identification module (UIM), a subscriber identity module (SIM), a general user authentication module A Universal Subscriber Identity Module (USIM), and the like. Devices with identification modules (hereinafter referred to as "identification devices") can be manufactured in a smart card format. Accordingly, the identification device can be connected to the terminal 100 through the port.

The interface unit may be a passage through which power from the cradle is supplied to the mobile terminal 100 when the mobile terminal 100 is connected to an external cradle, or various command signals input from the cradle by a user may be transferred. It may be a passage that is delivered to the terminal. The various command signals or the power source input from the cradle may be operated as a signal for recognizing that the mobile terminal is correctly mounted on the cradle.

The controller 180 typically controls the overall operation of the mobile terminal. For example, voice communication, data communication, video communication, and the like. The control unit 180 may include a multimedia module 181 for multimedia playback. The multimedia module 181 may be implemented in the control unit 180 or may be implemented separately from the control unit 180. [

The controller 180 may perform a pattern recognition process for recognizing handwriting input or drawing input performed on the touch screen as characters and images, respectively.

The power supply unit 190 receives an external power source and an internal power source under the control of the controller 180 to supply power for operation of each component.

The various embodiments described herein may be embodied in a recording medium readable by a computer or similar device using, for example, software, hardware, or a combination thereof.

According to a hardware implementation, the embodiments described herein include application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), and the like. It may be implemented using at least one of processors, controllers, micro-controllers, microprocessors, and electrical units for performing other functions. The described embodiments may be implemented by the controller 180 itself.

According to the software implementation, embodiments such as the procedures and functions described herein may be implemented as separate software modules. Each of the software modules may perform one or more of the functions and operations described herein. Software code can be implemented in a software application written in a suitable programming language. The software code is stored in the memory 160 and can be executed by the control unit 180. [

Organization description

FIG. 2 is a perspective view of a mobile terminal or a portable terminal according to the present invention, as viewed from the front.

The disclosed mobile terminal 100 has a bar-shaped terminal body. However, the present invention is not limited thereto, and can be applied to various structures such as a slide type, a folder type, a swing type, and a swivel type in which two or more bodies are relatively movably coupled.

The body includes a case (a casing, a housing, a cover, and the like) which forms an appearance. In this embodiment, the case may be divided into a front case 101 and a rear case 102. [ A variety of electronic components are embedded in the space formed between the front case 101 and the rear case 102. At least one intermediate case may be additionally disposed between the front case 101 and the rear case 102. [

The cases may be formed by injecting synthetic resin or may be formed of a metal material, for example, a metal material such as stainless steel (STS) or titanium (Ti).

The display unit 151, the audio output unit 152, the camera 121, the user input units 130/131 and 132, the microphone 122, and the interface 170 may be disposed in the terminal body, mainly the front case 101. have.

The display unit 151 occupies most of the main surface of the front case 101. A sound output unit 151 and a camera 121 are disposed in an area adjacent to one end of both ends of the display unit 151 and a user input unit 131 and a microphone 122 are disposed in an area adjacent to the other end. The user input unit 132 and the interface 170 may be disposed on the side surfaces of the front case 101 and the rear case 102. [

The user input unit 130 is operated to receive a command for controlling the operation of the portable terminal 100 and may include a plurality of operation units 131 and 132. The manipulation units 131 and 132 may also be collectively referred to as manipulating portions, and may be employed in any manner as long as the user operates the tactile manner with a tactile feeling.

The contents inputted by the first or second operation unit 131 or 132 may be variously set. For example, the first operation unit 131 receives commands such as start, end, scroll, and the like, and the second operation unit 132 controls the size of the sound output from the sound output unit 152 or the size of the sound output from the display unit 151 To the touch recognition mode of the touch screen.

On the other hand, the textile industry is divided into raw materials from spinning and processing, weaving and knitting, dyeing processing, design, sewing and marketing, so that multi-supply chains create added value through close exchange. Has the structure of.

In addition, due to the increase in domestic production costs, the price competitiveness of the textile industry has reached a limit compared to competitors, which requires differentiation, that is, quality of products, which can only be achieved through a system that guarantees quality.

Quality problems can occur at every stage of production, but the quality of raw materials will have the greatest influence on the competitiveness of the final product. Therefore, in order to secure high quality of finished products, in the production and dyeing process Quality control is very important.

However, most of the unit production sites rely on the quality inspectors' proficiency, they are only sensory inspections such as visual inspections, which makes it difficult to achieve uniform quality, and it is difficult to secure skilled inspectors. It is a situation.

In addition, in order to solve the problem of visual (sensation) inspection, each unit examines the automated inspection device, but there is a problem that it is difficult to introduce and spread the related industry because it is composed of expensive independent inspection devices regardless of domestic and foreign systems. do.

An example related to the quality test result to which the sensory test is applied and the quality test result to which the automation system is applied is shown in Table 1 below.

Referring to Table 1, it can be seen that the quality test results applied with the automation system are superior to the quality test results applied with the sensory test.

However, as described above, it is currently applied to the automated system is used as a stand-alone inspection device, because the stand-alone inspection device is operated separately from the production equipment, despite the excessive cost of introduction ① ① increase in the cost of securing a separate facility space ② The increase of operating personnel and costs due to the addition of the process ③ There is a problem that the quality control efficiency can be reduced due to the time required for quality feedback due to separation from the production process.

Accordingly, the present invention provides an economical product development in the form of add-on that can be used in addition to the existing production equipment, and the image inspection technology (S / W) and the integrated image sensor control system (H) in the quality inspection device. / W) to solve the above problems by integrating the user interface (UI) utilizing the intelligent learning process that has improved the convenience of operation, and to strengthen the competitiveness of the industry and create a new market. do.

However, for convenience of description, the present invention is described assuming that it is applied to the textile industry, but the content of the present invention is not limited thereto, and inspection of a roll type product, fabric inspection, and printing of a web press It is obvious that it can be applied to various fields such as quality inspection, printing quality inspection of sheetfed printing machine, film surface inspection, steel plate quality inspection, and roll type flexible PCB inspection.

On the other hand, prior to the detailed description of the present invention, terms that can be applied to the present invention will be described in advance.

First, the intelligent learning process refers to a process of acquiring a predefined quality standard based on computer learning.

In general, when replacing a work process, a method of inputting a new standard product into a computer and setting an inspection standard according to the standard is applied. In this case, it takes a long time to replace the process, resulting in a decrease in work efficiency. There is this.

On the other hand, when the intelligent learning process is applied, a standard such as setting as a standard when passing the inspection system of a prototype without quality definition may be applied, so that an easier and accurate quality inspection standard may be applied. There is this.

Next, the pixel Pixel refers to the number of pixels of the digital camera.

In addition, an encoder means an apparatus for calculating a feed rate of an object.

Next, an add-on type device means a device that can be installed in addition to an existing production facility, which can bring productivity improvement with spatial efficiency and consistent work.

In addition, a line scan camera (Linescan Camera) is a device for acquiring an image is composed of one line of the pixel is a camera mainly used for the inspection of continuous paper.

Hereinafter, the specific content of this invention is demonstrated.

The present invention consists of a hardware component including a high resolution sensor control integrated line scan camera, and a software component of a high speed data processing algorithm and an intelligent learning process.

Specifically, the hardware applied to the present invention may include a dedicated linescan camera for quality inspection, an encoder synchronization and a controller for controlling the camera, and a synchronous LED lighting unit.

Most roll-type products rely on expensive foreign line scan cameras, are very difficult to spread and spread due to high introduction costs, and area cameras cannot be applied to quality inspection of continuous products. All-in-one line-scan camera hardware, including Camera, Encoder Synchronization, and Camera, solves this problem.

In addition, the software applied to the present invention may include a PLC (existing production facility) interlocking process, a quality inspection program using a fabric pattern analysis algorithm, an Intelligent Learning Process, and the like.

In general, a 1.2-meter wide product is produced at a speed of 2 meters per second, and in order to detect a defect of 0.1 mm level, it is necessary to acquire and analyze about 144MB / second image information to make a positive judgment.

Therefore, in order to do this quickly, multiprocessing can be applied by implementing the fast inspection algorithm in OpenCL.

Basically, Hough Transform and Free Transform are integrated to search for singular frequencies in continuous and repeating patterns.

In addition, it is possible to secure a sufficient database by developing optimized algorithms by acquiring the characteristics of various fabrics.

In addition, by maximizing user convenience by integrating the Intelligent Learning Process, it is possible to increase the efficiency of the productivity, calculate the deviation from the standard sample, and recognize the change of work, thereby facilitating the replacement of the process by simply checking.

As a result, it is guaranteed that productivity can be improved by increasing interoperability with textile machinery by applying various algorithms to existing production facilities.

In addition, the secured high-speed inspection algorithm is expected to increase the applicability to other industries besides textiles and contribute to the dissemination and diffusion of economical inspection systems.

3 is a block diagram showing the flow of fabric pattern matching in connection with the present invention.

As described above, the present invention can be utilized in various manufacturing industries through minor modification in addition to the textile industry. For example, it can be directly applied to the printing industry, and can be immediately used to replace foreign print quality inspection systems which are being actively introduced in recent years.

Hereinafter, hardware components that can be applied to the present invention will be described in detail.

Hardware applied to the present invention may include a line scan camera, synchronous LED lighting and inspection dedicated controller. In other words, hardware in which the line scan camera and the inspection controller are integrated is used.

4 is a diagram illustrating an example of a camera structure diagram according to an embodiment of the present invention.

5 is a block diagram showing an example of the operation of the hardware in which the line scan camera and the inspection controller are integrated in accordance with the present invention.

6 is a view showing an example of a line scan camera according to an embodiment of the present invention.

Hereinafter, hardware applied to the present invention will be described in detail with reference to FIGS. 4 to 6.

First, a linescan camera will be described.

In general, considering that the width of the fabric to be inspected is generally about 120 cm and considering that the size of the defective object to be detected is a defect of class 0.1 mm, the minimum number of pixels is 12,000 pixels (1,200 mm / 0.1 mm). ), It can be configured as a system by connecting three 4K-class cameras.

Next, synchronous LED lighting can be expressed together. Since the line scan camera acquires the image according to the speed of the production line (weaving machine or the inspection machine), that is, the rotational speed of the motor, it is necessary to control the lighting synchronized with the camera. By integrating, material costs can be reduced.

In addition, an inspection only controller may be included. In this case, the inspection-only controller may include a module for inspection program, a camera, a lighting controller, an encoder value calculation, a controller for interface with a loom (or a detector), and the like.

Table 2 below summarizes the specific specifications of the components that can be applied to the hardware described above.

However, the contents described in Table 2 are merely examples of the present invention, and it is obvious that other types of hardware specifications may be applied.

Next, a software component applicable to the present invention will be described in detail.

Software components that may be applied to the present invention may include a fast inspection algorithm and an intelligent learning process.

In the following, with respect to the fast inspection algorithm applied to the present invention, a typical textile inspection application algorithm will be described in detail below.

Fabric damage detection plays a very important role in increasing fabric production efficiency, and automated fabric inspection using computer vision can significantly improve the accuracy and speed of inspection compared to manual fabric inspection by inspectors (humans). have.

First, the characteristics of the general fabric may be classified into a fabric having a pattern and a patternless fabric. Most fabrics with glyphs are damaged by model-based registration techniques, making it difficult to apply general fabric inspection techniques.

Therefore, most automated fabric inspections use a uniform texture of fabric.

Fabric damage can be divided into defects occurring during knitting and defects occurring during weaving. The types of defects occurring during knitting are as follows.

(1) Barrie: Refers to a defect appearing in the shape of a horizontal line in the course direction, which is looser than normal tissue due to tension change.

(2) Broken Needle: It refers to a defect caused in the form of a vertical line because the knitting needle is broken during knitting and no circular ring is formed in the Wale direction.

(3) Fly: Mischief caused by flying of miscellaneous goods during knitting.

(4) Hole: It refers to a defect that occurs due to the fact that the circular ring is not formed locally during knitting or that it is torn by external force after knitting.

(5) Thick Yarn: The thickness of the yarn is thicker than that of the normal part.

(6) Thin Yarn: The thickness of the yarn is thinner than the normal part, and it is a defect that appears in the form of a horizontal line after knitting.

In addition, the types of defects that occur during weaving are as follows.

(1) Gout: A defect in which lumps of short fiber or wind surface enter into a thread or opening. Slubs are generally symmetrical, whereas gouts are a type of defect that consists of a crude mass like an unstretched lump.

(2) Shed-splitting: A type of defect that results in inadequate seeding, resulting in many adverbs, resulting in upsets distracting the opening, causing the slopes to pass up or down to deviate from the tissue design of the fabric.

(3) Slack Warp: A type of defect that is inferior to a woven fabric that is weaker than the specified tension and, when severe, is pulled so that wrinkles or wrinkles appear on the front of the fabric, indicating an incomplete fabric.

(4) Warp Float: A type of defect in which warp and weft yarns do not partially form tissues and incline.

(5) Dragging End: It is a type of defect that is pulled in the inclined direction because of irregular and excessive tension due to matting of warp beam in warp knitted fabric.

(6) Broken End: A defect type that appears when the slope is broken.

(7) Tight End: A type of defect that is woven in a tensioned state and exhibits unusual luster.

(8) Soiled End: A type of warp flaw contaminated by grease or dust.

(9) End Out: It is a type of defect that appears when the slope is out.

(10) Slack End: A type of defect in which one or more warps of the warp are woven weaker than the specified tension, resulting in wrinkles or streaks across the fabric.

7 illustrates representative examples of the types of failures of the specific fabric described above.

In the following, a specific method for detecting a plurality of fabric damages described above will be described.

First fabric damage detection method

First, a fabric damage detection technique using the properties of the localized region can be used.

Damaged areas of the fabric produce changes in brightness or edges, so damage can be easily detected by binarization, morphological operations, or edge detection. As such, the method of directly using the brightness characteristic of the local region has the characteristics as described in Table 3 below.

Second fabric damage detection method

Next, fabric damage detection techniques using frequency characteristics can be used.

In other words, the local characteristics of the damaged part are different from those of the normal part, so Gabor filter or discrete Fourier transform, windowed FT, wavelet transform, etc. can be used. The characteristics of the techniques used are as shown in Table 4 below.

Third fabric damage detection method

In addition, various image processing techniques may be used to detect damage to the fabric.

(One) Fractal  Dimension( fractal dimension Image processing using

Phental geometry uses features that preserve magnetic similarity at different scales, and the quantitative representation of magnetic similarity is the fractal dimension.

This fractal dimension can be expressed as Equation 1 below.

은 각 단계에서 자기 유사성을 가지는 객체의 수이고,

는 크기 요소를 나타낸다.In Equation 1,

Is the number of objects with self-similarity at each level,

Represents the size factor.

(2) threshold binarization ( thresholding Image processing using

에 대한 이진화는 밝기값의 임계치

를 기준으로 두 가지 영역으로 구분하는 방법으로, 전경과 배경을 구분하거나 정상과 손상을 구분할 수 있다. Input image

The binarization for is the threshold of the brightness value.

By dividing the area into two areas, you can distinguish between foreground and background or normal and damage.

는 하기의 수학식 2와 같이 나타낼 수 있다.Thus binarized image

Can be expressed as in Equation 2 below.

 In addition, if the contrast of the damaged part has a large difference from the brightness value band of the normal texture area, the area may be divided into two threshold values as shown in Equation 3 below.

(3) histogram smoothing histogram equalization Image processing using

Histogram smoothing is a technique that improves the contrast by smoothing the frequency distribution expressed by the brightness value and is used in the preprocessing process.

가 된다. By histogram smoothing, the k- th brightness value of the original image is changed to the new brightness value as shown in Equation 4.

.

는 확률 분포 함수를 의미한다. In Equation 4,

Denotes a probability distribution function.

(4) Sobel  Operator( Sobel operator Image processing using

방향의 구배도와

방향의 구배도의 성분으로 계산할 수 있으며, 소벨 연산자는 도 8에 도시된 것과 같은 컨볼루션 마스크(convolution mask)를 사용할 수 있다.Sobel operator is the most widely used technique to calculate gradient in two-dimensional images. The gradient of the 2D image is

Gradient of direction

It may be calculated as a component of the gradient of the direction, and the Sobel operator may use a convolution mask as shown in FIG. 8.

(5) Average filter mean filter Image Processing Using

,

등으로 확장하여 사용될 수도 있다. The average value filter is a low pass filter (LPF) that converts the average brightness value of the surroundings. Therefore, by the average filter, the image of the texture is blurred overall, but the texture image of the texture with a small change can eliminate the effect of the texture. The simplest form of such an average value filter is shown in Figure 9,

,

It may be extended to and the like.

(6) the median filter ( median filter Image processing using

The median filter is a filter that selects a brightness value having a middle rank among neighboring pixel values, and may reduce the blurring result compared to the average filter.

Such a median filter may be used to remove noise of the original image or to remove a small noise region from a damage detection result.

(7) DC Notch  filter( DC notch filter Image processing using

The DC notch filter may be calculated as shown in Equation 5 below as a filter for removing the DC component of the local region.

If it is difficult to binarize an entire area with a single threshold due to differences in local lighting conditions, it can be used as a pretreatment process.

(8) morphological operations ( morphological operation Image processing using

Morphological treatments are handled by structuring elements of various shapes in a manner that processes structural forms. Such morphological processing can basically use the expansion of Equation 6 and the erosion operation of Equation 7 below.

는 입력 영상을 의미하고,

는 구조 요소를 의미한다. 또한

는 공집합을 의미하고,

는

의 반전이다.Generally in Equations 6 and 7

Means input video,

Means structural element. Also

Means an empty set,

The

Is the reverse of.

In addition, an extended operation using expansion and erosion may be closing and opening, and may be defined as in Equations 8 and 9 below.

In addition, expansion and erosion of the grayscale image may be defined as in Equations 10 and 11 below.

와 구조 요소

에 대한 형태학적 연산이며,

와

는 각각 f와 b의 정의역을 나타낸다.Equations 10 and 11 are 2-D grayscale images

And structural elements

Is a morphological operation on,

Wow

Denotes the domain of f and b , respectively.

(9) Discrete Fourier Transform ( discrete Fourier transform , DFT Image processing using

에 대한 이산 푸리에 변환은 하기의 수학식 12와 같이 계산할 수 있다.Two-dimensional image

The discrete Fourier transform for may be calculated as in Equation 12 below.

The result of equation (12) represents a signal in the spatial frequency band. In Equation 12, the uniformly textured fabric has a constant size at the same frequency.

(10) local Fourier transform ( windowed FT Image processing using

The local Fourier transform is a combination of a window function having a constant size and a Fourier transform, and the frequency characteristic of the local region can be checked. Therefore, uniformly textured textile images can be processed faster than DFT, and even the location of damage can be detected.

(11) Discrete Cosine Transform discrete cosine transform , DCT Image processing using

The discrete cosine transform may be calculated as in Equation 13 below and may be used instead of the discrete Fourier transform (DFT) described above.

DCT has the advantage of easy operation and analysis compared to DFT because DCT has only real area, not complex form.

(12) Gabor  filter( Gabor filter Image processing using

The Gabor filter can be obtained through Equation 14 below.

는 정현파의 파장,

는 가버 함수에서 줄무늬의 회전각,

는 위상의 변위,

는 가우시안(Gaussian) 함수의 표준 편차,

는 공간 측면 비율을 나타낸다.In Equation 14

Is the sinusoidal wavelength,

Is the angle of rotation of the stripes in the Gabor function,

Is the displacement of the phase,

Is the standard deviation of the Gaussian function,

Represents the spatial aspect ratio.

Fourth fabric damage detection method

Next, a method of detecting fabric damage by edge detection may be used.

Fig. 10 is a diagram showing an example of fabric damage detection results by edge detection in connection with the present invention.

Referring to FIG. 10, it can be seen that the detection of fabric damage by edge detection can guarantee the advantage that an edge detector (Sobel, canny, etc.) can easily detect damage occurring in a straight form.

Fifth fabric damage detection method

In addition, an application damage detection method using morphological operations may also be used.

11 is a view showing an example of the fabric damage detection results by morphological calculations in connection with the present invention.

12 is a view showing another example of the fabric damage detection result by the morphological calculation in connection with the present invention.

That is, FIGS. 11 and 12 illustrate the results of applying the method of detecting the damage to the fabric by performing the opening operation and the closing operation, and binarization.

The original image of FIG. 11 is an image in which damage is added to an artificially created fabric texture, and the original image of FIG. 12 represents an actual image. Thus, the actual fabric image may require additional post-processing operations (eg, median filter operations, binarization operations, etc.) after performing morphological operations.

6th fabric damage detection method

In addition, a method of detecting fabric damage by using a mean filter or a Gaussian filter directly on a fabric image without removing morphological operations may be used. It may be.

It is a figure which shows an example of the fabric damage detection result by an average value filter with respect to this invention.

It is a figure which shows another example of the fabric damage detection result by an average value filter with respect to this invention.

Referring to FIGS. 13 and 14, it is possible to confirm specific contents of the fabric damage detection result to which the average value filter is applied.

7th fabric damage detection method

In addition, an application method using the frequency characteristic may be applied.

15 is a view showing an example relating to the frequency characteristics of an intact textile image in relation to the present invention.

16 is a view showing an example relating to the frequency characteristics of a damaged textile image in connection with the present invention.

The method using the frequency characteristic is suitable for the case where the yarn appears periodically, and the periodic characteristic is shown in the discrete Fourier transform (DFT) or discrete cosine transform (DCT) as shown in FIG. 15. It shows the same characteristics at a constant frequency position.

In addition, as a result of the DFT and DCT of the damaged image is different from the characteristics of the non-damaged fabric, as shown in Figure 16, it is possible to determine the damage.

8th fabric damage detection method

On the other hand, since the expression of frequency and rotation is similar to the human visual system, the Gabor filter can be very useful for expressing or classifying textures.

Gabor filters are therefore a widely used method for fabric damage detection.

It is a figure which shows an example of the fabric damage detection result using a Gabor filter with respect to this invention.

Referring to FIG. 17, an example of generating a Gabor filter mask according to a specific frequency and rotation angle and performing filtering to detect damage is shown.

The frequency and rotation angle of the Gabor filter can be determined by pre-trained results for the inspection fabric, and several filters can be applied simultaneously using various parameters.

In the following, a specific process of inspecting the fabric using the fabric damage detection method described above will be described.

18 is a diagram illustrating an example of a fabric inspection technique flow in accordance with an embodiment of the present invention.

Referring to FIG. 18, first, a fabric inspection performs a process of converting a one-dimensional line image to grayscale.

Thereafter, inspection is performed in units of pixels, and the inspection criteria of each pixel may be determined by comparing the characteristics of the trained data and the characteristics of the input fabric image.

Thereafter, the damage detected in units of pixels is calculated in units of lines, and the calculated results are continuously stored.

In addition, it is possible to continuously compare the input one-dimensional line image to extract the area information, and to store the extracted area information, it is possible to obtain the final damage detection result value of the area unit.

A process of converting the one-dimensional line image to grayscale described above with reference to FIG. 18 will be described in more detail.

The gray scale conversion of the 1D image may be performed by (1) independently performing the pixel unit and (2) using the image characteristic.

Independent pixel-by-pixel methods are simply red (R, red), green (G, green),

It may include a method of using the average of the blue (B, blue), or to calculate the luminance (Y, luminance) as shown in Equation 15 below to convert to a grayscale.

On the other hand, the method using the characteristics of the image is a method of determining the weight of the red, green, blue by using the distribution of red, green, blue used in the image.

If an image obtained by a camera having different pixel characteristics differs in brightness of each color element according to a horizontal position. Therefore, since it may be difficult to find the damage location at a certain threshold, if the image is divided into red, green, and blue elements, unique characteristics can be seen.

In particular, the characteristics of the red element may exhibit a very sensitive characteristic depending on the position compared to the other elements.

In addition, damage locations may be found in grayscale images using luminance, and image characteristics may be used. In other words, a transformation may be needed to narrow the wider color distribution.

Next, a method of performing an inspection in units of pixels described above with reference to FIG. 18 will be described in detail.

As a method of performing inspection on a pixel basis, a method of considering a correlation difference may be used.

Since the fabric image has a constant correlation in the horizontal direction, if the difference in the correlation with the surrounding pixels is large, it can be designated as the damage position.

Therefore, in the present invention, since the sensitivity is increased when the difference with the surrounding pixels is calculated in pixel units, the difference with the surrounding pixels is calculated to calculate the difference with the surrounding pixels after filtering by the average value, and to compensate for the sensitivity lowered by the average filter. A method of determining the largest value as the difference in correlation may be used.

)에 대한 주위 평균값을

라고 하면, 각 위치(

)에서의 상관도 차이는 하기의 수학식 16을 이용하여 계산할 수 있다.Input line image (

For the mean

Speaking of each position (

The difference in correlation can be calculated using Equation 16 below.

은

의 주위에서 와 가장 차이가 큰 를 가지는 위치를 나타내고,

를 계산하기 위한 주위값의 범위(

)와

을 찾기 위한 주위값의 범위(

)는 영상의 크기와 검출할 손상의 크기에 따라서 설정값을 다르게 지정될 수 있다.In equation (16)

silver

Represents the position of with the largest difference between and

The range of ambient values to calculate

)Wow

Range of values to find

) Can be set differently according to the size of the image and the size of the damage to be detected.

는 동적 프로그램에 의해 계산된다.Also, to detect damage in real time

Is calculated by dynamic program.

Fabric images that do not have patterns show large differences in correlation at damaged locations.

On the other hand, in the case of the patterned fabric image, the correlation difference is large at most locations but is larger than the surroundings at the damaged locations.

Therefore, in order to use this technique in various images, it is necessary to grasp the characteristics of the fabric image in advance and apply a threshold differently according to the fabric.

)에 의해 손상된 위치를 쉽게 검출할 수 있다. On the other hand, fabric images without glyphs have a low threshold (

) Can easily detect the damaged position.

)로는 많은 오 검출(false alarm)을 보이며, 높은 임계치(

)로는 많은 오 검출을 줄일 수 있다.However, fabric images with patterns have low thresholds (

) Shows a large number of false alarms and a high threshold (

) Can reduce many false detections.

In addition, in the present invention, the threshold levels of the three stages (7, 14, 21) are determined by training several fabric images, and the threshold determination method may be applied differently according to the magnitude of the standard deviation of the line image. have.

That is, a low threshold is applied to a line image having a low standard deviation, and a high threshold is applied to a line image having a high standard deviation.

The pixel detected at the threshold determined as described above becomes a pixel indicating damage.

Since the detected damaged pixels include various false detections, in the next step, damages vertically connected to vertically connected damages are judged to perform final damage detection.

In addition, a method of calculating the above-described damage detected in units of pixels in units of lines will be described in detail with reference to FIG. 18.

In the present invention, a method of finding a damage location horizontally connected in the damage detection process of the line image may be used.

The damaged position connected horizontally is designated as the damaged line region when the detected detection length is longer than the threshold when the pixel x currently being inspected is not detected as the damage and the previous pixel x-1 is detected as the damage.

Damage detection (line) can be processed quickly because it is processed simultaneously with damage detection (pixel), and is performed independently on the current line image.

는 시간(t)에 따라 계속 입력되므로, 2차원 영상

로 표현할 수 있다. Also, line image

Is continuously input over time ( t ), so the two-dimensional image

.

에 표현되지만, 최종 결과는

에 표시되어야 한다.Damage detected in the above process

But the final result is

Should be indicated in.

19 is a diagram illustrating an example related to a process of connecting and creating a damaged area according to an embodiment of the present invention.

에서 새로운 선손상이 발견되고, 이전

에서 갱신된 손상 영역과 수평방향으로 겹쳐있다면 손상 영역을 갱신하고, 겹쳐진 손상 영역이 없으면 새로운 손상 영역을 생성한다.Referring to FIG. 19, the damaged area may be designated as a rectangular area to display a final damaged area. At this time

New line damage is found in

Updates the damaged area if it overlaps the updated damaged area in the horizontal direction, and creates a new damaged area if there is no overlapped damaged area.

In addition, if the vertical length of the damaged area is equal to or less than a certain size, the damaged area is removed from the damaged area, and the damaged area is merged with adjacent areas to generate a final damaged area.

In this process, damaged information is linked up and down, which can eliminate many false detections in the previous line damage area.

Returning to the specific software description of the present invention, another software component applicable to the present invention is described.

As mentioned above. Software components that can be applied to the present invention include a fast inspection algorithm and an intelligent learning process.

Hereinafter, an intelligent learning process applied to the present invention will be described in detail.

The intelligent learning process includes both a sheet test or a roll test method.

Intelligent Learning Process is an inconvenient process that takes a lot of time in the process of replacing the work by manually setting the work contents and acquiring the sample image that becomes the inspection standard when the existing system changes the work contents when inspecting the object. It is to solve the problem.

In other words, the Intelligent Learning Process recognizes the process as a replacement if a video that is markedly different from the standard sample image originally set up is replaced. By significantly shortening the time required, it is to provide the effect that the productivity can be improved.

In addition, when the intelligent learning process is applied, it can be immediately applied to a job by simple operation regardless of the number of products to be inspected, so that the process of passing the inspection system to obtain a standard image can be omitted. Therefore, the effect of enabling cost reduction and shortening of working time can be provided.

Through the above-described line scan camera with integrated image sensor control of the present invention and the software using the intelligent learning process, very precise defects (for example, defects of 0.1 mm) can be detected at a very high speed (for example, at a maximum per second). 2 meters).

In addition, the present invention can be implemented in an add-on type that can be applied in addition to the existing production equipment, it is also ensured the effect of reducing costs.

The object to which the present invention is applied includes a checker (printing, dyeing), and when a defect occurs, a method of identifying a defect position through a tape inserter may be additionally applied.

In addition, atypical stains may be distinguished (eg, using unit area increase or decrease) according to the difference expression from the standard (sample).

In addition, a method of detecting defects of the same color through transmission and reflection lighting in a bidirectional design of illumination may be used.

In addition, according to one embodiment of the present invention, the finally detected result value may be provided to the user through the display unit. Furthermore. When the present invention includes the wireless communication unit described above with reference to FIG. 1, a result value finally detected by an external device designated by a user may be transmitted under the control of the controller.

Further, according to an embodiment of the present invention, the above-described method can be implemented as a code that can be read by a processor on a medium on which the program is recorded. Examples of the medium that can be read by the processor include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, etc., and may be implemented in the form of a carrier wave (e.g., transmission over the Internet) .

The above-described mobile terminal and its control method are not limited to the configuration and method of the above-described embodiments, but the embodiments may be modified such that all or some of the embodiments are selectively And may be configured in combination.

Claims (15)

A user input unit for receiving a reference image;
A scan camera for successively obtaining a first image of at least one object; And
And a controller configured to determine whether the at least one object is damaged by using the reference image and the first image according to a preset algorithm.
And when the result of comparing the reference image with the first image exceeds a preset range, the controller controls the first image to be set to be changed to the reference image. The method of claim 1,
The scan camera includes a plurality of cameras,
Further comprising synchronous illumination to assist each of the plurality of cameras to acquire the first image,
The control unit, characterized in that for controlling the operation timing (timing) of the plurality of cameras and synchronous lighting. The method of claim 1,
The preset algorithm uses a change in brightness of a predetermined area included in the reference image and the first image,
The preset algorithm includes at least one of a fractal dimensional technique, a threshold binarization technique, a block averaging technique, and a morphological operations technique. The method of claim 1,
The preset algorithm uses a frequency change of a predetermined region included in the reference image and the first image,
The preset algorithm includes at least one of a binary Fourier transform technique, a local Fourier transform technique, and a Gabor filter mask technique. The method of claim 1,
The controller converts the first image into a grayscale image, compares the converted grayscale image with the reference image in pixel units, and determines whether the at least one object is damaged. Characterized by a quality inspection device. The method of claim 1,
Further comprising a memory,
When there is damage to the at least one object, the controller detects the damage-related information in pixel units, calculates the information detected in pixel units in line units, and calculates in line units. And control the stored information to be continuously stored in the memory. The method according to claim 6,
And the controller extracts area unit information by combining a plurality of line unit information continuously stored in the memory. 8. The method of claim 7,
And a display unit,
And the control unit controls the area unit information to be displayed on a predetermined area of the display unit. 8. The method of claim 7,
Further comprising a wireless communication unit,
And the control unit controls the area unit information to be transmitted through the wireless communication unit to an external device designated through the user input unit. Receiving a reference image;
Continuously obtaining a first image of at least one object;
Determining whether the at least one object is damaged using the reference image and the first image according to a preset algorithm; And
And controlling the first image to be changed and set as the reference image when a result of comparing the reference image with the first image exceeds a preset range. The method of claim 10,
The preset algorithm uses a change in brightness of a predetermined area included in the reference image and the first image,
The predetermined algorithm includes at least one of a fractal dimensional technique, a threshold binarization technique, a block averaging technique, and a morphological operations technique. The method of claim 10,
The preset algorithm uses a frequency change of a predetermined region included in the reference image and the first image,
The predetermined algorithm comprises at least one of a binary Fourier transform technique, a local Fourier transform technique, and a Gabor filter mask technique. The method of claim 10,
The determining of whether the at least one object is damaged may include converting the first image into a grayscale image and comparing the converted grayscale image with the reference image in pixel units. A control method for a quality inspection device, characterized in that used. The method of claim 10,
If the at least one object is damaged, detecting the damage related information in a pixel unit;
Calculating the information detected in the pixel unit in the line unit; And
And controlling the information calculated in units of lines to be continuously stored in a memory. The method of claim 14,
And extracting area unit information by combining a plurality of line unit information continuously stored in the memory.

Images