JP2010127809A - Visual inspection apparatus, visual inspection system, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To facilitate comparison and monitoring of information on an identical defect. <P>SOLUTION: An visual inspection apparatus includes a determination means for acquiring image data imaged by a plurality of camera devices disposed longitudinally along a roll paper transfer direction and performing image recognition processing for each image data from each camera device to determine whether there is a defect, a defect information creation means for clipping images containing the defect when the defect is detected by the determination means and creating defect information associating the clipped images with position information identifying a position of the detected defect, and a processing means for output of the defect information to a display device. The processing means includes functions to extract the defect information on the identical defect imaged by different camera devices from the position information and output the clipped images (defect images) as to the extracted defect simultaneously to an identical display screen (defect time series display screen shown in the figure). <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an appearance inspection apparatus, an appearance inspection system, and a program for inspecting the appearance of a sheet-like material (article) such as paper, film, nonwoven fabric, steel, and non-ferrous metal.

  In a manufacturing system for paper (roll paper) and other sheet-like materials, the presence or absence of foreign matter or perforations is monitored in real time in the production process in order to maintain quality. A monitoring system (inspection system) for monitoring the presence or absence of such defects includes, for example, cameras installed in various parts of the manufacturing process, and the inspection apparatus performs image recognition processing based on image data obtained from the cameras, and whether or not there are defects. In some cases, if there is a defect, information about the defect is output to a display device so as to notify the monitoring staff (operator).

The information displayed on the display device includes position information for specifying the defect position, text information indicating the size (vertical / horizontal length and area, etc.), the type of defect, and image information that is actual image data. is there. In this display layout, for example, as shown in FIG. 1, the text information is in a tabular form in which information related to one defect is shown in one column, and the image information has a predetermined number (three in the figure) in another frame. I am trying to output. Text information is sequentially output in the order of detection. Similarly, the latest predetermined number (for example, three) of image information is output. An inspection system for inspecting a sheet-like object such as paper for the presence or absence of defects by this type of image recognition processing is disclosed in, for example, Patent Document 1 and the like.
Japanese Patent No. 398646

  Image data to be subjected to image recognition processing is reflected light or transmitted light of an inspection object such as paper, and is an area sensor camera that captures two-dimensional image data, a one-dimensional line sensor camera, etc. Acquire using "Camera"). In order to inspect both the front and back surfaces of the object to be inspected, and to verify which process caused the defect because the object to be monitored such as paper is manufactured through a plurality of processes. In order to inspect an object to be inspected immediately after processing, a plurality of cameras are often installed.

  Then, if a defect occurs in a certain upstream process, the defect will appear after each subsequent process, and the same defect exists in the image data acquired by a plurality of cameras. Become. Therefore, each time the same defect is detected as image data by each camera, it is detected as a defect at the detected timing and output to the display device. On the other hand, the cameras are scattered in various parts of the production line, and in the roll paper production line, the total length is often 100 m or more, so the same defects were obtained with individual cameras. The timing of appearing in the image data is greatly shifted. Moreover, when a defect occurs in a certain process, only one defect may occur, but a plurality of or many defects may occur in a certain range.

  Then, on the display device, information on defects detected by a plurality of cameras will be displayed while being updated from moment to moment, especially when the number of cameras installed increases, the defect information increases, On the contrary, it is impossible to properly monitor without being organized.

  Furthermore, after the defect information detected by a camera for the same defect is displayed, a time lag occurs between the time when the defect information detected by the next camera is displayed, and the defect information for another defect in the meantime. Is often displayed, and it is difficult to examine in which production process one defective defect occurred and how it changed. As a result, it is impossible to confirm at a glance the inspection results from the upstream to the downstream of the production process as to how the production has been affected. In other words, simply increasing the number of cameras installed to increase the amount of information that can be obtained does not provide sufficient feedback to each production process.

  The present invention can easily compare and monitor information on the same defect, and can appropriately provide information for facilitating analysis of defects on the production line and feedback to the production process. An object is to provide an appearance inspection apparatus, an appearance inspection system, and a program.

  In order to achieve the above object, an appearance inspection apparatus according to the present invention is (1) an appearance inspection apparatus for a sheet-like article such as paper, and includes a plurality of front and rear arrangements along the conveyance direction of the article. When acquiring image data captured by the camera device and performing image recognition processing in units of image data from each camera device to determine the presence or absence of a defect, An image including a defect is cut out, and defect information creating means for creating defect information in which the cut image is associated with position information for specifying the position of the detected defect, and imaged by different camera devices based on the position information. And a processing unit that extracts defect information about the same defect and outputs an image cut out for the extracted defect to the same display screen at the same time. The position information is incorporated in a part of the attached information / processing attached information of the embodiment. The determination means corresponds to the detection rack unit 21 in the embodiment. The defect information creating means is realized by the detection rack unit 21 and the defect processing unit 22 in the embodiment. In the embodiment, once the image is cut out by the detection rack unit 21 and the raw data of the associated information (position information) is created, the defect processing unit 22 uses the raw data to easily understand the data (processing) (Incidental information) is created (in the case of position information, the raw data of “pulse values and bits” is converted into intuitive data such as “m and mm”). In this way, the processing is not limited to two processing means, but the functions of both are performed together by one processing means, additional processing information is obtained directly, or conversely, raw data is left as it is. Various methods can be taken. In the embodiment, the line sensor camera is used as the camera device, but an area sensor camera may be used. In addition, in the embodiment, since the width is wide like roll paper, one camera device is configured by a plurality of line CCD cameras. However, the single camera device is independent from the relationship between the width of the article to be inspected and the field of view of the camera. Of course, it may be configured with a camera.

  In the visual inspection apparatus of the present invention, images (cut-out images) that are regarded as having the same defect detected in image data captured by different camera devices are simultaneously displayed on the same screen, so the operator is the same Information about defects can be easily compared and monitored. As a result, by comparing them, it is possible to identify from which timing (process) on the production line the defect has occurred and from the change in the state of the displayed defect image (size, shape, other characteristics, etc.) Analysis of the relationship between each process can be performed quickly and easily. Since the image of the same defect is estimated and extracted based on the position information, it can be easily extracted.

  (2) The position information is the position in the front-rear direction along the conveyance direction of the article and the position from the side edge in the width direction of the article. Extraction of defect information for the same defect is specified by the position information. When the position of the defect is within the allowable range, it is estimated that the defect is the same, and the allowable range may be larger than the allowable range for the position from the side edge. . In the transport direction (flow direction), the processing of each process may cause the article itself to expand and contract, and in the case of a scroll, the length becomes very long compared to the width direction, and the error also increases. Therefore, by setting a wide allowable range for the position in the front-rear direction, it is possible to reliably extract and display an image based on the same defect.

  (3) When there are a plurality of candidates estimated as defect information for the same defect, the processing means outputs one of the plurality of candidates to the display device as an initial candidate, and a switching instruction given from the outside It is preferable to provide a function for displaying other candidates according to the above. For example, the initial candidates may have the same position information (the smallest deviation). When a plurality of defects such as holes and foreign matters occur nearby, it may be difficult to uniquely identify the same defect image. In addition, as described in (2), the position where the same defect exists (position in the front-rear direction (distance from the front edge of the paper, inspection start position, etc.)) due to the expansion and contraction of the article is the imaging position of each camera device. It may be different. Therefore, the processing means does not specify one thing, but when there are a plurality of candidates, they can be switched and displayed, and a human being such as an operator makes a final decision, thereby making it more reliable. , Images of the same defect can be displayed simultaneously. Although it is possible to add an algorithm that compares feature quantities such as the defect shape and shape and identifies the image of the same defect, the size and shape of the defect itself can be changed by performing each process. Therefore, it is preferable to specify based on the position.

  (4) The defect information created by the defect information creating means has text information indicating the feature of the defect including the dimension of the defect, and the processing means displays the corresponding text information together with the cut image. It is good to do so. In this way, by combining defect information other than the image, it is possible to analyze the defect more easily and to be a reference for determining whether the images are based on the same defect.

  (5) The appearance inspection system according to the present invention operates based on a plurality of camera devices arranged at the front and rear along the conveyance direction of the article in the sheet-like article production line, and outputs from the plurality of camera apparatuses. The visual inspection apparatus according to any one of (1) to (4) can be configured.

  (6) The program of the present invention obtains image data captured by a plurality of camera devices arranged in the front and back along the conveyance direction of the article, and images in units of image data from each camera device. A determination unit that performs recognition processing to determine the presence or absence of a defect, and when a defect is detected by the determination unit, an image including the defect is cut out, and the extracted image and position information that identifies the position of the detected defect And defect information creation means for creating defect information associated with the same, and based on the position information, the defect information for the same defect imaged by different camera devices is extracted, and the same image is displayed for the extracted defect It can be set as the program for functioning as a processing means which outputs simultaneously on a screen.

  In the present invention, an algorithm for determining the same defect is provided, and images detected by the camera devices of a plurality of inspection frames are displayed simultaneously on the same screen, so that information on the same defect can be easily compared and It is possible to monitor and appropriately provide information for facilitating the analysis of defects on the production line and the feedback to the production process.

  FIG. 2 shows a preferred embodiment of the present invention. The appearance inspection system according to the present embodiment is incorporated into a paper (roll paper) production line and has defects based on image data obtained by imaging a strip-shaped paper that is an object to be inspected that is conveyed on the production line. This is to determine the presence or absence of (defect).

  Specifically, a plurality of camera devices 10 are installed facing the paper 1. Each of the camera devices 10 is composed of a camera assembly in which a plurality of line CCD cameras 11 are arranged in a horizontal row. A plurality of line CCD cameras 11 mounted on the one camera device 10 are arranged so as to detect on the same line, that is, on a straight line perpendicular to the traveling direction (crossing in the width direction) of the paper 1. .

  Further, in the figure, for convenience, three camera devices 10 are provided at equal intervals and are arranged on the same surface side of the paper 1, but in reality, the appearance of the front surface and the back surface of the paper 1 should be detected. In some cases, they may be arranged on different planes, and the arrangement interval differs appropriately depending on the arrangement layout of the apparatus performing each step. In other words, the roll paper production line is, for example, a process in which a liquid containing paper fibers which have been bleached and boiled and dissolved is placed on a net for dehydration → a roll in which dehydrated wet paper is pressurized The process of squeezing with felt in between → The process of drying the paper → The process of surface treatment such as coating on the surface of the dried paper → The process of adjusting the thickness → The belt is continuously conveyed A plurality of processes such as a process of winding the paper is sequentially performed, and processing devices for performing each process are arranged in various places in the production factory. The total length may be 100 m or more, and the camera device 10 is disposed on the downstream side of a predetermined processing device. The camera device 10 detects transmitted light or reflected light and adjusts the amount of light and other parameters in order to obtain image data suitable for the type of defect to be detected at the installed position.

  The output of each camera device 10 (line CCD camera 11) is sequentially supplied to the image recognition processing device 20 in real time. The image recognition processing device 20 is configured by a personal computer or a dedicated device, and includes a detection rack unit 21, a defect processing unit 22, and a data processing unit 23. Image data sent line by line from each camera apparatus 10 is given to the detection rack unit 21. The detection rack unit 21 is also supplied with a pulse output from an encoder connected to a drive system of a transport device that transports the paper 1 constituting the production line. The image recognition processing device 20 has, as initial data, the distance of the paper 1 that travels in one pulse cycle, and by multiplying the distance by the number of pulses, the position of the image data (line) imaged by the camera device 10, That is, the distance from the arbitrary inspection start position to the captured image data can be obtained.

  The detection rack unit 21 stores image data for each line input from the camera device 10 every moment in a temporary storage memory, reads out image data for n lines, and obtains secondary plane image data having a predetermined size. A recognition target image is generated, image recognition processing is performed on the recognition target image, and the presence / absence of defects such as foreign matter adhesion and perforations is determined. When a defect is detected, image data of a predetermined size (for example, 256 × 256) including the defect is cut out, and the defect processing unit 22 associates the cut-out image data with the attached information about the defect. To pass. As an image recognition processing algorithm for recognizing the presence or absence of a defect, the one described in Patent Document 1 and other various algorithms can be used. The detection rack unit 21 includes, as attached information for identifying the detected defect, a pulse value of the existing position (obtained from the encoder) and a position in the field of view (position from one side edge of the paper (n bits): Since the distance from one side edge of the paper to one end of each line CCD camera 11 is known, it is obtained by adding the position of the defect from the end of the imaged line CCD camera 11 to the distance) Width and length (front-rear direction), camera No. (beam No.) for identifying the camera, light / dark information (such as “bright / dark” + degree) as a feature of the defect, and the like. The obtained attached information is transferred to the defect processing unit 22 as a table having a data structure as shown in FIG. Note that the attached information calculation (extraction) process can be realized by a process similar to the conventional one.

  Further, since the line CCD camera 11 acquires image data for each line, in order to generate a two-dimensional recognition target image as described above, it is necessary to read out image data for a plurality of lines collectively. There is. Therefore, for example, a ring buffer for the line CCD camera 11 is prepared, the image data sent from each line CCD camera 11 is distributed and stored in the corresponding ring buffer, and a predetermined line is read from each ring buffer. Yes.

  The defect processing unit 22 processes the attached information about the defect sent from the detection rack unit 21 into data that can be recognized by a human (operator), and sends the obtained processing attached information to the data processing unit 23. The data structure of the processing attachment information includes, for example, a position in the front-rear direction (winding length data) for specifying the defect position and distance data from one side edge of the paper (this distance from the paper edge is referred to as “FR distance”). ), A defect width and a defect length for specifying the dimension of the defect, a camera No., brightness information, and the like. The data related to the length is generated by the detection rack unit 21 and is raw data, so its unit is the number of bits, the number of pulses, etc. In this defect processing unit 22, humans such as m and mm are easy. It is converted to a unit that can be recognized. Specifically, the initial data includes the distance of the paper 1 that travels in one cycle of the pulses output from the encoder, and the current position in the length direction of the paper is obtained from the number of pulses from the arbitrary inspection start position. be able to. Therefore, the defect processing unit 22 can obtain the distance (winding length) from the inspection start position of the paper 1 at the position where the defect occurs by multiplying the pulse value by the movement length per pulse. . Further, since the defect position specified by the number of pixels and the number of bits and the size of the defect know the length (mm) per pixel and 1 bit, the unit is obtained from the raw data of the detection rack unit 21. Convert to a numerical value in units of m or mm. Thereby, for example, processing attachment information having a data structure as shown in FIG. 5 is generated and stored in the storage device 31. The processing ancillary information calculation (extraction) process can be realized by a process similar to the conventional process. The processing (correction) attached information stored in the storage device 31 is assigned a record number (described at the left end in the figure) in the order of detection, and stored in that order.

  The data processing unit 23 is information (image / text) that matches a predetermined condition based on the image data (cut-out data including the defect) created by the defect processing unit 22 and stored in the storage device 31 and the processing attached information. Is output to the display device 30. The layout of defect information (image data + text data) displayed on the display screen of the display device 30 can be the one shown in FIG. This is displayed in the order of detection, that is, in the order of record numbers. Therefore, a predetermined number of pieces of processing attached information made up of text information are displayed from the latest information, and the display content is updated when a new defect is detected. Similarly, the latest three pieces of cut-out image data are displayed. Note that these display layouts and display methods are the same as those in the prior art.

  Here, in the present embodiment, a defect time series display screen as shown in FIG. 3 is prepared so that defect information (image + text) regarding the same defect detected by different camera devices 10 can be displayed side by side. . In the present embodiment, since six camera devices 10 are provided, six small windows W are prepared on the defect time series display screen so that image data captured by each camera device 10 can be displayed respectively. ing. The camera apparatus 10 displayed in each small window W is matched with the production line in order, and the most upstream camera apparatus (beam name A) is associated with the rightmost small window W. Hereinafter, the production line flow (paper) The camera devices installed in accordance with the transport direction) are sequentially associated with the left small window W, and the most downstream camera device is associated with the left small window W.

  Each small window W is provided with a defect image display area W1 on the lower side and a text information display area W2 on the upper side. Further, on the outer left side of these display areas W1 and W2, there are NEXT selection buttons B1 and B2, The layout configuration in which the screen button B3 is arranged is adopted. The defect image display area W1 is an area where image data including the cut out defect is displayed. The text information display area W2 is an area for displaying the processing attached information associated with the image data displayed in the defect image display area W1. The NEXT selection buttons B1 and B2 read and display other image data by clicking these NEXT selection buttons B1 and B2 when there are a plurality of image data that appear to be the same defect. When the image data displayed in the defect image display area W1 is switched, the information displayed in the text information display area W2 is switched accordingly. When the initial screen button B3 is clicked, the image data estimated to be the same defect in the initial state is selected and displayed. When there are a plurality of image data that are considered to be the same defect, the number of candidates is displayed below the NEXT selection button B1 and above the NEXT selection button B2. That is, when there is no other image data, it is “0”, and when it exists, the number is displayed as a numerical value. In the case of FIG. 3, since the two small windows W on the left side are both displayed with “1” below the NEXT selection button B1 and “2” above the NEXT selection button B2, each NEXT selection is displayed. By clicking the buttons B1 and B2, the image to be displayed can be switched. In accordance with the switching, the numerical values are respectively updated by ± 1. In this way, by switching the image data to be displayed in the defect image display area W1 and comparing it with the image actually displayed in another small window, the operator finally selects image data that seems to be the same defect. be able to. When the numerical value is updated each time the image is switched as described above, it can be easily understood that there is no more candidate in that direction when the numerical value becomes “0”. Of course, the numerical value is not updated as such and may be left in the initial state.

  Note that FIG. 3 shows an example in which defect images are displayed in all six small windows W, but in actuality, there may be cases where only some small windows W are displayed (small windows that are not displayed). There is also.) For example, if a defect occurs in the process immediately before the third camera device, the defect is not detected in the first and second camera devices, and a defect image is displayed from the image captured by the third camera device. Therefore, in such a case, at least in the two small windows W on the right side, the defect image is not displayed, and accordingly, the text information is not displayed. Even if a defect is detected by the third camera device in this way, the defect may not be detected from image data captured by the fourth and subsequent camera devices. This is because, for example, the defect is a hole, and the hole is buried by coating in a subsequent process so that it does not appear as a defect, or when a foreign matter is attached to the surface of the paper 1, This is because the image data captured by the camera device that captures the image is not recognized as a defect because there is no such foreign matter.

  Next, the function of the data processing unit 23 for displaying the defect time series display screen will be described. The data processing unit 23 has a function of executing the flowchart shown in FIG. First, when the “real display pause command” given by the operator is detected, the real display shown in FIG. 1 is paused (S1). Although not shown in the drawing, the real display pause command is used to input a command from the input device (keyboard) of the appearance inspection device (image recognition processing device 20) or to operate a pointing device such as a mouse to display the real display on the display device 30. This may be done by appropriately clicking on the menu bar or the like placed above the screen that is being operated, and selecting the “real display pause command” prepared as one of the menu items. Can be taken.

  The data processing unit 23 accepts designation of an arbitrary defect image (S2). Such designation is, for example, one of the three defect images displayed on the temporarily stopped real display screen (the screen is not updated when a new defect is detected and the stop command is received). You can do this by clicking on one. Of course, by selecting an arbitrary item from the displayed text information items, the image data associated therewith may be designated. When an operator sees a defect image displayed in real time, the real-time display is temporarily stopped to identify the cause, and the above-described time-series display screen can be used. It is preferable to select a defective image because the operability is good.

  Next, the data processing unit 23 waits for “time series display” to be selected from the menu display screen or pull-down menu list displayed on the display device 30 (S3). The display is switched to such a defect time series display screen (S5).

  Next, the data processing unit 23, in the processing attached information associated with the defect image specified in the processing step S2, the distance in the flow direction of the target defect (winding length: distance from the inspection start position). And the width direction position (FR distance) are acquired, the acquired information is compared with the distance in the flow direction of the defect extracted from the image data captured by each camera device (beam) and the width direction position, and an allowable range is obtained. The inside one is extracted (S6). Here, the allowable range is relatively narrow in the width direction (FR distance), and the distance in the flow direction is set to be longer than that. This is because the paper does not extend greatly in the width direction, and as a cause of a large deviation in the width direction, there is a possibility of meandering, etc. However, since it is not too much (occurrence frequency / deviation distance), the allowable range is set narrow. This suppresses unnecessary candidates from being extracted.

  On the other hand, in the flow direction, for example, the distance from the inspection start position calculated based on the pulse value is the same ( The same defect) is often different. Therefore, a wide allowable range is set for the distance in the flow direction.

  Thereby, in the example shown in FIG. 2, for example, the defect 2a and the defect 2b may be selected as candidates for the same defect within the allowable range of the distance in the flow direction. Since the position in the width direction is different, even if the flow direction is close, it does not fall within the allowable range and can be recognized as another defect.

  Next, the closest candidate within the allowable range of each beam is searched to determine whether there is a corresponding one (S7). When there is no defect corresponding to the allowable range, no defect is displayed in the small window W of the defect time series display screen corresponding to the beam (camera device 10) (S8). On the other hand, there is a defect in which the width direction and the flow direction distance of the defect imaged by a camera device different from the camera device that imaged the defect specified in the processing step S2 are within the allowable range with those of the specified defect. In this case, the closest candidate is selected as the initial candidate, and if there are a plurality of defects within the allowable range imaged by the same camera device, the candidates are extracted before and after the flow direction, respectively. At this time, initial candidates are extracted in order from the closest to the reference (up to 10). As a result, an initial candidate that is a defect image candidate for the same defect determined by the apparatus and other possible candidates are extracted (S9).

  Next, the data processing unit 23 acquires the defect image thus extracted and the processing attached information associated therewith, and displays the defect image and the processing attached information of the initial candidate in the corresponding small window W for the beam. . As a result, the data processing unit 23 outputs a defect time series display screen (S10).

  If there are no multiple candidates (No in S11), the small window W for the beam has no display switching / change (S14). For example, in the case of FIG. 3, the small window W from the beam A to the beam D corresponds to this. On the other hand, when there are a plurality of candidates (Yes in S11), the data processing unit 23 waits for the input of the previous / next candidate key, that is, the NEXT selection button B1 or the NEXT selection button B2 is clicked (S12). If so, the next candidate in the corresponding direction (the next closest candidate) is extracted and displayed in each of the areas W1 and W2 (S13). In particular, the processing after processing step S7 is executed for each camera device (beam).

  Therefore, in this embodiment, it is possible to confirm at a glance each image detected in a separate process in the defect time series display. Therefore, since the occurrence location of the defective defect and the change of the defective defect can be confirmed, the influence on the production can be confirmed. Out of paper due to defective defects in paper production leads to a large production loss, but by using the defect time series display of this embodiment, it is possible to quickly perform an action to feed back to the upstream side of production, and quality control and production It can help increase efficiency.

  Each processing unit (the inspection rack unit 21, the defect processing unit 22, and the data processing unit 23) of the above-described embodiment can be realized as hardware or can be realized as software (application program).

It is a figure which shows an example of the display layout of defect information. It is a figure which shows one public embodiment of this invention. It is a figure which shows an example of a defect time series display screen. It is a figure which shows an example of the data structure of the attached information produced | generated in a detection rack part. It is a figure which shows an example of the data structure of the process attachment information produced | generated in a defect process part. 3 is a flowchart showing functions of a data processing unit 23.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Camera apparatus 11 Line CCD camera 20 Image recognition processing apparatus 21 Detection rack part 22 Defect processing part 23 Data processing part 30 Display apparatus 31 Memory | storage device

Claims (6)

A visual inspection apparatus for a sheet-like article,
Acquire image data captured by a plurality of camera devices arranged at the front and back along the conveyance direction of the article, and perform image recognition processing in units of image data from each camera device to determine the presence or absence of defects. Judgment means,
When a defect is detected by the determination unit, a defect information creating unit that cuts out an image including the defect and creates defect information in which the cut image is associated with position information for specifying the position of the detected defect. When,
Processing means for extracting defect information about the same defect imaged by different camera devices based on the position information, and simultaneously outputting the clipped image of the extracted defect to the same display screen;
An appearance inspection apparatus comprising: The position information is a position in the front-rear direction along the conveyance direction of the article, and a position from a side edge in the width direction of the article,
The defect information extraction for the same defect is to estimate the same defect when the position of the defect specified by the position information is within an allowable range,
The visual inspection apparatus according to claim 1, wherein the permissible range is such that the permissible range for the position in the front-rear direction is larger than the permissible range for the position from the side edge.   When there are a plurality of candidates estimated as defect information on the same defect, the processing means outputs one of the plurality of candidates as an initial candidate to the display device, and follows a switching instruction given from the outside The appearance inspection apparatus according to claim 1, further comprising a function of displaying another candidate. The defect information created by the defect information creating means has text information indicating the feature of the defect including the dimension of the defect,
The appearance inspection apparatus according to claim 1, wherein the processing unit displays the cut-out image together with the corresponding text information. A plurality of camera devices arranged at the front and rear along the conveying direction of the article in the production line of the sheet-like article,
An appearance inspection system comprising: the appearance inspection apparatus according to claim 1, wherein the appearance inspection apparatus operates based on outputs from the plurality of camera devices. Computer
Acquire image data picked up by a plurality of camera devices arranged at the front and back along the conveyance direction of the article, and perform image recognition processing in units of image data from each camera device to determine the presence or absence of defects. Judgment means,
When a defect is detected by the determination unit, a defect information creating unit that cuts out an image including the defect and creates defect information in which the cut image is associated with position information for specifying the position of the detected defect. ,
Processing means for extracting defect information about the same defect imaged by different camera devices based on the position information, and simultaneously outputting the clipped image of the extracted defect to the same display screen;
Program to function as.

Images