Foreign matter detection device and foreign matter detection system for clothing and accessories
The foreign object detection system uses dual-direction X-ray irradiation and AI models with dual-monitor display to enhance accuracy and facilitate remote updates, addressing the limitations of visual inspection in existing systems.
Patent Information
- Application Number
- JP2023085240
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-24
- Publication Date
- 2024-12-05
- Estimated Expiration
- 2043-05-24
AI Technical Summary
Existing foreign object detection systems for clothing and miscellaneous goods suffer from low accuracy in detecting the presence or absence of foreign objects due to reliance on visual inspection by operators, leading to oversight or over-detection.
A foreign object detection system that irradiates objects from two directions using X-rays, employs AI inspection models generated by external devices, and displays overlapping images on dual monitors to facilitate accurate detection and learning, with an update mechanism via a server for improved model accuracy.
Enhances detection accuracy by reducing oversight and over-detection of foreign objects, facilitates easy learning, and allows remote updating of AI models, thereby improving overall system performance.
Smart Images

Figure 2024168505000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a foreign object detection device that detects whether or not a foreign object is contained in clothing or miscellaneous goods, and also to a foreign object information acquisition method used in the foreign object detection device, and a foreign object detection system that detects foreign objects. [Background technology]
[0002] Clothing includes, for example, accessories such as shoes and bags, and clothing. Miscellaneous items include small items used in daily life. Conventionally, foreign object detection devices that detect foreign objects contained in inspected objects such as clothing and miscellaneous items have been known. The foreign object detection device includes, for example, a conveying path for conveying the inspected object and an X-ray inspection device. The X-ray inspection device includes an X-ray source that irradiates the inspected object on the conveying path with X-rays from above, and a sensor that receives the X-rays from above. The foreign object detection device includes a monitor that displays an image based on the imaging data from the sensor. An operator visually checks the image displayed on the monitor to determine whether or not there is a foreign object in the inspected object. In this manner, foreign objects contained in the inspected object are detected.
[0003] However, when detecting foreign objects shown on the image displayed on the monitor, the accuracy of detecting the presence or absence of foreign objects is sometimes low when relying on the worker's visual inspection. For example, the worker may judge that there is no foreign object in the inspected object when there is, or judge that there is a foreign object in the inspected object when there is no foreign object. Therefore, as disclosed in Patent Document 1, an anomaly inspection system using a learning model has also been developed. For example, the accuracy of foreign object detection is improved by using a mask image that makes the part with a foreign object black and the other parts white, or by using a background image without foreign objects. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Patent No. 7034529 Summary of the Invention [Problem to be solved by the invention]
[0005] Therefore, an objective of the present disclosure is to provide a foreign object detection device for clothing and miscellaneous goods that can detect foreign objects with high accuracy or that can facilitate learning to improve detection accuracy, a foreign object information acquisition method, and a foreign object detection system. [Means for solving the problem]
[0006] One feature of the present disclosure relates to a foreign object detection device for clothing and miscellaneous goods that detects foreign objects contained in clothing and miscellaneous goods. The foreign object detection device has a conveying path for conveying clothing and miscellaneous goods. An X-ray source irradiates X-rays from a first direction and a second direction to the clothing and miscellaneous goods on the conveying path. A first sensor receives the X-rays from the first direction. A second sensor receives the X-rays from the second direction. A file storage unit stores an AI inspection model file. A foreign object detection unit detects a foreign object based on a first imaging data from the first sensor or detects a foreign object based on a second imaging data from the second sensor using the AI inspection model file. A first monitor displays a first image based on the first imaging data. A first result monitor is arranged in parallel with the first monitor and displays a first foreign object display related to the location of the foreign object detected in the first imaging data superimposed on the first image. A second monitor is arranged in a place visible from a place where the first monitor is visible and displays a second image based on the second imaging data. A second result monitor is provided in parallel with the second monitor and displays a second foreign object display related to the location of the foreign object detected in the second imaging data superimposed on the second image. The input means is operated by an operator when the foreign object detection unit overlooks or overdetects a foreign object. The foreign object information memory stores information on the overlooked or overdetected foreign object based on a signal from the input means. The AI inspection model file is an initial model file generated based on the standard foreign object sample image data, or a basic model file obtained by updating the initial model file based on the information stored by the foreign object information memory and the first and second imaging data.
[0007] Therefore, the presence or absence of a foreign object is detected based on the X-rays irradiated from two directions on the clothing and miscellaneous goods. Therefore, compared to detecting the presence or absence of a foreign object based on the X-rays irradiated from one direction, it is possible to suppress overlooking or overdetection of a foreign object. Furthermore, since the first image and the first image with the first foreign object display superimposed thereon are displayed side by side, it is possible to compare these two first images. Therefore, by comparing the first monitor and the first result monitor, the worker can easily detect overlooking or overdetection of a foreign object by the foreign object detection unit. This is also true for the second image. Furthermore, the foreign object detection unit is provided with an initial model file or a basic model file obtained by updating the initial model file. The basic model file is learned (updated) based on the first imaging data or the second imaging data in which a foreign object was overlooked or overdetected, so that overlooking or overdetection of the same foreign object is suppressed in the future. Therefore, the detection accuracy of the presence or absence of a foreign object is improved. Furthermore, learning can be easily performed.
[0008] According to another feature of the present disclosure, the AI inspection model file is generated by an external device using a model file creation program. Therefore, an AI inspection model file with high detection accuracy can be generated. In addition, since the AI inspection model file is generated by an external device, the involvement of a user of the foreign object detection device in generating the AI inspection model file can be reduced.
[0009] According to another feature of the present disclosure, the first foreign object display or the second foreign object display is a frame that surrounds the foreign object and is displayed in a flashing manner, thereby making it possible to prevent an operator monitoring the first result monitor or the second result monitor from overlooking the foreign object.
[0010] According to another feature of the present disclosure, the foreign object detection unit obtains an image represented by pixels by dividing the first captured data or the second captured data into regions. The foreign object detection unit detects a foreign object when the number of consecutive pixels detected as a foreign object in the image exceeds a threshold. This allows the foreign object detection unit to easily detect the presence or absence of a foreign object.
[0011] Another feature of the present disclosure relates to a method for acquiring information on a foreign body sample to be used in a foreign body detection device for clothing and miscellaneous goods as foreign body information. In the foreign body information acquisition method, a foreign body sample is inserted into a polyhedral sample holder made of resin. Next, the sample holder is placed with a first surface facing down on a resin tray or a sample tray made of the same material as the tray, which is placed on a transport path and on which clothing and miscellaneous goods are placed. Then, X-rays are irradiated onto the sample holder. Next, the sample holder is placed on the tray or sample tray with a second surface facing down. Then, X-rays are irradiated onto the sample holder. Next, the sample holder is placed on the tray or sample tray with a third surface facing down. Then, X-rays are irradiated onto the sample holder. Next, information on the foreign body sample in at least three directions is acquired as foreign body information based on a signal from a sensor that receives the X-rays.
[0012] Therefore, the foreign object information stored in the foreign object information memory is stored from viewpoints in at least three directions by utilizing at least three faces of the polyhedron. Therefore, the foreign object information to be stored in the foreign object information memory can be obtained quickly and easily. Thus, the accuracy of foreign object detection based on the foreign object information is improved.
[0013] According to another feature of the present disclosure, a foreign object detection system including a foreign object detection device for clothing and miscellaneous goods includes a server to which an AI inspection model file is uploaded from an external device, and a writing unit downloads the AI inspection model file from the server and writes the AI inspection model file into a file storage unit of the foreign object detection device for clothing and miscellaneous goods.
[0014] Therefore, when the AI inspection model file stored in the server is updated, the AI inspection model file stored in the file storage unit of the foreign object detection device for clothing and miscellaneous goods can be updated. Therefore, the AI inspection model file stored in the foreign object detection device for clothing and miscellaneous goods can be updated via the server without having to go to the installation location of the foreign object detection device for clothing and miscellaneous goods. Therefore, updating of the AI inspection model file can be easily performed.
[0015] According to another feature of the present disclosure, the foreign object detection system has an X-ray inspection device that irradiates X-rays on clothing and miscellaneous goods to obtain imaging data. The foreign object detection means detects foreign objects from the imaging data using an AI inspection model file. The image monitor displays an image based on the imaging data. The result monitor displays a foreign object display related to the location of the foreign object detected from the imaging data superimposed on the image. The input means is operated by an operator when the foreign object detection unit overlooks a foreign object or overdetects a foreign object. The foreign object information memory stores information on the overlooking of a foreign object or the overdetection of a foreign object based on a signal from the input means. The AI inspection model file is an initial model file generated by an external device, or a basic model file in which the initial model file is updated by an external device. The basic model file is generated by updating the initial model file based on the information stored in the foreign object information memory and the imaging data.
[0016] Therefore, the foreign object detection unit is provided with an initial model file or a basic model file obtained by updating the initial model file. The basic model file is learned (updated) based on imaging data in which a foreign object has been overlooked or overdetected, so that the same foreign object is prevented from being overlooked or overdetected in the future. This improves the accuracy of detecting the presence or absence of a foreign object. Learning can also be easily performed. [Brief description of the drawings]
[0017] [Figure 1] FIG. 1 is a schematic diagram illustrating the configuration of a foreign object detection system. [Diagram 2] FIG. 2 is a front view of a foreign object detection device for clothing and miscellaneous goods. [Diagram 3] 1 is a block diagram of a foreign object detection system including a foreign object detection device for clothing and miscellaneous goods. [Figure 4] FIG. 2 is a perspective view of a sample holder and a tray. [Diagram 5] This is an X-ray image of a foreign body sample using a sample holder with the first surface facing up. [Figure 6] This is an X-ray image of a foreign body sample using the sample holder with the second surface facing up. [Figure 7]X-ray image of a foreign body sample using the sample holder with the third surface facing up. [Figure 8] This is an X-ray image of a foreign body sample using the sample holder with the fourth side facing up. [Figure 9] This is an X-ray image of a foreign body sample using a sample holder with the fifth surface facing up. [Figure 10] This is an X-ray image of a foreign body sample using a sample holder placed on the sixth surface. [Figure 11] This is an image in which foreign objects are expressed in pixels, and shows an example of a determination that no foreign object is present. [Figure 12] 1 is an image in which foreign matter is expressed in pixels, showing an example of a determination that a foreign matter is present. [Figure 13] FIG. 11 is a flowchart illustrating a procedure for detecting a foreign object. [Figure 14] 13 is an explanatory diagram of an image displayed on the first result monitor when a foreign object is detected. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0018] A preferred embodiment of the present invention will be described in detail below with reference to the drawings. The same reference numerals in the description refer to the same elements having the same functions without duplicate description. One embodiment of the present invention will be described with reference to Figures 1 to 17. In the following description, the up / down and left / right directions refer to the up / down and left / right directions shown in each figure.
[0019] [Foreign object detection system 1] As shown in FIGS. 1 and 2, the foreign object detection system 1 is a system for detecting whether or not a foreign object is mixed into clothing and miscellaneous goods that are to be inspected. The clothing to be inspected is, for example, clothing such as a shirt 90, shoes, bags, and gloves. The miscellaneous goods are daily necessities such as stationery. The foreign object detection system 1 includes a foreign object detection device 2 and a server 30. The foreign object detection device 2 includes an X-ray inspection device 2a, a first workstation 11 adjacent to the X-ray inspection device 2a for detecting foreign objects based on data from the X-ray inspection device 2a, and a display and input unit 9 that also serves as a video monitor and input means. The first workstation 11 is connected to the server 30 via a communication line 33. The foreign object detection system 1 also includes a second workstation 40 for learning the presence or absence of a foreign object using a predetermined tool. The second workstation 40 is connected to the server 30 via a third communication line 33 when necessary, such as for uploading.
[0020] [X-ray inspection equipment 2a] 1 and 2, the X-ray inspection device 2a includes a lower housing 3 having a horizontally long rectangular parallelepiped shape, and an upper housing 3d that is provided on the lower housing 3 and protrudes upward. An inlet 3a for receiving an object to be inspected is provided on the right side of the lower housing 3. An outlet 3b for sending out an object to be inspected is provided on the left side of the lower housing 3. The inlet 3a and outlet 3b are each covered with a lead curtain (not shown).
[0021] As shown in FIGS. 2 and 3, inside the lower housing 3, a conveying path 5 is provided between the entrance 3a and the exit 3b. The conveying path 5 includes a conveying belt 5a, a conveying belt driving unit 5b, and a conveying belt control unit 5c. A first pin conveyor 5d is provided on the upstream side (the entrance 3a side) of the conveying path 5 so as to be at the same height as the conveying belt 5a. A second pin conveyor 5e is provided on the downstream side (the exit 3b side) of the conveying path 5 so as to be at the same height as the conveying belt 5a. This allows the tray 91 carrying the shirt 90 to be smoothly conveyed in the order of the first pin conveyor 5d, the conveying belt 5a, and the second pin conveyor 5e. The conveying belt control unit 5c receives a command from the control unit 7 and controls the operation of the conveying belt driving unit 5b. The conveying belt driving unit 5b drives the conveying belt 5a.
[0022] As shown in Fig. 2, the X-ray inspection device 2a houses an irradiation unit 6. The irradiation unit 6 includes an X-ray source 6a that irradiates X-rays, a first light emitter 6b, a first light receiver 6c, a second light emitter 6d, a second light receiver 6e, and an irradiation control unit 6f. The irradiation control unit 6f shown in Fig. 3 receives commands from the control unit 7, including detailed settings such as the X-ray irradiation time for irradiating X-rays and the X-ray intensity, and controls the X-rays irradiated from the X-ray source 6a.
[0023] As shown in Fig. 2, the X-ray source 6a emits X-rays in a first direction a, which is vertically downward, and in a second direction b, which is inclined at a predetermined angle θ (5 to 30°, for example, 20°) with respect to the vertically downward. The X-ray source 6a may include an X-ray source for the first direction a and an X-ray source for the second direction b separately, or may include only one source. Therefore, the shirt 90 is irradiated with X-rays from two directions (the first direction a and the second direction b). The first light emitter 6b receives the X-rays in the first direction a and emits them.
[0024] The second light emitter 6d receives and emits X-rays in the second direction b. The light emitted by the first light emitter 6b and the second light emitter 6d is received by the light receivers 6c and 6e shown in FIG. 3. The light receivers 6c and 6e transmit signals (first imaging data, second imaging data) according to the amount of light received to the control unit 7. The first light emitter 6b and the first light receiver 6c correspond to a first sensor. The second light emitter 6d and the second light receiver 6e correspond to a second sensor.
[0025] 3, X-ray inspection apparatus 2a is provided with a control unit 7, a storage unit 8, a control panel 4, and an alarm device 19. X-ray inspection apparatus 2a is centrally managed by the control unit 7, and each component is executed based on instructions from the control unit 7. The control unit 7 has one or more arithmetic processing devices such as a CPU, MPU, GPU, etc., and reads and executes programs stored in the storage unit 8 to perform various information processing and control processing.
[0026] The memory unit 8 shown in Fig. 3 stores various information processing and control processing programs executed by the control unit 7. The control unit 7 is electrically connected to the irradiation unit 6, the transport path 5, the display / input unit 9, etc. The control panel 4 is provided on the upper part of the surface of the upper housing 3d. The control panel 4 includes an ammeter 4b, a voltmeter 4c, and various switches 4d. An operator 80 can visually check the ammeter 4b and the voltmeter 4c, and can operate the various switches 4d.
[0027] As shown in FIG. 1, the alarm device 19 is provided on the top surface of the upper housing 3d. The alarm device 19 is, for example, a light that emits a predetermined light when it detects an X-ray leak, a door of the X-ray inspection device 2a left open, a cover falling off, or a defect in the lead curtains at the entrance 3a or the exit 3b. Alternatively, the alarm device 19 is a speaker that emits a predetermined voice or warning sound. Since the alarm device 19 is located in front of the operator 80, it is possible to prevent the operator 80 from overlooking or missing the light, voice, and warning sound emitted by the alarm device 19. The control unit 7 is electrically connected to the transport path 5, the irradiation unit 6, the memory unit 8, and the control panel 4, respectively.
[0028] As shown in Fig. 3, the display / input unit 9 has multiple monitors, for example, four monitors. For example, it has a first monitor 9a, a first result monitor 9b, a second monitor 9c, and a second result monitor 9d. Each of these monitors 9a to 9d is a touch-type monitor that accepts touch operations and has a display function and an input function (a function for accepting touches on the screen). The first monitor 9a and the second monitor 9c, the first result monitor 9b, and the second result monitor 9d are electrically connected to a first workstation 11.
[0029] As shown in FIG. 1, the first monitor 9a is attached to the lower right side of the upper housing 3d via an arm-shaped attachment member 9e. The first result monitor 9b is attached to the upper right side of the upper housing 3d via an arm-shaped attachment member 9e. Therefore, the first monitor 9a and the first result monitor 9b are arranged side by side vertically. The second monitor 9c is attached to the lower left side of the upper housing 3d via an arm-shaped attachment member 9e. The second result monitor 9d is attached to the upper left side of the upper housing 3d via an arm-shaped attachment member 9e. Therefore, the second monitor 9c and the second result monitor 9d are arranged side by side vertically. Moreover, each of the monitors 9a to 9d has the same screen size.
[0030] Therefore, the worker 80 can compare the images displayed on the first monitor 9a and the first result monitor 9b without moving his / her eyes significantly. Therefore, the images displayed on both monitors 9a and 9b can be easily compared. The same is true for the second monitor 9c and the second result monitor 9d. The first monitor 9a and the second monitor 9c display X-ray images based on signals from the first light receiving unit 6c and the second light receiving unit 6e. The first result monitor 9b and the second result monitor 9d display X-ray images of the shirt 90 generated by the image generating unit 13 of the control unit 12 of the first workstation 11. The worker 80 can view the four monitors 9a to 9d at the same time.
[0031] The first monitor 9a and the first result monitor 9b do not have to be configured as two independent monitors, but may be a single monitor that displays a screen divided into two parts vertically or horizontally. The same is true for the second monitor 9c and the second result monitor 9d. The first monitor 9a to the second result monitor 9d do not have to be configured as four independent monitors, but may be a single monitor that displays a screen divided into four parts vertically and horizontally.
[0032] [Workstation 11] The first workstation 11 shown in FIG. 1 analyzes image data (first imaging data, second imaging data) from the X-ray inspection device 2a. The first workstation 11 includes an analysis device main body 11a. Input to the analysis device main body 11a is performed by the input functions of the first monitor 9a and the second monitor 9c. As shown in FIG. 3, the first workstation 11 includes a control unit 12, a foreign substance information memory 17, a storage unit 21, and a transmitting / receiving unit 23 (receiving means). The first workstation 11 is centrally managed by the control unit 12, and each component is executed based on an instruction from the control unit 12.
[0033] 3 has one or more arithmetic processing devices such as a CPU, MPU, GPU, etc., and executes various information processing and control processing by reading and executing programs stored in a storage unit 21. The control unit 12 also includes an image generating unit 13, a foreign object detecting unit 14 (foreign object detecting means), a foreign object display providing unit 20, an AI operation result data generating and providing means 22, and a writing means 24. The image generating unit 13 receives signals (second imaging data) from the first light receiving unit 6c and the second light receiving unit 6e of the X-ray inspection device 2a, and generates an X-ray irradiation image.
[0034] The foreign object detection unit 14 shown in FIG. 3 includes a calculation unit 15 and a file storage unit 25. The calculation unit 15 has one or more arithmetic processing devices such as a CPU, an MPU, a GPU, etc., and reads and executes an AI inspection model file 16. The file storage unit 25 stores the AI inspection model file 16. The AI inspection model file 16 is an AI brain file that performs foreign object detection, and is an AI inspection model file generated by additionally learning an initial model file generated based on standard foreign object sample image data from the first imaging data and the second imaging data based on a group of image files selected by an operator operating the second workstation 40. The AI inspection model file 16 is generated by the second workstation 40 using a model file creation program. The AI inspection model file 16 does not include image data such as the first imaging data and the second imaging data.
[0035] The foreign object detection unit 14 detects a foreign object based on the first imaging data from the first light receiving unit 6c or the second imaging data from the second light receiving unit 6e and the AI inspection model file 16 in the file storage unit 25. The foreign object information memory 17 stores the first imaging data or the second imaging data in which the foreign object detection unit 14 has overlooked or overdetected a foreign object. The first imaging data or the second imaging data includes image data and AI operation result data. The AI operation result data includes information such as the image file name, the AI inspection model file name, the threshold value, the inspection label, the number of pixels of the block, the circumscribing rectangle of the detected block, the inspection type (0: apparel, 1: shoes), the inspection result (0: OK, 1: NG), the presence or absence of a foreign object (0: no foreign object, 1: foreign object present), the inspection speed (msec), and the inspection exclusion area (offset value from the left end, top, right end, and bottom).
[0036] 3, in the first imaging data or the second imaging data in which a foreign object is detected by the foreign object detection unit 14, the foreign object indication adding unit 20 adds a first foreign object indication 92 and a second foreign object indication (not shown) in the form of a rectangular frame that preferably flashes and surrounds the foreign object in association with the foreign object, respectively. A predetermined color (red, yellow, etc.) is added to both of these foreign object indications 92. This allows the operator 80 to easily recognize the foreign object in the imaging data.
[0037] The storage unit 21 shown in Fig. 3 stores various information processing and control processing programs executed by the control unit 12. The transmission / reception unit 23 electrically connects the control unit 12 and the server 30 via the Internet (through the third communication line 33) to enable transmission and reception of signals. The transmission / reception unit 23 may transmit and receive signals wirelessly, not limited to wired transmission. The AI operation result data generating and providing means 22 generates and provides AI operation result data (presence or absence of foreign object (0: no foreign object, 1: foreign object present), etc.) that distinguishes image data (first imaging data, second imaging data) in which a foreign object has been overlooked or overdetected.
[0038] 3 writes (stores) the AI inspection model file 16 in the file storage unit 25 based on a signal from the server 30 via the transmission / reception unit 23. The control unit 12 is electrically connected to the storage unit 21, the foreign substance information memory 17, and the transmission / reception unit 23. The first workstation 11 is electrically connected to the X-ray inspection device 2a and the display / input unit 9 via a first communication line 31 and a second communication line 32. The second communication line 32 is, for example, four display cables and a USB cable.
[0039] [Server 30] As shown in Fig. 1, the server 30 is set, for example, at a location (for example, on the cloud) different from the X-ray inspection apparatus 2a via an Internet line (third communication line 33). The server 30 only includes a server main body 30a. The server 30 is an information processing device capable of various information processes and sending and receiving information, for example, a general-purpose computer. The server 30 can save the AI inspection model file 16 of the foreign object detection unit 14 stored in the first workstation 11.
[0040] The server 30 has the following three functions (first function to third function). The first function is a function of authenticating the operation of the first workstation 11. In other words, the server 30 is provided with an authentication function so that only predetermined users authorized by the administrator of the foreign object detection system 1 can use the first workstation 11.
[0041] The second function is a function in which the AI testing model file 16 generated by the second workstation 40 is uploaded, and the uploaded AI testing model file 16 is downloaded to the first workstation 11 via the Internet (third communication line 33). In other words, this is a function that allows the AI testing model file 16 to be remotely installed in the first workstation 11. This allows the AI testing model file 16 to be easily updated (upgraded).
[0042] The third function is a function that can share the AI operation result data of the first workstation 11. The AI operation result data is a file that includes information such as an image file name, an AI inspection model file name, a threshold value, an inspection label, a block pixel count, a circumscribing rectangle of the detected block, an inspection type (0: apparel, 1: shoes), an inspection result (0: OK, 1: NG), presence or absence of a foreign object (0: no foreign object, 1: foreign object), an inspection speed (msec), an inspection exclusion area (offset value from the left end, the top, the right end, and the bottom), and the AI operation result data is generated in a predetermined file format (for example, CSV format) for the first imaging data and the second imaging data, and when a foreign object is overlooked or overdetected, a record of the overlooking or overdetection of the foreign object is saved as part of the AI operation result data by the operator 80 touching the first result monitor 9b or the second result monitor 9d. That is, the third function is a function that collects the AI operation result data in a predetermined file format (for example, CSV format). This allows the operator 80 of the X-ray inspection device 2a to easily identify only the first imaging data and the second imaging data that have been determined to be oversights or overdetections. Also, the number of oversights or overdetections per month, for example, can be easily known. Also, the history of oversights or overdetections of foreign objects can be easily known. Also, these results can be shared on the Internet.
[0043] [Workstation 2 40] The second workstation 40 is located at a different location (remote) from the X-ray inspection device 2a and the first workstation 11, and is an information processing device capable of various information processing and sending and receiving information, such as a general-purpose computer. The second workstation 40 has an AI model file creation program. The AI model file creation program is a program that performs AI learning or additional AI learning on the first imaging data and the second imaging data to create an AI inspection model file, which is an AI brain file that detects foreign objects, and creates or updates the file.
[0044] The initial model file is generated based on the standard foreign matter sample image data by utilizing a model file creation program through the operation of an operator operating the second workstation 40. The standard foreign matter sample image data is generated externally by an acquisition method described later, and is acquired by importing the data stored in a storage medium such as a HDD. When generating the initial model file, the operator selects the standard foreign matter sample image data to be used based on his or her own experience and knowledge, and uses only the selected standard foreign matter sample image data.
[0045] The basic model file is generated by updating the AI inspection model file from time to time based on the first imaging data and the second imaging data using a model file creation program by the operation of an operator operating the second workstation 40. The first imaging data and the second imaging data here are data in which a foreign object has been overlooked or overdetected. The first imaging data and the second imaging data are obtained by importing data that has been created externally and stored in a storage medium such as a HDD (in this example, the foreign object information memory 17 of the first workstation 11). In addition, when generating the basic model file, the operator selects the first imaging data and the second imaging data to be used based on his or her own experience and knowledge, and uses only the selected first imaging data and the second imaging data.
[0046] In this way, the AI inspection model file 16 is generated using only image data based on the operator's own experience and knowledge, so the foreign object detection accuracy of the generated AI inspection model file 16 is improved. The basic model file is an AI inspection model file that has been updated (learned) from the initial model file. Therefore, when this basic model file is used to inspect for foreign objects thereafter, the same foreign object will not be overlooked or overdetected. Therefore, the foreign object detection accuracy improves each time a new basic model file is updated and generated. A new basic model file is generated periodically (for example, once a month). In other words, the basic model file is learned (re-learned) periodically. The second workstation 40 and the server 30 may be integrated and operated as one workstation.
[0047] [How to obtain standard foreign matter sample images (how to obtain foreign matter sample information)] The procedure for acquiring a standard foreign body sample image will be described. A sample holder 51 is prepared in advance as shown in FIG. 4. The sample holder 51 is, for example, a rectangular parallelepiped melamine sponge with a side of about 4 cm. Alternatively, it may be a polyhedral sponge or a foamed resin body. An example of a foreign body sample is a broken clip 50. It is preferable to prioritize the foreign body samples before learning. This makes it possible to prevent forgetting to learn. For example, foreign bodies that are thought to have an effect on the human body when mixed in, such as glass fragments, needles, cutter blades, safety pins, nails, screws, etc., are learned as the first priority. Items that are mixed in due to factory mistakes or careless mistakes by workers, such as scissors, pens, packing tape, etc., are learned as the second priority. Small foreign bodies, such as sand grains, are learned as the third priority.
[0048] As shown in Fig. 4, the sample holder 51 has a slit 58 formed from the first surface 52 toward the inside. Next, a clip 50 is inserted into the slit 58 of the sample holder 51. The sample holder 51 is placed on a tray 91 (a sample tray made of the same material as the tray 91). In order to irradiate each of the six surfaces of the sample holder 51 with X-rays and obtain each of the X-ray irradiation images, first, the sample holder 51 is placed on the tray 91 with the first surface 52 of the sample holder 51 facing up, i.e., the second surface 53 facing down, and X-rays are irradiated from the first surface 52.
[0049] Similarly, the sample holders 51 are placed on the tray 91 so that the second surface 53, the third surface 54, the fourth surface 55, the fifth surface 56, and the sixth surface 57 of the sample holder 51 are facing up, i.e., the first surface 52, the fourth surface 55, the third surface 54, the sixth surface 57, and the fifth surface 56 are facing down, and X-rays are irradiated from the second surface 53, the third surface 54, the fourth surface 55, the fifth surface 56, and the sixth surface 57, respectively. Then, as shown in Figs. 5 to 10, six X-ray irradiation images are acquired. Note that the sample holder 51 itself is unlikely to be reflected in the X-ray irradiation images, so clear X-ray irradiation images from six directions can be acquired. The six acquired X-ray irradiation images are stored in the second workstation 40 in association with the item (in this case, the paperclip 50).
[0050] In this manner, a standard impurity sample image can be obtained. Note that this standard impurity sample image is obtained for each impurity to be detected. Furthermore, even if the impurities are the same type, impurities with different shapes, sizes, etc. are further classified by item and stored in the second workstation 40. In this way, thousands to tens of thousands of standard impurity sample images can be created.
[0051] [Generating and assigning AI operation result data] When detecting a foreign object in the foreign object detection unit 14, a foreign object may be overlooked or overdetected. In such a case, the presence or absence of a foreign object (0: no foreign object, 1: foreign object present) is recorded as part of the AI operation result data for the first imaging data and the second imaging data (image data) in which a foreign object was overlooked or overdetected. This recording of the presence or absence of a foreign object (0: no foreign object, 1: foreign object present) is performed by the operator 80 touching the screens of the first result monitor 9b and the second result monitor 9d. For example, when a foreign object is overlooked or overdetected by the foreign object detection unit 14, the operator 80 touches the screens of the first result monitor 9b and the second result monitor 9d. Then, the AI operation result data generating and providing means 22 provides a part of the AI operation result data provided to the image data corresponding to the touched screen.
[0052] The image data to which this AI operation result data has been added is stored in foreign object information memory 17. Since this foreign object information memory 17 is, for example, a HDD or the like, this foreign object information memory 17 can be transported to and connected to the second workstation 40, which is an external device. The image data to which the AI operation result data has been added is read in the second workstation 40, and from the read image data, only that selected by the operator of the second workstation 40 is used (picked up) for generating a basic model file.
[0053] [Foreign object detection procedure] Next, the procedure for detecting a foreign object will be described with reference to FIG. 13. As an example of detecting a foreign object, detection of a foreign object mixed into a shirt 90 will be described. An operator 80 starts up the foreign object detection device 2 (S1). Note that the server 30 is normally always running. Next, the operator 80 accesses the server 30 from the first workstation 11 and obtains authentication (S2). The operator 80 has been given an ID, a password, etc. for access in advance through a subscription contract or the like.
[0054] During initial setup or when an update is required, the operator 80 downloads the latest AI inspection model file 16 from the server 30 to the first workstation 11 (S3). The downloaded latest AI inspection model file 16 is written and stored in the file storage unit 25 of the foreign matter detection unit 14 of the first workstation 11 by the writing means 24. If an update is not required, the step of S3 is skipped. Next, the operator 80 operates the control panel 4 to start the conveyor belt 5a (S4). Next, the operator 80 places the tray 91 carrying the shirts 90 on the first pin conveyor 5d (S5).
[0055] 1 and 13, next, the worker 80 places the tray 91 from the first pin conveyor 5d onto the conveyor belt 5a (on the conveyor path) (S6). Next, the worker 80 carries the tray 91 carrying the shirt 90 through the entrance 3a of the X-ray inspection device 2a (S7). When the tray 91 reaches below the X-ray source 6a by the conveyor belt 5a, the shirt 90 is irradiated with X-rays from the first direction a and the second direction b (S8). The irradiated X-rays pass through the shirt 90 and reach both light emitting units 6b and 6d below the conveyor belt 5a.
[0056] Both light emitting elements 6b, 6d emit light in accordance with the amount of X-rays that reach them. The first light receiving element 6c and the second light receiving element 6e receive the emitted light.
[0057] On the first monitor 9a, an X-ray irradiation image (first video) of the shirt 90 from the first direction a is displayed based on a signal corresponding to the amount of light received from the first light receiving unit 6c (S9). In this image, the clip 50 is displayed as a foreign object. Therefore, the worker 80 can see the X-ray irradiation image in which the clip 50 is displayed. Therefore, the worker 80 can recognize the clip 50 mixed in the shirt 90 (S10).
[0058] Similarly, the second monitor 9c displays an X-ray irradiation image (second video) of the shirt 90 from the second direction b based on a signal corresponding to the amount of light received from the first light receiving unit 6c (S9). In this image, the clip 50 tilted at 20° is displayed as a foreign object. Therefore, the worker 80 can see the X-ray irradiation image in which the clip 50 tilted at 20° is displayed. Therefore, the worker 80 can recognize the clip 50 tilted at 20° that is mixed in the shirt 90 (S10).
[0059] At the same time, image generating unit 13 of control unit 12 generates X-ray irradiation images of shirt 90 from the light received by both light receiving units 6c, 6e. Then, foreign object detection unit 14 of control unit 12 detects the presence or absence of a foreign object from the X-ray irradiation images. In this case, foreign object detection unit 14 recognizes clip 50, so foreign object indication unit 20 indicates clip 50 with a first foreign object indication 92 and a second foreign object indication surrounding clip 50.
[0060] The foreign object detection unit 14 obtains an image represented by pixels by dividing the first image data or the second image data into regions, and detects a foreign object when the number of consecutive pixels detected as a foreign object in the image exceeds a threshold. In the image represented by the obtained pixels, pixels that are connected vertically, horizontally, or diagonally are regarded as one block. For example, the threshold is set to "5." The threshold can be arbitrarily changed.
[0061] Then, the cluster of pixels 60 as shown in FIG. 11 has "4" pixels 60. That is, the number of pixels 60 is "4". In this case, the foreign object detection unit 14 determines that there is no foreign object because the number of pixels 60 is smaller than the threshold value. On the other hand, the cluster of pixels 60 as shown in FIG. 12 has "7" pixels 60. That is, the number of pixels 60 is "7". In this case, the foreign object detection unit 14 determines that there is a foreign object because the number of pixels 60 is greater than the threshold value. In this way, the foreign object detection unit 14 detects the presence or absence of a foreign object. In addition to the above determination, the foreign object detection unit 14 may also determine whether or not there is a foreign object based on the shape of the cluster of pixels 60.
[0062] An X-ray irradiation image of the shirt 90 from the first direction a is displayed on the first result monitor 9b (S9). In this image, a clip 50 is displayed as a foreign object. At this time, a first foreign object indicator 92 is added so as to surround the periphery of the clip 50 (see FIG. 14). Therefore, the operator 80 can see the X-ray irradiation image with the first foreign object indicator 92 added. Therefore, the operator 80 notices the blinking display of the first foreign object indicator 92, and can reliably recognize the clip 50 mixed in the shirt 90 (S10). Note that the X-ray irradiation image displayed on the first result monitor 9b is the X-ray irradiation image displayed on the first monitor 9a with the first foreign object indicator 92 added.
[0063] Similarly, the second result monitor 9d displays an X-ray irradiation image of the shirt 90 from the second direction b (S9). In this image, the clip 50 is displayed as a foreign object tilted at 20°. At this time, the second foreign object indicator is added so as to surround the periphery of the clip 50. Therefore, the worker 80 can see the X-ray irradiation image with the second foreign object indicator added. Therefore, the worker 80 notices the blinking display of the second foreign object indicator, and can reliably recognize the clip 50 mixed in the shirt 90 (S10). Note that the X-ray irradiation image displayed on the second result monitor 9d is the X-ray irradiation image displayed on the second monitor 9c with the second foreign object indicator added.
[0064] Next, the tray 91 placed on the conveyor belt 5a is discharged from the exit 3b of the foreign matter detection device 2 (S11). The worker 80 takes out the shirt 90 and checks for foreign matter (S12). Through this series of operations, the worker 80 can detect any foreign matter that has entered the shirt 90.
[0065] Furthermore, in the above-described series of operations, there may be a case where the first foreign object display 92 is not provided on the first result monitor 9b even though the clip 50 is displayed as a foreign object on the first monitor 9a. In other words, there may be a case where the foreign object detection unit 14 has overlooked the foreign object. In that case, the worker 80 touches (inputs) the screen of the first result monitor 9b as described above. Then, the AI operation result data generating means 22 of the first workstation 11 generates and provides an AI operation result data file to the first imaging data corresponding to this touch. This generated and provided AI operation result data file and the first imaging data are stored in the foreign object information memory 17.
[0066] Conversely, even if a foreign object is not mixed in the shirt 90, the foreign object detection unit 14 may mistakenly detect it as a foreign object, and the foreign object display unit 20 may display the first foreign object display 92. That is, the foreign object detection unit 14 may overdetect a foreign object. In this case, the worker 80 touches (inputs) the screen of the first result monitor 9b as described above. Then, the AI operation result data providing means 22 of the first workstation 11 generates and provides AI operation result data to the first imaging data corresponding to this touch. The generated and provided AI operation result data is provided and the first imaging data is stored in the foreign object information memory 17. The stored first imaging data is transported to the second workstation 40 periodically (for example, once a month).
[0067] The first monitor 9a and the second monitor 9c display X-ray irradiation images with an X-ray irradiation angle from the X-ray source 6a differing by 20°. Therefore, a foreign object that is not visible on the first monitor 9a may be visible on the first result monitor 9b, and vice versa. This prevents foreign objects from being overlooked. The same is true for the first result monitor 9b and the second result monitor 9d.
[0068] In addition, in the X-ray inspection device 2a, the voltage for X-ray irradiation is set to a predetermined value. By changing this voltage, the range of the gray scale of, for example, 256 levels changes. When changing the threshold, it is preferable to use a voltage that reduces the difference due to the voltage. The range of the gray scale does not change when changing the brightness. Therefore, the brightness of the screen is not adjusted by adjusting the voltage. For example, below the first predetermined voltage, the difference in gray scale value of a part where a foreign object other than metal such as plastic and clothing are overlapped is reduced. At a second predetermined voltage higher than the first predetermined voltage, the image may white out depending on the brightness adjustment. Furthermore, if the irradiation intensity of the X-ray is high, the life of the X-ray sensor may be shortened.
[0069] The presence or absence of blinking and the color of the first foreign object display 92 and the second foreign object display can be set arbitrarily so as not to strain the eyes of the operator 80. The light, voice and warning sound issued by the alarm device 19 can be set to ON or OFF. Area division is used to determine foreign objects by the foreign object detection unit 14. A threshold is set for the number of adjacent pixels detected as foreign objects vertically, horizontally and diagonally, and the foreign object detection unit 14 performs foreign object determination processing using that number of pixels (threshold).
[0070] The foreign object detection device 2 can select an object such as clothing or miscellaneous goods. It may be configured to read out the AI inspection model file 16 according to the selected object. There may be one or more objects. An AI may be selected for each inspection object. Changing the contrast of the X-ray irradiation image makes it easier for the worker 80 to see. The boundary of the X-ray line sensor can also be adjusted. The server 30 manages files of various X-ray irradiation images and has a function for creating reports for X-ray inspection. The position information of the foreign object is determined by AI. The foreign object is identified on the lower screen of the two screens, the first monitor 9a and the first result monitor 9b, and since it is a black and white screen, it is easy to grasp the shape, etc.
[0071] A deadline may be set for the authentication of the subscription contract of the first workstation 11. Also, a deadline may be set for the maintenance of the first workstation 11. The authentication system, the server 30, and the basic model file can be upgraded.
[0072] The hexahedral sample holder 51 (resin holder) is a rectangular parallelepiped, and may be approximately 3.2 cm x 4 cm x 4 cm. A slit 58 is made in the sample holder 51 and a foreign object is inserted into it. By irradiating each of the six sides with X-rays, data from six directions can be obtained. The polyethylene or urethane tray and the sample holder 51 have similar images in the X-ray image. Therefore, only faint lines appear and there is no effect on AI learning. The foreign object to be found by X-ray inspection is created, or the actual object is procured and embedded in the sample holder 51. By placing a foreign object in the sample holder 51 and photographing it, six shapes can be photographed with one foreign object (foreign objects with different areas can be obtained).
[0073] When re-learning the basic model file, the AI learns and corrects the detection failures, foreign object detections, and normal objects from actual work. During correction, the high-priority foreign objects created are used to check the accuracy of the AI learning, and it is confirmed that there is no decrease in detection accuracy. The priority of the created foreign objects is ranked according to the frequency of occurrence at the site and the degree of danger to the human body. A foreign object list is created only for the initial model file, based on the AI learning priority. An initial model is created that is trained on the basic NG (general foreign objects that may be mixed in) and OK (clothing with no contamination at all). For example, about 40,000 images are inspected, and any overdetections or oversights that occur among them are additionally trained. The initial model learning is prioritized. Scissors, pens, and packing tape are given high priorities. Grains of sand used in processing jeans are given a low priority. The program is run using the learning data.
[0074] To train the AI's initial model file, standard foreign objects that are likely to cause harm to the human body if mixed in are trained. This includes objects that occur in factory accidents. The AI is trained in the order in which it has learned about foreign objects that were accidentally mixed in by workers. The learning order is determined based on the priority of the foreign objects to be detected, to avoid forgetting to learn objects with higher priorities. If the AI's learning procedure and priorities include high and medium priorities, the high priority has already been trained by the AI. To eliminate any impact on the high priority, the learning conditions for the medium priority are changed, and the detection accuracy is improved. By repeating these operations, the AI's initial model file is created.
[0075] The basic model file is a file in which the initial model file is used in the actual inspection work and the initial model file is modified by the model file creation program. The basic model file is generated based on the learning data selected by the operator of the model file creation program from the first and second imaging data generated by performing the actual inspection work, and the AI is trained on the data of the foreign object that actually occurred, improving the accuracy. Assuming that an oversight occurs in the actual inspection work, foreign object A is overlooked in the image (overseen image). 1. AI is trained with several normal images of the actual object and an image (overseen image) of foreign object A. 2. After learning, it is confirmed whether foreign object A can be detected. 3. The detection accuracy after AI learning is confirmed by setting the foreign object sample to high priority. In order to confirm whether there is a decrease in accuracy other than the learned foreign object, step 3 can be performed with high priority for artificial foreign objects, and can be used to check for malfunctions after AI learning.
[0076] In additional learning, if an object is overlooked in both the first direction X-ray image and the second direction X-ray image, it is considered an "overlooked" object. The current inspection model has a fairly high detection accuracy for small granular foreign objects. However, on the other hand, larger foreign objects (nails, screws, cutter pieces) may be overlooked depending on their shape. This is because clothing accessories (buttons, hooks, zippers, buckles) that have been learned as normal items often have a shape similar to that of larger foreign objects depending on the angle at which they are captured.
[0077] Large foreign objects can be seen at a glance on the first monitor 9a and the second monitor 9c, so there is a chance that one may be overlooked. This is an approach in which AI is good at detecting small foreign objects that are hard to notice. It is also possible to display items in different colors. For example, it can be applied to detecting the number of buttons on a shirt 90 to prevent people from forgetting to button them. It can also be applied to checking whether nails inside high heels are broken. In this case, it is necessary to determine whether the nail is normal, and this can be determined by setting a threshold value.
[0078] Foreign objects / contamination refers to unwanted objects that have been mixed into the product being inspected. Overdetection is when the AI detects a foreign object in an area that is not actually a problem. In other words, it refers to the AI detecting a foreign object in an area that is not actually a problem. Oversight is when the AI fails to detect a foreign object even though it is mixed in. An AI model (including programs, foreign object information, and thresholds) is the stored brain of an AI that has already been trained. It can also store files that output the results of using a learning tool to learn "foreign object" and "normal" areas using X-ray images. Internally, it also remembers which part of which image was trained.
[0079] According to the foreign object detection system 1 as described above, the presence or absence of a foreign object is detected based on X-rays irradiated from two directions, the first direction a and the second direction b, to the shirt 90. Therefore, compared to detecting the presence or absence of a foreign object based on X-rays irradiated from one direction, it is possible to suppress overlooking or overdetection of a foreign object to be detected. Furthermore, since the X-ray irradiation image of the shirt 90 from the first direction a and the X-ray irradiation image in which the first foreign object display 92 is superimposed on this X-ray irradiation image are displayed side by side one above the other, these two X-ray irradiation images can be compared. Therefore, by comparing the first monitor 9a and the first result monitor 9b, the operator 80 can easily check whether the foreign object detection unit 14 has overlooked or overdetected a foreign object. This is also true for the X-ray irradiation image of the shirt 90 from the second direction b. Furthermore, the foreign object detection unit 14 has an initial model file or a basic model file obtained by updating the initial model file. The basic model file is learned (updated) based on the first imaging data or the second imaging data in which a foreign object was overlooked or overdetected, so that the same foreign object is prevented from being overlooked or overdetected in the future. This improves the accuracy of detecting the presence or absence of a foreign object. Learning can also be simplified.
[0080] Furthermore, the AI inspection model file 16 is generated by the second workstation 40 using a model file creation program. Therefore, an AI inspection model file with high detection accuracy can be generated. Also, since it is generated by the second workstation 40, the involvement of the user of the foreign object detection device 2 in generating the AI inspection model file 16 can be reduced.
[0081] Furthermore, the first foreign object display 92 or the second foreign object display is a frame that surrounds the foreign object and is displayed in a flashing manner, which makes it possible to prevent the operator 80 monitoring the first result monitor 9b or the second result monitor 9d from overlooking the foreign object.
[0082] Furthermore, the foreign object detection unit 14 obtains an image represented by pixels by dividing the X-ray irradiation image from the first direction a or the X-ray irradiation image from the second direction b into regions. The foreign object detection unit 14 detects a foreign object when the number of consecutive pixels detected as a foreign object in the image exceeds a threshold. This allows the foreign object detection unit 14 to easily detect the presence or absence of a foreign object.
[0083] The present invention further relates to a foreign substance information acquisition method for acquiring standard foreign substance sample image data to be used in the foreign substance detection device 2 for clothing and miscellaneous goods. In the foreign substance information acquisition method, a foreign substance sample (e.g., a paperclip 50) is inserted into a six-sided resin sample holder 51. Next, the sample holder 51 is placed on a resin tray 91 on which a shirt 90 is placed and which is placed on the transport path 5, with the first surface 52 facing down. The sample holder 51 is then irradiated with X-rays. Next, the sample holder 51 is placed on the tray 91 with the second surface facing down. The sample holder 51 is then irradiated with X-rays. Next, the sample holder 51 is placed on the tray 91 with the third surface facing down. The sample holder 51 is then irradiated with X-rays. Next, information on the foreign substance sample from at least three directions is acquired based on signals from both light receiving units 6c and 6e that receive the X-rays. Therefore, the information on the foreign substance sample is stored from the viewpoints of at least three directions by using at least three surfaces of the six-sided shape. Therefore, the information on the foreign substance sample can be obtained quickly and easily. Thus, the accuracy of foreign object detection based on information from the foreign object sample is improved.
[0084] Furthermore, the foreign object detection system 1 including the foreign object detection device for clothing and miscellaneous goods has a server 30 to which the AI inspection model file 16 is uploaded from the second workstation 40. The writing means 24 downloads the AI inspection model file 16 from the server 30 and writes the AI inspection model file 16 to the file storage unit 25 of the foreign object detection device 2 for clothing and miscellaneous goods. Therefore, when the AI inspection model file 16 stored in the server 30 is updated, the AI inspection model file 16 stored in the file storage unit 25 of the foreign object detection device 2 can be updated. Therefore, the AI inspection model file 16 stored in the foreign object detection device 2 can be updated via the server 30 without going to the installation site of the foreign object detection device 2. Therefore, the AI inspection model file 16 can be easily updated.
[0085] Although the embodiments of the present invention have been described with reference to the above structure, it will be apparent to those skilled in the art that many alternatives, modifications, and variations are possible without departing from the scope of the present invention. Therefore, the embodiments of the present invention may include all alternatives, modifications, and variations that do not depart from the spirit and scope of the appended claims. For example, the embodiments of the present invention are not limited to the specific structures described above, and may be modified as follows:
[0086] The embodiments described above in detail with reference to the accompanying drawings are representative of the present invention and are not intended to limit the present invention. The detailed description is intended to teach one of ordinary skill in the art to make, use and / or implement various aspects of the present teachings and is not intended to limit the scope of the present invention. Furthermore, each of the additional features and teachings described above may be applied and / or used separately or together with other features and teachings to provide an improved foreign object detection device 2 for clothing and miscellaneous goods.
[0087] In the embodiment, the predetermined angle θ has been described as, for example, 20°. Alternatively, it may be any angle within the range of 5 to 30°. Also, in the embodiment, the X-ray sources 6a in the first direction a and the second direction b have been described as having the same configuration (made of an integrated member). Alternatively, these X-ray sources 6a may be of different configurations. Also, in the embodiment, the sample holder 51 has been described as being hexahedral. Alternatively, the sample holder 51 may be any polyhedral shape so long as it is a polyhedron.
[0088] In the embodiment, the foreign object detection device 2 has been described as having the X-ray inspection device 2a, the first workstation 11, and the display / input unit 9. In this case, the X-ray inspection device 2a and the first workstation 11 have been described as having separate configurations. Alternatively, the X-ray inspection device 2a and the X-ray inspection device 11 may have the same configuration. For example, if they have different configurations, the foreign object detection system 1 can be constructed by retrofitting the first workstation 11 to an existing X-ray inspection device 2a. Also, if they have the same configuration, the first workstation 11 can be incorporated into the X-ray inspection device 2a. This eliminates the need to provide a separate first workstation 11, resulting in a simple configuration.
[0089] Furthermore, in this embodiment, the procedure for acquiring a standard foreign matter sample image is to place the sample holder 51 on the tray 91 with the first surface 52 to the sixth surface 57 of the sample holder 51 facing up, and to irradiate X-rays from the first surface 52 to the sixth surface 57, respectively. Alternatively, the sample holder 51 may be placed on the tray 91 with the first surface 52 to the sixth surface 57 of the sample holder 51 facing down, and to irradiate X-rays from the opposite surfaces, respectively. Furthermore, the directions in which X-rays are irradiated are not limited to six directions, and may be at least three directions. [Explanation of symbols]
[0090] 1 Foreign object detection system 2. Foreign object detection device 5. Transport Path 6a X-ray source 6b First light emitting unit (first sensor) 6c First light receiving unit (first sensor) 6d Second light emitting unit (second sensor) 6e Second light receiving unit (second sensor) 9a 1st Monitor 9b 1st Result Monitor 9c Second Monitor 9d 2nd Result Monitor 11 Workstation 1 14 Foreign object detection unit 22 AI operation result data generation and provision means 25 File storage section 30 Server 30 40 Second Workstation (External Device) 90 Shirt a First direction b Second direction
Claims
1. A foreign object detection device for detecting foreign objects contained in clothing and miscellaneous goods, comprising: A conveying path for conveying the clothing and miscellaneous goods; an X-ray source that irradiates the clothing and miscellaneous goods on the transport path with X-rays from a first direction and a second direction; a first sensor that receives X-rays from the first direction; a second sensor that receives X-rays from the second direction; A file storage unit that stores an AI inspection model file; a foreign object detection unit that detects a foreign object based on first imaging data from the first sensor or detects a foreign object based on second imaging data from the second sensor by using the AI inspection model file; a first monitor that displays a first image based on the first imaging data; a first result monitor that is arranged in parallel with the first monitor and that displays a first foreign object display related to a location of a foreign object detected in the first imaging data, superimposed on the first image; a second monitor that is provided in a place visible from a place where the first monitor can be seen and displays a second image based on the second imaging data; a second result monitor that is arranged in parallel with the second monitor and that displays a second foreign object display related to a location of a foreign object detected in the second imaging data, superimposed on the second image; an input means that is operated by an operator when the foreign object detection unit overlooks or overdetects a foreign object; a foreign object information memory for storing information on an oversight or overdetection of a foreign object based on a signal from the input means, the AI inspection model file is an initial model file generated based on standard foreign body sample image data, or a basic model file obtained by updating the initial model file based on information stored in the foreign body information memory, the first imaging data, and the second imaging data.
2. The foreign object detection device for clothing and miscellaneous goods according to claim 1, The AI inspection model file is generated by an external device using a model file creation program, and the foreign object detection device for clothing and miscellaneous goods.
3. The foreign object detection device for clothing and miscellaneous goods according to claim 1 or 2, The first foreign object display or the second foreign object display is a frame that surrounds the foreign object and is displayed in a flashing manner.
4. The foreign object detection device for clothing and miscellaneous goods according to claim 1 or 2, The foreign object detection unit obtains an image represented by pixels by dividing the first image capture data or the second image capture data into regions, and detects the foreign object as a foreign object when the number of consecutive pixels detected as the foreign object in the image exceeds a threshold.
5. 3. A method for acquiring foreign object information to be used in the foreign object detection device for clothing and miscellaneous goods according to claim 1, comprising: A foreign body sample is inserted into a polyhedral resin sample holder; placing the sample holder with a first surface facing down on a resin tray that is placed on the transport path and on which clothing and miscellaneous goods are placed or on a sample tray made of the same material as the resin tray; and irradiating the sample holder with X-rays; placing the sample holder on the tray or the sample tray with the second surface facing down, and irradiating the sample holder with X-rays; placing the sample holder on the tray or the sample tray with the third surface facing down, and irradiating the sample holder with X-rays; A foreign matter sample information acquisition method for acquiring information of the foreign matter sample in at least three directions based on a signal from a sensor receiving the X-rays, as the foreign matter information.
6. A foreign object detection system including the clothing and miscellaneous goods foreign object detection device according to claim 2, A server to which the AI inspection model file is uploaded from the external device; A foreign object detection system for a foreign object detection device for clothing and miscellaneous goods, comprising a writing means for downloading the AI inspection model file from the server and writing the AI inspection model file to the file memory unit of the foreign object detection device for clothing and miscellaneous goods.
7. A foreign object detection system for detecting foreign objects contained in clothing and miscellaneous goods, comprising: an X-ray inspection device for irradiating the clothing and accessories with X-rays to obtain imaging data; a foreign object detection means for detecting a foreign object from the imaging data by using an AI inspection model file; a video monitor for displaying an image based on the imaging data; and a result monitor that displays a foreign object indication related to the location of the foreign object detected from the imaging data on the image; and an input means that is operated by an operator when the foreign object detection unit overlooks or overdetects a foreign object; a foreign object information memory for storing information on an oversight or overdetection of a foreign object based on a signal from the input means, The AI inspection model file is an initial model file generated by an external device, or a basic model file obtained by updating the initial model file by the external device, A foreign object detection system, wherein the basic model file is generated by updating the initial model file based on the information stored in the foreign object information memory and the imaging data.
Citation Information
Patent Citations
A equipment for automated inspection puts in order case finished shoes
CN207198062U
Device for detecting broken needles of shoes and clothes based on artificial intelligence technology
CN213779923U
Radioscopic unit
JP1994265485A
X-ray foreign matter inspecting apparatus
JP1999023494A
X-ray foreign matter detector
JP2011196778A
