Object fingerprint detection system, object fingerprint detection method, and program

Abstract

To provide an object fingerprint detection system, an object fingerprint detection method, a program and the like capable of detecting object fingerprints in real time with high efficiency.SOLUTION: An object fingerprint detection system according to the present disclosure includes: image extraction means configured to extract captured images, obtained by imaging means that captures one or more conveyed objects, into cropped images; determination means configured to determine, from the cropped images, whether or not a target to be determined is present; ID assignment means configured to assign an ID to the cropped image having the target to be determined when the target to be determined is present in the cropped image; object fingerprint reading means configured to read object fingerprints of one or more targets to be determined from the cropped images containing the one or more targets to be determined; and registration means configured to register the ID, the object fingerprint and the cropped image in association with one another.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a system for detecting a fingerprint of an object, a method for detecting a fingerprint of an object, and a program. [Background technology]

[0002] In recent years, manufacturing sites in the manufacturing industry have been accumulating and analyzing the manufacturing history of each and every product, including its processing and inspection, as big data, and using this data to improve quality control, production efficiency, and even design and processing accuracy. Product quality control is particularly important, and it is necessary to identify the individual product itself. In other words, by acquiring the individual identification information of products that flow through the production line and storing this information in association with manufacturing status information, it is possible to accumulate manufacturing history.

[0003] To identify individual products, products may be stamped, given serial numbers or barcodes, or tagged with tags such as RFID (Radio Frequency Identifier). However, when using stamping, barcodes, RFID, or other tags to identify mass-produced products such as screws and rods, these tags must be added to each individual product, resulting in the problem of enormous costs. Furthermore, even for small products such as tablets, it may not be possible to add stamping, barcodes, RFID, or other tags due to size constraints or product characteristics. Another problem with stamping, barcodes, RFID, or other tags is that the information added to the product is easily lost.

[0004] Therefore, in recent years, Fingerprint of Things authentication technology has been proposed, which uses minute patterns (Fingerprint of Things) on the surface of a product to identify individuals. Specifically, Fingerprint of Things authentication technology uses a photographing device such as a camera to capture images of naturally occurring minute patterns that occur during the manufacturing process of a product, such as minute irregularities or patterns on the surface of a product or random patterns on the surface of a material, and recognizes the minute patterns to identify individual products. For example, Patent Document 1 describes an example of technology for identifying individuals using Fingerprint of Things. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 7238966 Summary of the Invention [Problem to be solved by the invention]

[0006] In Patent Document 1, the image of the target object is not cut out, and the Fingerprint of Things detection process is performed in a line-out state from the image of the target object read by a camera. This results in a low degree of freedom in identification, and it is not possible to detect a precise Fingerprint of Things in real time for one or more objects that are moving quickly due to a conveyance device or the like.

[0007] The present disclosure has been made to solve such problems, and aims to provide a Fingerprint of Things detection system, method, program, etc. that can detect Fingerprints of Things efficiently in real time. [Means for solving the problem]

[0008] The Fingerprint of Things detection system according to the present disclosure comprises an image cropping means for cropping an image of one or more transported objects captured by an imaging means into a cropped image, a determination means for determining whether or not an object to be determined exists in the cropped image, an ID assignment means for assigning an ID to the cropped image containing the object to be determined if the object to be determined exists in the cropped image, a Fingerprint of Things reading means for reading the Fingerprint of the one or more objects to be determined from the cropped image containing the one or more objects to be determined, and a registration means for registering the ID, the Fingerprint of Things, and the cropped image in association with each other.

[0009] The Fingerprint of Things detection method according to the present disclosure cuts out a captured image of one or more transported objects captured by an imaging means into a cut-out image, determines whether or not an object to be determined exists in the cut-out image, and if the object to be determined exists in the cut-out image, assigns an ID to the cut-out image containing the object to be determined, reads the Fingerprint of Things of the one or more objects to be determined from the cut-out image containing the one or more objects to be determined, and associates and registers the ID, the Fingerprint of Things, and the cut-out image.

[0010] The program according to the present disclosure causes a computer to execute the following steps: cut out an image of one or more objects being transported, captured by an imaging means, into a cut-out image; determine whether or not an object to be determined exists in the cut-out image; if the object to be determined exists in the cut-out image, assign an ID to the cut-out image containing the object to be determined; read Fingerprints of the one or more objects to be determined from the cut-out image containing the one or more objects to be determined; and associate and register the ID, Fingerprints of the Objects, and the cut-out image. [Effects of the Invention]

[0011] According to the present disclosure, it is possible to provide a Fingerprint of Things detection system, method, program, etc. that can detect Fingerprints of Things efficiently in real time. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of a Fingerprint of Things detection system according to an embodiment. [Figure 2] FIG. 2 is a flowchart illustrating a Fingerprint of Things detection method according to an embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of a Fingerprint of Things detection system according to some embodiments. [Figure 4] FIG. 4 is a block diagram illustrating an example of the configuration of a scanner-type line camera. [Figure 5] FIG. 5 is a diagram for explaining a specific example of pre-processing required for real-time Fingerprint of Things detection. [Figure 6] FIG. 6 is a flowchart illustrating a Fingerprint of Things detection method and a remote monitoring method according to some embodiments. [Figure 7] FIG. 7 is a diagram illustrating an example of the configuration of a Fingerprint of Things detection system according to another embodiment. [Figure 8] FIG. 8 is a flowchart illustrating a visual inspection method and a remote monitoring method according to another embodiment. [Figure 9] FIG. 9 is a block diagram showing an example of the configuration of a Fingerprint of Things detection device and the like. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, specific embodiments to which the present invention is applied will be described in detail with reference to the drawings. However, the present invention is not limited to the following embodiments. In addition, the following description and drawings have been simplified as appropriate for clarity of explanation.

[0014] FIG. 1 is a diagram illustrating an example of the configuration of a Fingerprint of Things detection system according to an embodiment. The Fingerprint of Things detection system 1 includes an image cropping unit 110, a determination unit 111, an ID assignment unit 112, a Fingerprint of Things reading unit 120, and a registration unit 121. Each component of the Fingerprint of Things detection system 1 may be embodied as software or code executed on general-purpose hardware, or alternatively, as dedicated hardware, or a combination of software / general-purpose hardware and dedicated hardware.

[0015] The image cropping unit 110, also called image cropping means, crops an image of one or more objects being transported, captured by an imaging means, into a cropped image. Examples of the objects include, but are not limited to, screws and bolts, and may be any object manufactured on a production line and transported.

[0016] The determination unit 111, which is also called a determination means, determines whether or not an object to be determined exists in each cut-out image. The determination unit 111 may determine whether or not an object to be determined exists in each cut-out image using a known object recognition technique.

[0017] The ID assigning unit 112 is also called an ID assigning means, and when the cut-out image contains the target to be determined, assigns an ID to the cut-out image containing the target to be determined.

[0018] The Fingerprint of Things reading unit 120 is also called a Fingerprint of Things reading means, and reads the Fingerprint of one or more objects to be determined from the cut-out image containing the objects. The Fingerprint of Things has unique characteristics that differ from one another even for machine parts that are machined with high precision or parts manufactured from the same mold.

[0019] The registration unit 121 is also called a registration means, and registers (in a storage unit) an ID, a Fingerprint of a Thing, and a cut-out image in association with each other.

[0020] FIG. 2 is a flowchart illustrating a Fingerprint of Things detection method according to an embodiment. The image cropping unit 110 crops an image of one or more transported objects captured by an imaging unit into a cropped image (S11). The determination unit 111 determines whether or not there is an object to be determined from the cropped image (S12). If there is an object to be determined in the cropped image, the ID assigning unit 112 assigns an ID to the cropped image containing the object to be determined (S13). The Fingerprint of Things reading unit 120 reads the Fingerprint of the one or more objects to be determined from the cropped image containing the one or more objects to be determined (S14). The registration unit 121 associates the ID, Fingerprint of Things, and cropped image and registers them (S15).

[0021] The Fingerprint of Things detection system and method according to the embodiment described above can detect a Fingerprint of Things efficiently in real time.

[0022] FIG. 3 is a diagram illustrating an example of the configuration of a Fingerprint of Things detection system according to some embodiments. The Fingerprint of Things detection system 1a can be used to continuously acquire Fingerprints of Things from images captured by an imaging means 8 of one or more objects conveyed by a conveying device 5 (for example, a belt conveyor), and to register the Fingerprints of Things in a storage unit. The Fingerprints of Things have unique characteristics that differ from one another even for machine parts that are machined with high precision or parts manufactured from the same mold. Therefore, even for parts that are so small that they cannot be tagged or marked on the surface for identification, it is possible to identify the individual parts simply by capturing an enlarged image of the Fingerprint of Things with a camera under appropriate lighting conditions.

[0023] Until now, in component production lines, Fingerprint of Things detection processing has been performed in a line-out state using images of target objects (e.g., screws, bolts, etc.) captured by a camera. In other words, component production lines have performed sampling inspections rather than full inspections. However, it is desirable to realize Fingerprint of Things detection processing as efficiently as possible in real time while suppressing a decrease in production throughput in component production lines. Therefore, the present disclosure provides a Fingerprint of Things detection system, method, program, etc. that can detect Fingerprint of Things in real time and efficiently. This makes it possible to realize full inspection.

[0024] A scanner-type line camera is used as the imaging means 8. Fig. 4 is a block diagram illustrating an example of the configuration of a scanner-type line camera. A scanner-type line camera is a compact camera that integrates an imaging unit 81, a lens 82, a light source 83, etc. A scanner-type line camera can capture an image of a "line" as the object to be imaged is transported, rather than a "plane," and create a single image.

[0025] The light source 83 irradiates the surface of the object 5, which is the image capture target, with illumination light. The light source 83 irradiates the surface of the object 5 with illumination light that extends in a direction approximately perpendicular to the transport direction X1. The light source 83 is, for example, an LED (light emitting diode) array. The LED array is a plurality of LEDs arranged in a straight line.

[0026] The lens 82 is provided between the object 5 and the imaging unit 81. The lens 82 transmits light from the object 5. The transmitted light travels toward the imaging unit 81.

[0027] The imaging unit 81 may be any device that generates a monochrome image, such as a monochrome CCD (Charge Coupled Device) sensor or a monochrome CMOS (Complementary Metal Oxide Semiconductor) sensor.

[0028] Since the conveying device 2 may not transmit the object 5 at a constant speed (constant conveyance amount), a timing generator 7 is provided. That is, the timing generator 7 receives a rotation angle signal of the belt conveyor, which is the conveying device 2, and generates a line detection timing signal according to the conveyance amount indicated by the rotation angle signal. A rotary encoder is used for timing generation. A rotary encoder is a sensor that converts the mechanical displacement of rotation into an electrical signal and processes this signal to detect position, speed, etc. For details, please refer to JP 2021-141385 A.

[0029] The reading control unit 85 controls the operations of the imaging unit 81 and the light source 83 based on the line detection timing signal, and outputs the read image to the Fingerprint of Object detection device 10a.

[0030] The description will be continued by returning to Fig. 3. The Fingerprint of Things detection device 10a includes hardware 11a that performs preprocessing on an acquired read image in order to realize real-time detection of a Fingerprint of Things, and a server 12a that reads and registers a Fingerprint of Things from the image.

[0031] The pre-processing hardware 11a includes an image cropping unit 110a, a determination and ID assignment unit 111a, and a cropped image storage unit 115a. The image cropping unit 110a crops a read image into a cropped image. The image cropping unit 110a is an image cropping circuit, and can be realized by a logic circuit such as an FPGA (Field Programmable Gate Array).

[0032] The determination and ID assignment unit 111a determines whether or not an object to be determined exists in the cut-out image (using a known object recognition technique), and if the object to be determined exists in the cut-out image, assigns an ID to the cut-out image containing the object to be determined. The determination and ID assignment unit 111a is a determination circuit and an ID assignment circuit, and can be realized by a logic circuit such as an FPGA (Field Programmable Gate Array), for example.

[0033] FIG. 5 is a diagram for explaining a specific example of pre-processing required for real-time Fingerprint of Things detection. The Fingerprint of Things detection device 10a acquires a read image from a scanner-type line camera. The image cropping unit 110a crops the elongated read image into multiple standard-sized images. In FIG. 5, adjacent images are cropped without overlapping. If the same object to be determined is captured in multiple adjacent cropped images, the same ID may be assigned to the multiple cropped images. In another example, standard-sized images may be cropped with a margin such that adjacent cropped images partially overlap each other. This prevents an object from being present between the cropped images without overlapping, resulting in the object being captured in an interrupted manner. The size of the cropped images is determined depending on the conveying speed of the conveying device or the Fingerprint of Things reading performance of the server.

[0034] The determination and ID assignment unit 111a determines whether or not there is an object to be determined from a plurality of cutout images (using a known object recognition technology), and assigns individual IDs (for example, IDs A and B) to the cutout image containing the object A to be determined and the cutout image containing the object B to be determined. The cutout images to which IDs (for example, IDs A and B) have been assigned are transmitted to the server 12. Note that cutout images to which IDs have not been assigned do not need to be transmitted to the server 12 in order to reduce the load of detecting the Fingerprint of Things.

[0035] In this embodiment, the image cropping unit 110a and the determination and ID assignment unit 111a are realized by a logic circuit (hardware), and thus can perform preprocessing for performing Fingerprint of Things detection processing at high speed on a single elongated image captured by a "line."

[0036] The description will continue by returning to Fig. 3. The server 12a is realized by a computer having a processor, a memory, etc. The server 12a includes a Fingerprint of Things reading unit 120a, a Fingerprint of Things registration unit 121a, and a Fingerprint of Things storage unit 125a.

[0037] The Fingerprint of Things reading unit 120a reads the Fingerprint of the one or more objects to be determined (for example, objects A and B in FIG. 5) from the clipped image containing the one or more objects to be determined.

[0038] The Fingerprint of Things registration unit 121a registers the Fingerprint of Things of one or more Fingerprint of Things objects A and B to be determined in the Fingerprint of Things storage unit 125a.

[0039] The remote monitoring device 50 may be a computer connected to the server 12 via a wired or wireless network N. The remote monitoring device 50 may be monitored by one or more workers 3 who are remote monitors using various terminals. In the example of FIG. 3 , the remote monitoring device 50 includes, but is not limited to, a personal computer 51, a tablet terminal 52, and a smartphone 53. The remote monitoring device 50 may include at least one computer. The workers 3 can obtain Fingerprint of Things information, IDs, and cropped images from the server 12 via these terminals.

[0040] 6 is a flowchart illustrating a method for detecting a Fingerprint of an Object and a method for remote monitoring according to some embodiments. In this example, the transport device 5 is a belt conveyor, and the imaging means 8 is a scanner-type line camera.

[0041] The timing generator 7 receives a rotation angle signal of the belt conveyor which is the transport device 2, and generates a line detection timing signal according to the transport amount indicated by the rotation angle signal (S101). The scanner type line camera which is the imaging means 8 continuously captures images of the transported object in accordance with the line detection timing signal, and outputs the read images to the Fingerprint of Object detection device 10a (S102).

[0042] The image cutting circuit, which is the hardware 11a of the Fingerprint of Things detection device 10a, cuts out a plurality of standard-sized images from the read image (S103). The determination circuit reads out one cut-out image from the plurality of cut-out images and determines whether or not there is an object to be determined in the one cut-out image (S104). If it is determined that there is an object to be determined in the one cut-out image (YES in S105), the ID assignment circuit assigns an ID to the cut-out image containing the object to be determined (S106). If it is determined that there is no object to be determined in the one cut-out image (NO in S), the process returns to S104 and determines whether or not there is an object to be determined in another cut-out image.

[0043] The cut-out image to which the ID has been assigned is sent to the server 12 of the Fingerprint of Things detection device 10a. The Fingerprint of Things reading unit 120a of the server 12a reads the Fingerprint of Things of the object to be determined from the cut-out image containing the object to be determined (S107). The Fingerprint of Things registration unit 121a associates the ID of the cut-out image with the read Fingerprint of Things (S108), and registers the cut-out image, ID, and Fingerprint of Things in the Fingerprint of Things storage unit 125a in association with each other (S109).

[0044] The server 12a of the Fingerprint of Things detection device 10a confirms the reference request from the remote monitoring device 50 (S110). When the reference information is received (YES in S112), the server 12a outputs the cut-out image, ID, and Fingerprint of Things to the remote monitoring device 50 that made the reference request (S114).

[0045] FIG. 7 is a diagram illustrating an example of the configuration of a Fingerprint of Things detection system according to another embodiment. The Fingerprint of Things detection system 1b is basically the same as the Fingerprint of Things detection system 1a shown in FIG. 3, and the description thereof will be omitted where appropriate.

[0046] In the Fingerprint of Things detection system 1b, the appearance inspection device 30 can acquire the Fingerprint of Things in real time for one or more objects 5 manufactured and transported on a parts production line, and can also perform an appearance inspection of the manufactured objects 5. For this reason, the appearance inspection device 30 is added to the Fingerprint of Things detection system 1a. The appearance inspection device 30 includes an appearance inspection determination unit 31, an abnormality output unit 32, and an appearance inspection result storage unit 35. The appearance inspection device 30 can be realized by a computer having a processor, a memory, etc.

[0047] The appearance inspection device 30 acquires a cut-out image, an ID, and a Fingerprint of Things from the Fingerprint of Things storage unit 125b of the Fingerprint of Things detection device 10b. The appearance inspection determination unit 31 determines the appearance of the object to be determined in the cut-out image. The appearance inspection determination unit 31 analyzes the image to detect defects such as scratches and cracks in the object. The appearance inspection determination unit 31 may extract feature amounts of the object using known deep learning, and determine the presence or absence of a defect or the type of defect based on the feature amounts. The appearance inspection determination unit 31 associates the presence or absence of a defect, the type of defect, etc. with the cut-out image, ID, and Fingerprint of Things, and stores them in the appearance inspection result storage unit 35.

[0048] If the visual inspection result indicates that an object has a defect, the abnormality output unit 32 outputs an abnormality. For example, depending on the type of defect, the abnormality output unit 32 can issue an alarm to the worker 3 on-site or output a signal to stop the belt conveyor, as shown in FIG.

[0049] Alternatively, the abnormality output unit 32 may transmit an alarm signal to the remote monitoring device 50. In this case, the remote monitoring device 50 can send a request to the appearance inspection device 30 to refer to the cropped image, ID, and Fingerprint of Things for the defective object. In response to this, the appearance inspection device 30 or the Fingerprint of Things detection device 10b can output a request to the remote monitoring device 50 to refer to the cropped image, ID, and Fingerprint of Things for the defective object.

[0050] In another embodiment, a scanner-type line camera and a high-precision camera (9 in FIG. 7) may be used together as the imaging means 8. The high-precision camera 9 can acquire high-resolution images of, for example, 300 dpi (dots per inch) or 600 dpi. Fingerprint of Things reading and appearance inspection may be performed using an image captured by the high-precision camera associated with an object (or ID) captured by the scanner-type line camera.

[0051] 8 is a flowchart illustrating a visual inspection method and a remote monitoring method according to another embodiment. The processing in the first half of Fig. 8 is omitted because S101 to S106 are the same as those in Fig. 6.

[0052] The Fingerprint of Thing reading unit 120b acquires an image captured by the high-precision camera 9 associated with an object (or ID) captured by a scanner-type line camera (S206). The Fingerprint of Thing reading unit 120b reads the Fingerprint of Thing of the target to be determined from the high-precision image captured by the high-precision camera 9 (S207). The Fingerprint of Thing registration unit 121b associates the ID of a cut-out image corresponding to the captured image with the read Fingerprint of Thing (S208), and registers the cut-out image, high-precision image, ID, and Fingerprint of Thing in association with each other in the Fingerprint of Thing storage unit 125b (S209).

[0053] The appearance inspection determination unit 31 of the appearance inspection device 30 determines the appearance of the object to be determined using the cropped image or the high-precision image (S210). If the determination result indicates an abnormality (YES in S212), the abnormality output unit 32 outputs the abnormality (S214). For example, as shown in FIG. 7, the abnormality output unit 32 can issue an alarm to the worker 3 on-site or output a signal to stop the belt conveyor depending on the type of defect. The abnormality output unit 32 can also output the abnormality to the remote monitoring device 50.

[0054] The server 12b of the Fingerprint of Things detection device 10b confirms the reference request from the remote monitoring device 50 (S215). When the reference information is received (YES in S216), the server 12b outputs the cut-out image, the high-precision image, the ID, and the Fingerprint of Things to the remote monitoring device 50 that made the reference request (S218).

[0055] FIG. 9 is a block diagram showing a configuration example of a Fingerprint of Things detection device, etc. The Fingerprint of Things detection device 10, etc. may include servers 12a and 12b of Fingerprint of Things detection devices 10a and 10b, an appearance inspection device 30, and a remote monitoring device 50. Referring to FIG. 9, the Fingerprint of Things detection device 10, etc. includes a network interface 1201, a processor 1202, and a memory 1203. The network interface 1201 is used to communicate with other network node devices constituting a communication system. The network interface 1201 may be used for wireless communication. For example, the network interface 1201 may be used for wireless LAN communication defined in the IEEE 802.11 series or mobile communication defined in 3GPP (3rd Generation Partnership Project). Alternatively, the network interface 1201 may include a network interface card (NIC) conforming to the IEEE 802.3 series.

[0056] The processor 1202 reads and executes software (computer programs) from the memory 1203 to perform the processes of the Fingerprint of Object detection device 10 and the like described using flowcharts or sequences in the above-described embodiments. The processor 1202 may be, for example, a microprocessor, an MPU (Micro Processing Unit), a CPU (Central Processing Unit), or a GPU (Graphics Processing Unit). The processor 1202 may include multiple processors.

[0057] The memory 1203 is configured by a combination of volatile memory and non-volatile memory. The memory 1203 may include storage located remotely from the processor 1202. In this case, the processor 1202 may access the memory 1203 via an I / O interface (not shown).

[0058] 9, the memory 1203 is used to store software modules. The processor 1202 reads these software modules from the memory 1203 and executes them to perform the processing of the Fingerprint of Things detection device 10 and the like described in the above-described embodiment.

[0059] As explained using FIG. 9, each of the processors included in the Fingerprint of Things detection device 10, etc. executes one or more programs including a group of instructions for causing a computer to perform the algorithms explained using FIG. 6, FIG. 8, etc.

[0060] In the above examples, the program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray® disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0061] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0062] Each drawing is merely an example for describing one or more embodiments. Each drawing may relate not only to one particular embodiment, but also to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0063] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. (Appendix 1) an image cutout means for cutting out a captured image of one or more objects being conveyed, the captured image being taken by the imaging means, into a cutout image; a determination means for determining whether or not an object to be determined is present from the extracted image; an ID assigning means for assigning an ID to the cut-out image containing the object to be determined if the cut-out image contains the object to be determined; a Fingerprint of Things reading means for reading the Fingerprint of one or more objects to be determined from the extracted image having the objects; a registration means for registering the ID, the Fingerprint of Things, and the extracted image in association with each other, Object fingerprint detection system. (Appendix 2) the imaging means is a scanner-type line camera, 2. The object fingerprint detection system according to claim 1, further comprising a timing generator that generates a reading timing signal for the scanner-type line camera in accordance with a conveying speed of a conveying device that conveys the object. (Appendix 3) the conveying device is a belt conveyor, 3. The object fingerprint detection system according to claim 2, wherein the timing generator receives a rotation angle signal from the belt conveyor and generates the timing signal for the scanner-type line camera. (Appendix 4) the cutout means, the determination means, and the ID assignment means are an image cutout circuit, a determination circuit, and an ID assignment circuit implemented by FPGAs (field programmable gate arrays), The Fingerprint of Things detection system described in Appendix 1, wherein the Fingerprint of Things reading means and the registration means are implemented by a server computer including at least one processor and a memory coupled to the at least one processor. (Appendix 5) a cut-out image storage unit that stores the cut-out image; The Fingerprint of Things detection system according to Supplementary Note 1, further comprising: a Fingerprint of Things information storage unit that stores the ID and the clipped image containing the object to be determined as the Fingerprint of Things in association with each other. (Appendix 6) an appearance inspection and judgment means for inspecting the appearance of an object from the extracted image containing the object to be judged and judging whether the appearance of the object is good or bad based on the inspection results; 6. The Fingerprint of Things detection system according to claim 5, further comprising: an output unit that outputs an abnormality based on the result of determining whether the appearance of the object is good or bad. (Appendix 7) further comprising a visual inspection determination result storage unit that stores the determination result of the visual inspection, 7. The Fingerprint of Things detection system according to claim 6, further comprising a remote monitoring device connected to the Fingerprint of Things information storage unit or the appearance inspection determination result storage unit via a network. (Appendix 8) 2. The Fingerprint of Object detection system according to claim 1, wherein the cut-out image has a predetermined standard size. (Appendix 9) Cutting out a captured image of one or more objects being conveyed by the imaging means into a cut-out image; determining whether or not an object to be determined exists from the extracted image; If the object to be determined is present in the cut-out image, an ID is assigned to the cut-out image containing the object to be determined; reading a fingerprint of one or more objects to be determined from the extracted image having the one or more objects to be determined; The ID, the Fingerprint of Things, and the cut-out image are associated with each other and registered. Object fingerprint detection method. (Appendix 10) Cutting out a captured image of one or more objects being conveyed by the imaging means into a cut-out image; determining whether or not an object to be determined exists from the extracted image; If the object to be determined is present in the cut-out image, an ID is assigned to the cut-out image containing the object to be determined; reading a fingerprint of one or more objects to be determined from the extracted image having the one or more objects to be determined; A program that causes a computer to register the ID, the Fingerprint of Things, and the extracted image in association with each other.

[0064] Some or all of the elements (e.g., configurations and functions) described in Supplementary Notes 2 to 8 that are dependent on Supplementary Note 1 may also be dependent on Supplementary Notes 9 and 10 in the same dependency relationship as Supplementary Notes 2 to 8. Some or all of the elements described in any Supplementary Note may be applied to various hardware, software, recording means for recording software, systems, and methods. [Explanation of symbols]

[0065] 1. 1a Object Fingerprint Detection System 2. Conveyor equipment 3. Workers 5 objects 7 Timing Generator 8. Imaging means 9 High-precision cameras 10 Object Fingerprint Detection Device 50 Remote monitoring device 30 Visual inspection equipment 31 Visual Inspection and Judgment Department 32 Abnormal output section 35 Visual inspection result storage unit 110 Image cropping section 111 Judgment section 112 ID Assignment Department 120 Object Fingerprint Reader 121 Fingerprint of Object Registration Unit 110a, 110b image cutting section 111a, 111b Judgment and ID assignment unit 120a, 120b Object fingerprint reading unit 121a, 121b Object fingerprint registration unit 125a, 125b Object fingerprint storage section

Claims

1. an image cutout means for cutting out a captured image of one or more objects being conveyed, the captured image being taken by the imaging means, into a cutout image; a determination means for determining whether or not an object to be determined is present from the extracted image; an ID assigning means for assigning an ID to the cut-out image containing the object to be determined if the cut-out image contains the object to be determined; a fingerprint of thing reading means for reading a fingerprint of one or more objects to be determined from the extracted image having the objects; a registration means for registering the ID, the Fingerprint of Things, and the extracted image in association with each other, Object fingerprint detection system.

2. the imaging means is a scanner-type line camera, 2. The fingerprint detection system according to claim 1, further comprising a timing generator that generates a reading timing signal for the scanner-type line camera in accordance with a conveying speed of a conveying device that conveys the object.

3. the conveying device is a belt conveyor, 3. The fingerprint detection system according to claim 2, wherein the timing generator receives a rotation angle signal from the belt conveyor and generates the timing signal for the scanner-type line camera.

4. the cutout means, the determination means, and the ID assignment means are an image cutout circuit, a determination circuit, and an ID assignment circuit implemented by FPGAs (field programmable gate arrays), The Fingerprint of Things detection system according to claim 1 , wherein the Fingerprint of Things reading means and the registration means are implemented by a server computer including at least one processor and a memory coupled to the at least one processor.

5. a cut-out image storage unit that stores the cut-out image; The Fingerprint of Things detection system according to claim 1 , further comprising: a Fingerprint of Things information storage unit that stores the ID and the clipped image containing the object to be determined as the Fingerprint of Things in association with each other.

6. an appearance inspection and judgment means for inspecting the appearance of an object from the extracted image containing the object to be judged and judging whether the appearance of the object is good or bad based on the inspection results; 6. The Fingerprint of Object detection system according to claim 5, further comprising: an output unit that outputs an abnormality based on the result of the judgment of whether the appearance of the object is good or bad.

7. further comprising a visual inspection determination result storage unit that stores the determination result of the visual inspection; 7. The Fingerprint of Things detection system according to claim 6, further comprising a remote monitoring device connected to the Fingerprint of Things information storage unit or the appearance inspection determination result storage unit via a network.

8. The Fingerprint of Object detection system according to claim 1 , wherein the cut-out image has a predetermined standard size.

9. Cutting out a captured image of one or more objects being conveyed by the imaging means into a cut-out image; determining whether or not an object to be determined exists from the extracted image; If the target to be determined is present in the cut-out image, an ID is assigned to the cut-out image containing the target to be determined; reading a fingerprint of one or more objects to be determined from the extracted image having the one or more objects to be determined; the ID, the Fingerprint of Things, and the extracted image are registered in association with each other; Object fingerprint detection method.

10. Cutting out a captured image of one or more objects being conveyed by the imaging means into a cut-out image; determining whether or not an object to be determined exists from the extracted image; If the target to be determined is present in the cut-out image, an ID is assigned to the cut-out image containing the target to be determined; reading a fingerprint of one or more objects to be determined from the extracted image having the one or more objects to be determined; A program that causes a computer to register the ID, the Fingerprint of Things, and the extracted image in association with each other.

Images