Image inspection system and image inspection method

Abstract

To provide a technique capable of appropriately performing reinspection of an inspection object subjected to image inspection.SOLUTION: The image inspection system 1 can communicate with a blockchain, and inspects an inspection object using a captured image Dp of the inspection object. The image inspection system 1 includes the inspection section 42 that inspects the captured image Dp and outputs the inspection history Dr, the hash value generation section 43 that generates the last hash value Dh based on the last inspection history Dr and the hash value Dh before last, the image storage section 3 that stores the inspected captured image Dp, the plurality of data storage sections 40,91 that store the data sets Ds in which the inspection history Dr and the hash value Dh are combined, the transmission section 45 that transmits the latest data set Ds to each data storage section 40,91 every time the inspection of the inspection section 42 is completed, and the read section 46 that can read the past data set Ds from the data storage section 40,91.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an image inspection system and an image inspection method for inspecting a captured image of an object to be inspected. [Background technology]

[0002] Conventionally, image inspection devices have been known that inspect objects, such as parts of equipment, by taking images of the objects and processing the images. After shipping, it may become necessary to prove that the inspection was correct, based on customer requests or other factors. While it is possible to submit the inspection history and results stored in the inspection device as evidence, it has been difficult to prove that the inspection history and results have not been tampered with.

[0003] In response to this, blockchain has been used in recent years as a method for guaranteeing the authenticity (non-tampering) of digital data. For example, in Patent Document 1, the operation history of an imaging device is managed using a blockchain. Blockchain uses a distributed ledger system in which the same data is shared among multiple nodes, and records data by linking it in a chain in units called blocks.

[0004] Blockchain employs a distributed ledger system, making it easy to detect tampering even if it occurs in some nodes, as it does not affect other nodes. Furthermore, each block contains the hash value of the data contained in the previous block. This makes tampering difficult because tampering with data in a past block will no longer be consistent with the hash values ​​of all subsequent blocks. Using such a blockchain makes it possible to prevent tampering with inspection history and results, making it possible to present accurate inspection history and results. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2022-121619 Summary of the Invention [Problem to be solved by the invention]

[0006] However, there are cases where further verification is required and the images used during the inspection must be re-examined. Compared to inspection history and results, the amount of data in images is large, making them impossible to include in a blockchain. For this reason, it is difficult to prevent tampering with images to the same extent as using a blockchain.

[0007] An object of the present invention is to provide a technique that allows appropriate re-inspection of an inspection object that has undergone image inspection. [Means for solving the problem]

[0008] In order to solve the above problem, the first invention is an image inspection system capable of communicating with a blockchain, which inspects an object to be inspected using a photographed image of the object, and which comprises: an inspection unit which inspects the photographed image and outputs an inspection history; a hash value generation unit which generates the previous hash value based on the previous inspection history and the hash value from the inspection before that; an image storage unit which stores the inspected photographed image; a plurality of data storage units which store a data set combining the inspection history and the hash value; a transmission unit which transmits the latest data set combining the latest inspection history and the previous hash value to each data storage unit each time the inspection unit completes an inspection; and a reading unit which is capable of reading past data sets from the data storage units.

[0009] The second invention is an image inspection system of the first invention, comprising an inspection device having the inspection unit, an image storage device constituting the image storage unit, and a plurality of nodes of a blockchain, wherein the inspection device, the image storage device, and each of the nodes of the blockchain are communicatively connected via the Internet, and each of the nodes of the blockchain functions as one of the data storage units.

[0010] The third invention is an image inspection system of the first invention, comprising a plurality of inspection devices each having the inspection unit, the hash value generation unit, the transmission unit, and the reading unit, and an image storage device that constitutes the image storage unit, wherein the plurality of inspection devices and the image storage device are connected to each other so as to be able to communicate via the Internet, and each of the inspection devices is equipped with one of the data storage units.

[0011] The fourth invention is an image inspection system according to any one of the first to third inventions, wherein the inspection history includes at least the inspection conditions in the inspection section and used image information, which is information about the captured image used.

[0012] A fifth aspect of the present invention is the image inspection system of the fourth aspect of the present invention, wherein the used image information includes a hash value of the photographed image that was used.

[0013] A sixth invention is an image inspection method for inspecting an object to be inspected using a photographed image of the object to be inspected, the method comprising: a) an image acquisition step of photographing the object to be inspected and acquiring the photographed image; b) an inspection step of inspecting the photographed image obtained in step a) by image processing; c) a step of generating a previous hash value from a previous inspection history in step b) and a hash value from the time before last; d) a data storage step of storing a data set combining the current inspection history in step b) and the previous hash value in a plurality of data storage units; and e) an image storage step of storing the photographed image obtained in step a) in an image storage unit. Repeat this process.

[0014] The seventh invention is an image inspection method of the sixth invention, which includes, after repeating steps a) to e) multiple times, f) a first readout step of reading out from the image memory unit a specific captured image, which is the captured image of the object to be inspected again, g) a second readout step of reading out from the data memory unit the data set corresponding to the specific captured image, h) a re-inspection step of re-inspecting the specific captured image read out in step f) by image processing, and i) a comparison step of comparing the inspection result in step h) with the contents of the inspection history included in the data set read out in step g).

[0015] The eighth invention is an image inspection method according to the seventh invention, wherein the inspection history includes at least the inspection conditions in step b), and in step h), a re-inspection is performed using the inspection conditions included in the data set read in step g).

[0016] A ninth invention is an image inspection method according to the seventh or eighth invention, wherein at least some of the plurality of data storage units are nodes of a blockchain.

[0017] A tenth aspect of the present invention is the image inspection method of the seventh or eighth aspect of the present invention, wherein an inspection device that performs step b) includes one of the data storage units.

[0018] An eleventh invention is an image inspection method according to the seventh or eighth invention, wherein the inspection history includes at least a hash value of the photographed image used as used image information, which is information about the photographed image used. [Effects of the Invention]

[0019] According to the first to eleventh aspects of the invention, it is possible to appropriately re-inspect an inspection object that has undergone image inspection. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a schematic diagram of an image inspection system according to a first embodiment. [Figure 2] FIG. 1 is a functional block diagram of an image inspection system according to a first embodiment. [Figure 3] 1A and 1B are diagrams showing an example of an image inspection according to the first embodiment and an example of a data set created from the inspection history. [Figure 4] 4 is a flowchart showing the flow of a normal image inspection process in the image inspection system according to the first embodiment. [Figure 5] 10 is a flowchart showing the flow of re-inspection in the image inspection system according to the first embodiment. [Figure 6] FIG. 10 is a schematic diagram of an image inspection system according to a second embodiment. [Figure 7] FIG. 10 is a functional block diagram of an image inspection system according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0021] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings. Note that the components described in the embodiment are merely examples and are not intended to limit the scope of the present invention. In the drawings, the dimensions and numbers of each part may be exaggerated or simplified as necessary to facilitate understanding.

[0022] 1. First Embodiment <1-1. Image inspection system> FIG. 1 is a schematic diagram of an image inspection system 1 according to a first embodiment. This image inspection system 1 is a system that performs inspection by image processing of photographed images of an object to be inspected. The object to be inspected may be, for example, an industrial product part such as an automobile part, a final product itself such as a wooden toy, or any other object that can be inspected from a photographed image. Furthermore, the photographed image is not limited to an image taken under a normal visible light environment, and may be an X-ray photographed image, etc.

[0023] The image inspection system 1 includes an inspection device 2, a mass storage device 3, and a blockchain network 9. The inspection device 2, the mass storage device 3, and the blockchain network 9 are connected via the Internet N.

[0024] The inspection device 2 has a computer 21 and an imaging unit 22. The computer 21 includes a processor 211 such as a CPU, a memory 212 such as a RAM, and a storage unit 213 such as a hard disk drive. The memory 212 and the storage unit 213 are connected to the processor 211 via a bus wiring (not shown). The storage unit 213 stores a computer program P1. The processor 211 loads the computer program P1 stored in the storage unit 213 into the memory 212 and sequentially executes codes included in the computer program P1. As a result, the inspection device 2 performs an imaging process of the inspection object in the imaging unit 22, an inspection process for the captured image Dp captured by the imaging unit 22, and a storage process of the inspection history of the inspection process.

[0025] The imaging unit 22 may be a device separate from the inspection device 2. In that case, the inspection device 2 receives a captured image Dp of the inspection object from an external imaging device serving as the imaging unit 22, for example, via an intranet or the Internet, and performs an inspection on the captured image Dp.

[0026] 2 is a functional block diagram showing the functions of the image inspection system 1. The computer 21 has a first storage unit 40, an imaging control unit 41, an inspection unit 42, a hash value generation unit 43, a data set generation unit 44, a transmission unit 45, and a readout unit 46. The imaging control unit 41, the inspection unit 42, the hash value generation unit 43, the data set generation unit 44, the transmission unit 45, and the readout unit 46 are functions realized by the processor 211 executing a computer program P1.

[0027] The first storage unit 40 is a storage unit provided within the computer 21. The memory 212 of the computer 21 may be used as the first storage unit 40, or it may be a storage unit provided separately from the memory 212.

[0028] The photographing control unit 41 is a control unit that controls photographing of the inspection object in the imaging unit 22. The photographing control unit 41 acquires a photographed image Dp of the inspection object by causing the imaging unit 22 to photograph the inspection object. The photographing control unit 41 transfers the acquired photographed image Dp to the inspection unit 42 and the transmission unit 45.

[0029] The inspection unit 42 inspects the inspection object using the photographed image Dp of the inspection object. Then, the inspection unit 42 outputs an inspection history Dr including the inspection conditions and inspection results of the photographed image Dp, and hands it over to the data set generation unit 44.

[0030] When a re-examination is performed, the inspection unit 42 acquires the specific photographed image Dp* to be re-examined via the readout unit 46, and also reads out the inspection history Dr* included in the data set Ds when the specific photographed image Dp* was previously inspected from the first storage unit 40. The specific photographed image Dp* is then inspected using the inspection process and parameters recorded in the inspection history Dr*. After the re-examination is completed, the inspection unit 42 determines whether the inspection results of the re-examination are the same as the inspection results included in the inspection history Dr*.

[0031] 3 is a diagram showing an example of an inspection performed by the inspection unit 42 and an example of a data set Ds created from the inspection history Dr. As shown in Fig. 3, the image inspection performed by the inspection unit 42 determines whether or not there is a defect in the inspection object shown in the captured image Dp by performing multiple image processing steps A, B, and C on the captured image Dp.

[0032] 3, the inspection history Dr output by the inspection unit 42 after the inspection is completed includes, for example, the hash value of the captured image Dp, the type of inspection process performed, the parameters used in each inspection process, and the inspection results indicating the presence or absence of defects. In the image inspection system 1, this inspection history Dr is stored in the form of a blockchain Db in multiple data storage units including the first storage unit 40 and multiple nodes of the blockchain network 9, which will be described later.

[0033] As shown in Fig. 3, hereinafter, each block in the blockchain Db will be referred to as a data set Ds. A data set Ds is created for each inspection that is repeatedly performed by the inspection unit 42. Below, the data set Ds for the current inspection may be referred to as the "current data set Ds" or the "new data set Ds," and the data set Ds for the previous inspection may be referred to as the "previous data set Ds'."

[0034] The data set Ds includes the inspection history Dr for that inspection and a previous hash value Dh, which is the hash value of the previous data set Ds'. The previous data set Ds' includes the inspection history Dr' for the previous inspection and a previous-to-previous hash value Dh', which is the hash value of the data set before the previous. In this way, by creating a blockchain Db in which each data set Ds includes the hash value Dh of the previous data set Ds, it is possible to prevent tampering with the individual inspection histories Dr.

[0035] The hash value generation unit 43 reads the previous data set Ds' from the first memory unit 40, and generates a new hash value Dh (previous hash value Dh) based on the previous inspection history Dr' and the previous-to-last hash value Dh' contained in the previous data set Ds'.

[0036] The dataset generation unit 44 generates a dataset Ds by combining the current inspection history Dr output by the inspection unit 42 and the previous hash value Dh generated by the hash value generation unit 43. Thereafter, the dataset generation unit 44 delivers the new dataset Ds to the first storage unit 40 and the transmission unit 45. Then, the first storage unit 40 stores the delivered dataset Ds in addition to the blockchain Db composed of past datasets Ds.

[0037] The transmission unit 45 transmits the captured image Dp delivered from the photography control unit 41 to the mass storage 3 via the Internet N. In addition, the transmission unit 45 transmits the data set Ds delivered from the data set generation unit 44 to each node 91 (described later) of the blockchain network 9 via the Internet N.

[0038] The reading unit 46 reads the specific photographed image Dp* to be re-examined from the mass storage 3 via the Internet N, and transfers it to the inspection unit 42.

[0039] The large-capacity storage 3 is an image storage unit that stores inspected captured images Dp. The large-capacity storage 3 is communicably connected to the inspection device 2 via the Internet N. The large-capacity storage 3 is configured with a storage device such as a hard disk drive. The large-capacity storage 3 may be cloud storage or the like. The large-capacity storage 3 stores a plurality of captured images Dp. The large-capacity storage 3 may be connected to the inspection device 2 without going through the Internet N.

[0040] The blockchain network 9 is a distributed network consisting of multiple nodes 91. The nodes 91 are individual computers that make up the blockchain network 9. The nodes 91 perform tasks related to the operation of the network, such as creating and verifying blocks, which are units for storing data. When a new block is added to the network, it is linked to an existing blockchain (chain of blocks). Each block in the blockchain contains a hash (unique identifier) ​​of the previous block, thereby maintaining the integrity and security of the blockchain. In this embodiment, a data set Ds is sent as a block to each node 91, and a new data set Ds is linked to the existing blockchain Db as a new block each time the inspection unit 42 performs an inspection.

[0041] <1-2. Normal image inspection processing> Next, normal image inspection processing in the image inspection system 1 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the flow of normal image inspection processing in the image inspection system 1. In the image inspection system 1, the image inspection processing shown in Fig. 4 is performed on a plurality of inspection objects. Therefore, the image inspection processing shown in Fig. 4 is performed repeatedly many times.

[0042] In a normal image inspection process, first, the photography control unit 41 controls the imaging unit 22 to photograph the inspection object and acquire a photographed image Dp (step S101: image acquisition step). Then, the photography control unit 41 transfers the photographed image Dp to the inspection unit 42 and the transmission unit 45.

[0043] The transmission unit 45 transmits the captured image Dp to the mass storage 3 via the Internet N. Then, the captured image Dp is stored in the mass storage 3 (step S102: captured image storage step). Note that step S102 may be performed in parallel with steps S103 to S105 or after steps S103 to S105.

[0044] Next, the inspection unit 42 inspects the captured image Dp by image processing (step S103: inspection process). In the example of Fig. 3, the inspection unit 42 performs three types of image processing, namely, image processing A, image processing B, and image processing C, on the captured image Dp to obtain an inspected image Df and an inspection result. In the example of Fig. 3, the image processing determines whether or not the object to be inspected shown in the captured image Dp has a defect, and if a defect is present, the defect position is detected.

[0045] Furthermore, the inspection unit 42 passes the inspection history Dr of step S102 to the data set generation unit 44. In the example of Fig. 3, the inspection history Dr includes an image hash value, inspection process information, parameters for each inspection process, and inspection results.

[0046] The image hash value is the hash value of the photographed image Dp. In other words, the image hash value is used image information, which is information about the photographed image Dp that was used. If the photographed image Dp has been tampered with, the hash value of the image after tampering will be different from the hash value of the photographed image Dp before tampering. Therefore, by including the image hash value as used image information in the inspection history Dr rather than simply being information linked to the photographed image Dp, it is possible to prove that the specific photographed image Dp* that is the subject of re-inspection has not been tampered with when a re-inspection is performed.

[0047] The inspection history Dr also includes inspection process information indicating what inspection process was performed and parameters for each inspection process as inspection conditions in the inspection unit 42. This allows image inspection to be performed under the same conditions as those used in the normal inspection when re-examination is performed.

[0048] Meanwhile, the hash value generation unit 43 reads the previous data set Ds' from the first storage unit 40, and generates a previous hash value Dh based on the previous inspection history Dr' and the hash value Dh' before last included in the previous data set Ds' (step S104: hash value generation step).The hash value generation unit 43 then passes the generated previous hash value Dh to the data set generation unit 44. Note that step S104 may be performed in parallel with steps S101 to S103, or before steps S101 to S103.

[0049] After steps S103 and S104, the dataset generation unit 44 generates a dataset Ds by combining the inspection history Dr and the previous hash value Dh. Then, the dataset Ds is stored in the first storage unit 40 and the multiple nodes 91 of the blockchain network 9 (step S105: data storage step). Specifically, the dataset generation unit 44 transfers the generated dataset Ds to the first storage unit 40 and transmits it to the multiple nodes 91 of the blockchain network 9 via the transmission unit 45. Then, the first storage unit 40 and each node 91 store the transferred dataset Ds in addition to a blockchain Db composed of past datasets Ds.

[0050] As described above, normal image inspection processing is performed, whereby the captured image Dp used in the image inspection and the inspection history Dr including the inspection conditions and inspection results are stored in a state that makes it difficult to tamper with.

[0051] <1-3. Re-inspection process> Next, the re-inspection process in the image inspection system 1 will be described with reference to Fig. 5. Fig. 5 is a flowchart showing the flow of the re-inspection process in the image inspection system 1. This re-inspection process inspects a specific captured image Dp*, which is a captured image Dp of an inspection object to be re-inspected, under the same inspection conditions as those applied in the normal image inspection process.

[0052] When re-inspection is performed, the inspection device 2 first reads out the specific photographed image Dp* to be re-inspected from the mass storage 3 via the Internet N using the reading unit 46 (step S201: first reading step). Then, the reading unit 46 delivers the specific photographed image Dp* to the inspection unit 42.

[0053] Next, the inspection unit 42 reads out from the first storage unit 40 a dataset Ds* that includes an inspection history Dr when a previous inspection was performed on the specific photographed image Dp* (step S202: second reading step). At this time, the reading unit 46 may read out the dataset Ds* stored in any of the nodes 91 in the blockchain network 9 and compare it with the dataset Ds* read out from the first storage unit 40 to confirm that the dataset Ds* has not been tampered with.

[0054] Thereafter, the inspection unit 42 re-inspects the specific photographed image Dp* read out in step S201 by image processing (step S203: re-inspection step). Finally, the inspection device 2 compares the inspection result in step S203 with the inspection result included in the data set Ds* read out in step S202 (step S204: result confirmation step).

[0055] Here, in step S203, the inspection unit 42 can refer to the inspection history Dr included in the data set Ds* read in step S202 and perform an inspection using the inspection conditions included in the inspection history Dr. In this case, a re-inspection is performed under the same conditions as the previous image inspection process, so it is possible to determine whether the previous image inspection process was correct.

[0056] On the other hand, in step S203, the inspection unit 42 can also perform an inspection under conditions different from the inspection conditions included in the inspection history Dr included in the data set Ds* read out in step S202. In this case, a re-inspection is performed under conditions different from those of the previous image inspection process, and it can be determined whether the inspection conditions in the previous image inspection process were appropriate.

[0057] 2. Second Embodiment <2-1. Image inspection system> Fig. 6 is a schematic diagram of an image inspection system 1A according to the second embodiment. Fig. 7 is a functional block diagram showing the functions of the image inspection system 1A. This image inspection system 1A has multiple inspection devices 2A, 2B, and 2C, a large-capacity storage 3A, a management server 8A, and a blockchain network 9. The inspection devices 2A, 2B, and 2C, the management server 8A, and the blockchain network 9 are connected via the Internet N.

[0058] The image inspection system 1A of the second embodiment differs from the image inspection system 1 of the first embodiment in that it includes a plurality of inspection devices 2A, 2B, and 2C, has a management server 8A, and has a large-capacity storage 3A connected to the Internet N via the management server 8A. The following description will focus on the differences from the first embodiment, and the points in common with the first embodiment will be denoted by the same reference numerals in Figures 6 and 7 and will not be described again.

[0059] Since the multiple inspection devices 2A, 2B, and 2C all have the same configuration, only one inspection device 2A will be described. Similar to the inspection device 2 of the first embodiment, the computer 21A of the inspection device 2A has a first storage unit 40, an imaging control unit 41, a first transmission unit 45A, and a first readout unit 46A. Meanwhile, the computer 21A does not have a hash value generation unit or a data set generation unit. These functions are possessed by the management server 8A. The inspection device 2A performs an imaging process of the inspection object in the imaging unit 22, an inspection process on the captured image Dp captured by the imaging unit 22, and a storage process of the data set Ds generated by the management server 8A.

[0060] The management server 8A is a computer including a processor 81A such as a CPU, a memory 82A such as RAM, and a storage unit 83A such as a hard disk drive. The memory 82A and the storage unit 83A are connected to the processor 81A via a bus line (not shown). The storage unit 83A stores a computer program P2. The processor 81A loads the computer program P2 stored in the storage unit 83A into the memory 82A and sequentially executes the codes included in the computer program P2. As a result, the management server 8A generates a data set Ds from the inspection results performed by each of the inspection devices 2A, 2B, and 2C, and stores the data set Ds in a first storage unit 40, which is a data storage unit, a second storage unit 50A (described later), and multiple nodes 91 of the blockchain network 9.

[0061] Furthermore, in the second embodiment, the mass storage 3A is not directly connected to the Internet N. In the second embodiment, the management server 8A is connected to the mass storage 3A and manages the mass storage 3A. Therefore, the storage of the captured image Dp in the mass storage 3A and the reading of the previously captured image Dp such as the specific captured image Dp* from the mass storage 3A are performed via the management server 8A.

[0062] The management server 8A has a second storage unit 50A, a second transmission unit 51A, a second reading unit 52A, a hash value generation unit 43A, and a data set generation unit 44A. The second transmission unit 51A, the second reading unit 52A, the hash value generation unit 43A, and the data set generation unit 44A are functions realized by the processor 81A executing a computer program P2.

[0063] The second storage unit 50A is a storage unit provided in the management server 8A. The memory 82A of the management server 8A may be used as the second storage unit 50A, or it may be a storage unit provided separately from the memory 82A.

[0064] <2-2. Normal image inspection processing> A normal image inspection process in the image inspection system 1A according to the second embodiment will be described with reference to FIG.

[0065] First, in the inspection device 2A, the photography control unit 41 controls the imaging unit 22, causing the imaging unit 22 to photograph the inspection object and acquire a photographed image Dp (step S101: image acquisition step). Then, the photography control unit 41 transfers the photographed image Dp to the inspection unit 42 and the first transmission unit 45A.

[0066] The first transmission unit 45A transmits the captured image Dp to the management server 8A via the Internet N. Then, the management server 8A stores the captured image Dp in the mass storage 3 (step S102: captured image storage step). Note that step S102 may be performed in parallel with steps S103 to S105 or after steps S103 to S105.

[0067] Next, the inspection unit 42 inspects the captured image Dp by image processing (step S103: inspection step). Furthermore, the inspection unit 42 transfers the inspection history Dr to the management server 8A via the first transmission unit 45A. The management server 8A transfers the inspection history Dr to the data set generation unit 44A via the second reading unit 52A.

[0068] Meanwhile, the hash value generation unit 43A reads the previous data set Ds' from the second storage unit 50A, and generates a previous hash value Dh based on the previous inspection history Dr' and the hash value Dh' before last included in the previous data set Ds' (step S104: hash value generation step).The hash value generation unit 43A then passes the generated previous hash value Dh to the data set generation unit 44A.Note that step S104 may be performed in parallel with steps S101 to S103, or before steps S101 to S103.

[0069] After steps S103 and S104, the data set generation unit 44A generates a data set Ds that combines the inspection history Dr and the previous hash value Dh. Then, the data set Ds is stored in the first storage unit 40, the second storage unit 50A, and the multiple nodes 91 of the blockchain network 9 (step S105: data storage step).

[0070] Specifically, the dataset generation unit 44A delivers the generated dataset Ds to the second storage unit 50A and transmits it to each of the inspection devices 2A, 2B, and 2C and multiple nodes 91 of the blockchain network 9 via the second transmission unit 51A. Each of the inspection devices 2A, 2B, and 2C stores the dataset Ds received via the first reading unit 46A in the first storage unit 40, in addition to a blockchain Db configured from past datasets Ds. Furthermore, each node 91 of the blockchain network 9 stores the delivered dataset Ds in addition to a blockchain Db configured from past datasets Ds.

[0071] <2-3. Re-inspection process> Next, the re-inspection process in the image inspection system 1A according to the second embodiment will be described with reference to FIG.

[0072] When performing a re-inspection, the inspection device 2A first reads out the specific photographed image Dp* to be re-inspected from the mass storage 3A via the Internet N and the management server 8A using the first reading unit 46A (step S201: first reading step). Then, the first reading unit 46A delivers the specific photographed image Dp* to the inspection unit 42.

[0073] Next, the inspection unit 42 reads out from the first storage unit 40 a data set Ds* including an inspection history Dr when a previous inspection was performed on the specific captured image Dp* (step S202: second reading step). At this time, the first reading unit 46A may read out a data set Ds* stored in the first storage unit 40 of another inspection device 2B, 2C, the second storage unit 50A of the management server 8A, or any node 91 of the blockchain network 9, and compare it with the data set Ds* read out from the first storage unit 40 to confirm that the data set Ds* has not been tampered with.

[0074] Thereafter, the inspection unit 42 re-inspects the specific photographed image Dp* read out in step S201 by image processing (step S203: re-inspection step). Finally, the inspection device 2A compares the inspection result in step S203 with the inspection result included in the data set Ds* read out in step S202 (step S204: result confirmation step).

[0075] As in the image inspection system 1A according to the second embodiment, the hash value Dh and the data set Ds may be generated by the management server 8A instead of by each of the inspection devices 2A, 2B, and 2C.

[0076] Furthermore, in the image inspection system 1A according to the second embodiment, not only the first storage unit 40 of the inspection device 2A that performed the inspection and each node 91 of the blockchain network 9 are used as data storage units for storing the blockchain Db composed of the data set Ds, but also the first storage units 40 of the other inspection devices 2B and 2C and the second storage unit 50A of the management server 8A. In this way, the blockchain Db composed of the data set Ds for one inspection device 2A may also be stored in the other inspection devices 2B and 2C or the management server 8A. Note that the data sets Ds of multiple inspection devices 2A, 2B, and 2C may be stored as a single blockchain Db.

[0077] <3. Modifications> Although the embodiments have been described above, the present invention is not limited to the above and various modifications are possible.

[0078] In the above embodiment, the blockchain made up of the data set is stored in a data storage unit inside the inspection device that performed the inspection, but the present invention is not limited to this. The blockchain made up of the data set may not be stored in a storage unit inside the inspection device, but may be stored only in an external data storage unit such as a blockchain network.

[0079] In the above embodiment, the blockchain composed of the data set is stored in each node of the blockchain network, which is a distributed ledger system, but the present invention is not limited to this. As the multiple data storage units, only the internal storage units of multiple inspection devices may be used.

[0080] Although the present invention has been described in detail, the above description is merely illustrative in all respects and does not limit the present invention. It is understood that countless variations not illustrated can be envisioned without departing from the scope of the present invention. The configurations described in the above embodiments and variations can be combined or omitted as appropriate as long as they are not mutually inconsistent. [Explanation of symbols]

[0081] 1,1A: Image inspection system 2, 2A, 2B, 2C: Inspection equipment 3,3A:Large capacity storage 8A: Management Server 9: Blockchain Network 21, 21A: Computer 40: 1st memory section 42: Inspection Department 43, 43A: Hash value generation unit 44, 44A: Dataset generation section 45: Transmitter 45A: First transmitter 46: Readout section 46A: First readout unit 50A: 2nd memory section 51A: Second transmitter 52A: Second readout unit 91: Node Db: Blockchain Dh, Dh': hash value Dp, Dp*: Captured image Dr, Dr', Dr*: Examination history Ds, Ds', Ds*: Data set N: Internet

Claims

1. An image inspection system capable of communicating with a blockchain that inspects an object to be inspected using a photographed image of the object to be inspected, an inspection unit that inspects the captured image and outputs an inspection history; a hash value generation unit that generates the previous hash value based on the previous inspection history and the hash value before the previous one; an image storage unit that stores the inspected photographed image; a plurality of data storage units that store a data set that combines the inspection history and the hash value; a transmission unit that transmits the latest data set, which is a combination of the latest inspection history and the previous hash value, to each data storage unit every time inspection by the inspection unit is completed; a read unit capable of reading the past data set from the data storage unit; An image inspection system comprising:

2. 10. The image inspection system of claim 1, an inspection device having the inspection unit; an image storage device constituting the image storage unit; Multiple nodes of the blockchain; and The inspection device, the image storage device, and each of the nodes of the blockchain are communicatively connected via the Internet, An image inspection system, wherein each of the nodes of the blockchain functions as one of the data stores.

3. 10. The image inspection system of claim 1, a plurality of inspection devices each having the inspection unit, the hash value generation unit, the transmission unit, and the reading unit; an image storage device constituting the image storage unit; and the plurality of inspection devices and the image storage device are communicably connected via the Internet; An image inspection system, wherein each of the inspection devices comprises one of the data storage units.

4. 4. The image inspection system according to claim 1, The inspection history includes at least Inspection conditions in the inspection unit; Used image information, which is information about the captured image that was used; 1. An imaging inspection system, comprising:

5. 5. The image inspection system of claim 4, An image inspection system, wherein the used image information includes a hash value of the captured image used.

6. An image inspection method for inspecting an object to be inspected using a photographed image of the object to be inspected, a) an image acquisition step of photographing the inspection object and acquiring the photographed image; b) an inspection step of inspecting the photographed image obtained in the step a) by image processing; c) generating the previous hash value from the inspection history in the previous step b) and the hash value before the previous one; d) a data storage step of storing a data set combining the current inspection history in step b) and the previous hash value in a plurality of data storage units; e) an image storage step of storing the photographed image obtained in step a) in an image storage unit; An imaging examination method in which the above steps are repeated.

7. The image inspection method according to claim 6, After repeating the steps a) to e) multiple times, f) a first reading step of reading out a specific photographed image, which is the photographed image of the inspection object to be re-inspected, from the image storage unit; g) a second reading step of reading the data set corresponding to the specific photographed image from the data storage unit; h) a re-inspection step of re-inspecting the specific photographed image read out in step f) by image processing; i) a comparison step of comparing the inspection result in step h) with the contents of the inspection history included in the data set read in step g); An imaging inspection method comprising:

8. The image inspection method according to claim 7, The inspection history includes at least Inspection conditions in step b) Including, An image inspection method, wherein in step h), re-inspection is performed using the inspection conditions included in the data set read out in step g).

9. The image inspection method according to claim 7 or claim 8, An image inspection method, wherein at least some of the plurality of data storage units are nodes of a blockchain.

10. The image inspection method according to claim 7 or claim 8, An image inspection method, wherein an inspection device performing step b) is equipped with one of the data storage units.

11. The image inspection method according to claim 7 or claim 8, The inspection history includes at least As used image information, which is information about the photographed image used, a hash value of the photographed image used An imaging inspection method comprising:

Images