Image processing apparatus

Abstract

To improve convenience in using image data after anonymization processing, while protecting personal information.SOLUTION: An image processing apparatus comprises: an image reading unit that reads a document on which personal information is written; and a control unit that performs anonymization processing on original image data obtained through reading of the document by the image reading unit, and thereby generates image data for output in which the personal information is anonymized. When generating the image data for output, the control unit extracts text data through OCR processing on the original image data, extracts the name as the personal information from the text data, recognizes an area of the original image data including the name as a target area, and performs, as anonymization processing, processing of making unrecognizable characters other than the initial character of a character strings forming the name in the target area.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to an image processing device. [Background technology]

[0002] Conventionally, there has been known an image processing device that reads a document containing personal information and performs anonymization processing (in other words, confidentiality processing) on ​​the personal information area of ​​the image data obtained by reading the document. Such an image processing device is disclosed, for example, in Patent Document 1. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-87121 Summary of the Invention [Problem to be solved by the invention]

[0004] In conventional image processing devices, anonymization processing involves blacking out character strings that make up personal information. In this process, all characters in the character string that make up personal information are blacked out. As a result, the content of the personal information becomes completely unknown after the anonymization processing. As a result, although this is effective in protecting personal information, it reduces the convenience of using image data after the anonymization processing.

[0005] The present invention has been made to solve the above-mentioned problems, and aims to provide an image processing device that is configured to anonymize personal information in image data obtained by reading a document, and that can protect personal information while improving convenience when using image data after anonymization processing. [Means for solving the problem]

[0006] To achieve the above object, an image processing device according to one aspect of the present invention includes an image reading unit that reads a document containing personal information, and a control unit that generates output image data in which the personal information has been anonymized by performing an anonymization process on original image data obtained by reading the document with the image reading unit. When generating the output image data, the control unit extracts text data by performing OCR processing on the original image data, extracts a name as personal information from the text data, recognizes an area in the original image data that includes the name as a target area, and performs an anonymization process in which characters other than the initial character of a character string that constitutes the name in the target area become unrecognizable. [Effects of the Invention]

[0007] In the present invention, in a configuration in which personal information in image data obtained by scanning a document is anonymized, it is possible to protect the personal information while improving the convenience of using the image data after the anonymization process. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram of a multifunction peripheral according to an embodiment. [Figure 2] FIG. 1 is a block diagram of a multifunction peripheral according to an embodiment. [Figure 3] 1 is a diagram schematically illustrating an example of a document (personal information) that can be read by the multifunction peripheral of an embodiment. [Figure 4] 10 is a flowchart illustrating a flow of an anonymization job executed by the multifunction peripheral of the embodiment. [Figure 5] FIG. 10 is a diagram for explaining a first process as an anonymization process executed by the multifunction peripheral of an embodiment. [Figure 6] FIG. 10 is a diagram for explaining a second process as an anonymization process executed by the multifunction peripheral of the embodiment. [Figure 7] FIG. 10 is a diagram for explaining a third process as an anonymization process executed by the multifunction peripheral of the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] <Configuration of the multifunction device> An image processing apparatus according to an embodiment of the present invention will be described below with reference to FIGS. 1 to 7, taking as an example a multifunction peripheral 100 having multiple functions such as a scanning function, a printing function, and a transmission function.

[0010] As shown in FIG. 1, the multifunction device 100 (corresponding to an "image processing device") includes a printing unit 1. The printing unit 1 constitutes the main body of the multifunction device 100. The printing unit 1 prints an image on a sheet S. The printing method of the printing unit 1 is an electrophotographic method. However, this is not limited to this. The printing method of the printing unit 1 may also be an inkjet method.

[0011] The printing unit 1 forms an image based on image data input to the multifunction device 100. The printing unit 1 also transports a sheet S along a sheet transport path. The printing unit 1 prints an image on the sheet S while it is being transported. In FIG. 1, the sheet transport path is indicated by a dashed line.

[0012] The printing unit 1 includes a paper feed roller 11. The paper feed roller 11 comes into contact with a sheet S stored in a sheet cassette CA and rotates in this state, thereby feeding the sheet S from the sheet cassette CA to a sheet transport path.

[0013] The printing unit 1 includes an image forming unit 12. The image forming unit 12 includes a photosensitive drum 12a and a transfer roller 12b. The photosensitive drum 12a carries a toner image on its peripheral surface. The transfer roller 12b is in pressure contact with the photosensitive drum 12a, forming a transfer nip between the photosensitive drum 12a and the transfer roller 12b. The transfer roller 12b rotates together with the photosensitive drum 12a. The image forming unit 12 transfers the toner image onto the sheet S while transporting the sheet S that has entered the transfer nip.

[0014] Although not shown, the image forming unit 12 further includes a charging device, an exposure device, and a developing device. The charging device charges the circumferential surface of the photosensitive drum 12a. The exposure device forms an electrostatic latent image on the circumferential surface of the photosensitive drum 12a. The developing device develops the electrostatic latent image on the circumferential surface of the photosensitive drum 12a into a toner image.

[0015] The printing unit 1 includes a fixing unit 13. The fixing unit 13 includes a heating roller 13a and a pressure roller 13b. The heating roller 13a has a built-in heater (not shown). The pressure roller 13b is pressed against the heating roller 13a, forming a fixing nip between the heating roller 13a and the pressure roller 13b. The pressure roller 13b rotates together with the heating roller 13a. The fixing unit 13 fixes the toner image transferred onto the sheet S onto the sheet S while transporting the sheet S that has entered the fixing nip. The sheet S that has exited the fixing nip is discharged onto an ejection tray ET.

[0016] The multifunction device 100 also includes an image reading unit 2. The image reading unit 2 is disposed on top of the main body of the multifunction device 100. In a job involving reading an original D, the original D is set in the image reading unit 2. The image reading unit 2 reads the original D set in the image reading unit 2 and generates image data of the read original D.

[0017] The image reading unit 2 includes contact glasses G1 and G2. The contact glasses G1 and G2 are installed in a housing RH of the image reading unit 2. The housing RH has an opening on the top surface. The contact glasses G1 and G2 are attached to the opening on the top surface of the housing RH.

[0018] The image reading unit 2 includes a document transport device DP. The document transport device DP is attached to the housing RH. When viewed from the front of the multifunction device 100, the document transport device DP pivots around its rear portion as if swinging its front portion up and down. The document transport device DP opens and closes relative to the top surface of the housing RH.

[0019] The document transport device DP has a set tray ST on which a document D is set. The document transport device DP transports the document D set on the set tray ST onto the contact glass G1.

[0020] In the conveying reading mode, the user sets the document D on the set tray ST. Then, the document D is automatically conveyed onto the contact glass G1 by the document conveying device DP (in other words, the document D passing over the contact glass G1) and is read. On the other hand, in the placed reading mode, the user sets the document D on the contact glass G2, and the document D on the contact glass G2 is read.

[0021] The image reading unit 2 includes a light source 21, an image sensor 22, a mirror 23, and a lens 24. The light source 21, the image sensor 22, the mirror 23, and the lens 24 are installed inside the housing RH. The image reading unit 2 performs a scanning operation in which light is irradiated from the light source 21 toward the contact glass G1 or G2 and photoelectrically converted by the image sensor 22.

[0022] The light source 21 has a plurality of LED elements. The plurality of LED elements are arranged in a line in the main scanning direction (a direction perpendicular to the paper surface of FIG. 1). The image sensor 22 has a plurality of photoelectric conversion elements arranged in the main scanning direction. The mirror 23 reflects light toward the lens 24. The lens 24 collects the light reflected by the mirror 23 and guides it to the image sensor 22.

[0023] The light source 21 and the mirror 23 are mounted on a carriage 25 that is movable in a sub-scanning direction (left and right direction in FIG. 1) that is perpendicular to the main scanning direction. As the carriage 25 moves in the sub-scanning direction, the reading line of the image reading unit 2 moves in the sub-scanning direction.

[0024] As shown in FIG. 2, the multifunction device 100 also includes an operation display unit 3. The operation display unit 3 is an operation panel having a touch screen. The operation display unit 3 displays software buttons, messages, and the like on the touch screen. The operation display unit 3 is also provided with a plurality of hardware buttons. The operation display unit 3 accepts operations from the user. The user can configure the multifunction device 100 via the operation display unit 3 regarding various jobs, such as an anonymization job, which will be described later.

[0025] The multifunction peripheral 100 includes a control unit 10. The control unit 10 includes a CPU, an ASIC, a memory, and the like. The control unit 10 also includes an image processing circuit. The control unit 10 performs various image processing operations on image data. The control unit 10 also controls the printing of an image onto a sheet S by the printing unit 1, and the reading of an original D by the image reading unit 2.

[0026] The control unit 10 also controls the operation and display unit 3. Specifically, the control unit 10 controls the display operation of the touch screen. The control unit 10 detects operations on software buttons and hardware buttons. The control unit 10 sets jobs based on operations received by the operation and display unit 3 from the user.

[0027] The multifunction peripheral 100 includes a storage unit 101. The storage unit 101 is a non-volatile storage device. An HDD, an SSD, or the like may be used as the storage unit 101. The storage unit 101 is connected to the control unit 10. The control unit 10 writes information to the storage unit 101 and reads information from the storage unit 101.

[0028] The storage unit 101 stores a character recognition program in advance. The control unit 10 performs character recognition processing such as OCR (Optical Character Recognition) processing based on the character recognition program. The control unit 10 subjects the image data obtained by the image reading unit 2 reading the document D to the character recognition processing.

[0029] The multifunction peripheral 100 includes a communication unit 102. The communication unit 102 is an interface for communicatively connecting an external device to the multifunction peripheral 100. The communication unit 102 includes a communication circuit, a communication memory, a communication connector, and the like. The communication unit 102 is connected to the control unit 10. The control unit 10 uses the communication unit 102 to send and receive data to and from the external device.

[0030] The communication unit 102 is communicably connected to an external device via a network NT such as a LAN or the Internet. Although not shown, the communication unit 102 may be directly connected to an external device via a communication cable. An external device connected to the communication unit 102 is, for example, a personal computer 1000 (hereinafter referred to as PC 1000) used by a user of the multifunction peripheral 100. An external device other than the PC 1000 may be communicably connected to the multifunction peripheral 100. By connecting the PC 1000 to the multifunction peripheral 100, image data of the original D obtained by reading the original D with the image reading unit 2 can be transmitted to the PC 1000. This allows the image data of the original D to be saved in the PC 1000.

[0031] <Anonymization process overview> The multifunction peripheral 100 has an anonymization function. In other words, the multifunction peripheral 100 is capable of executing a job related to the anonymization function (hereinafter referred to as an anonymization job). In the anonymization job, a document D containing personal information is read, and an anonymization process is performed on the original image data obtained by reading the document D to anonymize the personal information. As a result, image data for output is generated in which at least a portion of the personal information has been anonymized. The image data for output is image data generated from the original image data, and is image data in which a portion of the original image data has been altered.

[0032] By using the anonymization function, it is possible to obtain image data (i.e., output image data) in which at least part of the personal information of the document D has been anonymized. Then, an image based on the output image data can be printed on a sheet S. In addition, the output image data can be sent to the PC 1000 and saved in the PC 1000.

[0033] The document D containing personal information may be a driver's license, an insurance card, a passport, a medical record (chart), etc. The personal information may be a name, an address, a telephone number, a credit card number, an email address, etc. In the following explanation, the document D containing personal information will be simply referred to as the document D.

[0034] An example of manuscript D is shown in Figure 3. Personal information (item value) and the type of personal information (item name) are written in pairs in manuscript D. For convenience, Figure 3 illustrates each piece of personal information related to name (including furigana) and address.

[0035] When executing an anonymization job, the user sets the document D on the image reading unit 2. In this state, the user performs a start operation for the anonymization job on the operation display unit 3. When the start operation is performed on the operation display unit 3, the control unit 10 starts the anonymization job.

[0036] The flow of an anonymization job will be described below with reference to the flowchart shown in Fig. 4. The flow shown in Fig. 4 starts when a start operation for an anonymization job is performed on the operation display unit 3.

[0037] In step #1, the control unit 10 causes the image reading unit 2 to read the original document D. The image reading unit 2 reads the original document D and generates image data of the read original document D. The image data generated at this time becomes the original image data. The control unit 10 acquires the original image data obtained by the image reading unit 2 reading the original document D.

[0038] In step #2, the control unit 10 performs OCR processing on the original image data and extracts text data from the original image data. As a result, the control unit 10 recognizes character strings present in the original image data. The control unit 10 also recognizes the position (i.e., coordinates) of a character area containing character strings within the original image data. If the document D shown in FIG. 3 is the target of the anonymization job, character strings A, B, and C are extracted as text data.

[0039] In step #3, the control unit 10 performs morphological analysis on the text data extracted from the original image data. That is, the control unit 10 breaks down the text data extracted from the original image data into word units. When the manuscript D shown in FIG. 3 is the target of the anonymization job, the character string A is broken down into character strings A0, A1, and A2 as words. The character string B is broken down into character strings B0, B1, and B2 as words. The character string C is broken down into character strings C0 and C1 as words. Furthermore, the control unit 10 performs morphological analysis on the text data extracted from the original image data to determine the part of speech of each word in the text data (i.e., the broken down character strings).

[0040] In step #4, the control unit 10 performs a personal information extraction process. Specifically, the control unit 10 recognizes whether each word in the text data extracted from the original image data is personal information, and extracts the personal information from the text data. In other words, the control unit 10 extracts named entities from the text data.

[0041] The personal information extraction process uses a machine learning model for extracting named entities. The machine learning model for the personal information extraction process is a trained named entity extraction model, and is stored in advance in the storage unit 101. The control unit 10 uses the machine learning model to extract character strings that are presumed to be personal information. By performing the personal information extraction process, the control unit 10 extracts names (first and last names) as personal information from text data corresponding to the original image data.

[0042] 3 is the target of an anonymization job, the character strings A1, A2, B1, B2, and C1 are named entities, so they are extracted as personal information. Furthermore, the character strings A1 and B1 are determined to be the surname, and the character strings A2 and B2 are determined to be the given name.

[0043] In step #5, the control unit 10 recognizes the initials of the name as personal information. If the surname and given name are separated from each other by a space, the control unit 10 recognizes the initials of each of the surname and given name. That is, the control unit 10 identifies separators present in the character strings that make up the name, and recognizes the first character of each of the multiple character strings separated by the separators as the initial.

[0044] 3 is the target of an anonymization job, the first character of the character string A1 and the first character of the character string A2 are each recognized as the initial of the name. Also, the first character of the character string B1 and the first character of the character string B2 are each recognized as the initial of the name.

[0045] In step #6, the control unit 10 performs an anonymization process on the original image data. As a result, the control unit 10 generates output image data in which personal information (specifically, name) has been anonymized. The anonymization process is a process of anonymizing personal information within a target area.

[0046] When generating the output image data, the control unit 10 recognizes an area in the original image data that includes a name as personal information as a target area. That is, the control unit 10 recognizes an area in the original image data that includes a name to be anonymized as a target area.

[0047] After recognizing the target area in the original image data, the control unit 10 anonymizes the name as personal information in the target area. Specifically, the control unit 10 performs an anonymization process in which characters other than the initial letter of the character string constituting the name in the target area are made unrecognizable. Details will be described later.

[0048] In step #7, the control unit 10 causes the output unit to perform output processing of the image data for output. For example, in the settings of an anonymization job, the output method of the image data for output can be selected. The output methods include printing and transmission.

[0049] When printing is selected as the output method, the control unit 10 causes the printing unit 1 to print (in other words, output) an image based on the image data for output onto a sheet S. In this case, the printing unit 1 corresponds to the "output unit," and the output destination is the sheet S.

[0050] When transmission is selected as the output method, the control unit 10 causes the communication unit 102 to transmit (in other words, output) the image data for output to the PC 1000. The image data for output may be converted into PDF data and transmitted to the PC 1000. By transmitting the image data for output to the PC 1000, the image data for output can be saved in the PC 1000. In this case, the communication unit 102 corresponds to the "output unit," and the output destination is the PC 1000.

[0051] <Anonymization of personal information> The anonymization process for names as personal information includes a first process, a second process, and a third process.

[0052] For example, the control unit 10 recognizes the structure of the character string in the target area. Specifically, the control unit 10 recognizes whether the character string in the target area is a Japanese character string or an alphabetic character string (i.e., an English character string). Furthermore, if the character string in the target area is a Japanese character string, the control unit 10 recognizes whether the Japanese character string includes kanji with furigana. Then, the control unit 10 changes the process to be performed as the anonymization process from the first process, the second process, and the third process depending on the structure of the character string in the target area.

[0053] Alternatively, for example, the control unit 10 performs the anonymization process selected by the user from among the first process, the second process, and the third process. In this configuration, the operation display unit 3 receives an operation from the user to select one of the first process, the second process, and the third process.

[0054] 1. First process The first process will be described with reference to FIG.

[0055] When the name in the target area is composed of a Japanese character string, the control unit 10 performs, as the first process (anonymization process), a process of blacking out characters other than the initial character in the Japanese character string that constitutes the name in the target area.

[0056] In the example shown in Figure 5, the first character A11 of character string A1 is recognized as the initial character, and the first character A21 of character string A2 is recognized as the initial character. Therefore, the second character A12 of character string A1 is filled in, and the second character A22 of character string A2 is filled in. In Figure 5, the target area before anonymization (i.e., the original image data) is shown in the upper diagram, and the target area after anonymization (i.e., the image data for output) is shown in the lower diagram.

[0057] In the example shown in Figure 5, character strings A1 and A2 are separated by a space. Therefore, character A11 in character string A1 and character A21 in character string A2 are recognized as initial characters. However, if character strings A1 and A2 were not separated, only character A11 would be recognized as the initial character. In this case, character A12 in character string A1 is filled in, and further, both characters A21 and A22 in character string A2 are filled in.

[0058] Note that the target of the first process is not limited to Japanese character strings consisting of only kanji. Although not shown, the first process may be performed on Japanese character strings consisting of only hiragana, or the anonymization process may be performed on Japanese character strings consisting of only katakana. Furthermore, the first process may be performed on Japanese character strings that contain a mixture of two or more types of hiragana, katakana, and kanji.

[0059] 2. Second processing The second process will be described with reference to FIG.

[0060] When a name in the target area is composed of a Japanese character string including kanji, the control unit 10 determines whether the kanji has furigana attached. When the kanji has furigana attached, the control unit 10 recognizes an alphabetic character string obtained by converting the Japanese character string that makes up the name in the target area into roman characters based on the furigana.

[0061] For example, a romanization conversion table for converting Japanese (specifically, hiragana and katakana) into romanization is stored in advance in storage unit 101. Control unit 10 converts the Japanese character string that constitutes the name in the target area into romanization based on the romanization conversion table. That is, control unit 10 converts the Japanese character string that constitutes the name in the target area into an alphabetic character string based on the romanization conversion table. Then, control unit 10 performs a second process (anonymization process) in which the Japanese character string that constitutes the name in the target area is replaced with a character string consisting of the initials of the alphabetic character string.

[0062] In the example shown in Figure 6, character strings A1 and A2 correspond to a name, and the name is written in kanji. Also, character string B1 corresponds to the furigana added to character string A1, and character string B2 corresponds to the furigana added to character string A2. That is, in the example shown in Figure 6, the name in the target area is composed of kanji with furigana.

[0063] 6, when the Japanese character string that constitutes the name is converted into Roman characters, it becomes "YAMADA TARO," and therefore a character string "YT" consisting of the initials of that character string is generated. As a result, the Japanese character string that constitutes the name is replaced with the character string "YT." For example, in the second process, a period may be added as an ellipsis to each character of the replaced character string.

[0064] In the second process, the character strings that make up the furigana (character strings B1 and B2 in the example shown in FIG. 6) are made unrecognizable. The character strings that make up the furigana may be filled in as shown in the lower diagram of FIG. 6. Furthermore, the character strings that make up the furigana may be erased, although this is not shown.

[0065] 3.Third Processing The third process will be described with reference to FIG.

[0066] When the name in the target area is composed of an alphabetic string, the control unit 10 performs a third process (anonymization process) in which the alphabetic string constituting the name in the target area is replaced with a string consisting of the initial letters of the alphabetic string.

[0067] 7, the first character A101 of the character string A100 is recognized as an initial character, and the first character A201 of the character string A200 is recognized as an initial character. Therefore, a character string "JS" consisting of the characters A101 and A201 is generated. Then, the alphabetic character string that makes up the name is replaced with the character string "JS." For example, in the third process, a period may be added as an ellipsis to each character of the replaced character string.

[0068] In this embodiment, the anonymization process is a process that makes unrecognizable all characters other than the initials of the character string that constitutes the name (i.e., personal information) in the original image data obtained by scanning the document D. In this configuration, the initials of the name are recognizable, so it is easy for those involved to know to whom the output image data (i.e., image data after the anonymization process) corresponds. On the other hand, even if the output image data is obtained by a third party, it is possible to prevent the third party from identifying the contents of the personal information. This makes it possible to reliably protect personal information from third parties while improving the convenience of using the output image data.

[0069] Furthermore, in this embodiment, by performing the first process, when the name as personal information is composed of Japanese characters, it is possible to easily and reliably protect the personal information from third parties while improving convenience when using image data for output.

[0070] Furthermore, in this embodiment, by performing the second process, when a name as personal information is composed of a Japanese string of characters including kanji with furigana, it is possible to easily and reliably protect the personal information from third parties while improving convenience when using image data for output.

[0071] Furthermore, in this embodiment, by performing the third process, when the name as personal information is composed of an alphabetic string, it is possible to easily and reliably protect the personal information from third parties while improving the convenience of using the image data for output.

[0072] In addition, in this embodiment, the first character of each of multiple character strings separated by separators (specifically, spaces) is recognized as the initial. That is, after anonymization processing, a name as personal information is displayed as the initial of the family name and the initial of the given name. This is convenient because it makes it easier for related parties to identify the content of the personal information.

[0073] The embodiments disclosed herein are to be considered in all respects as illustrative and not restrictive. The scope of the present invention is defined by the claims, not by the description of the above embodiments, and further includes all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0074] 1 Printing section (output section) 2 Image reading unit 10 Control Unit 100 Multifunction printers (image processing devices) 102 Communication unit (output unit) 1000 PCs (external equipment) D Manuscript S seat

Claims

1. an image reading unit that reads a document containing personal information; a control unit that performs an anonymization process on the original image data obtained by reading the document by the image reading unit, thereby generating output image data in which the personal information has been anonymized; When generating the output image data, the control unit: extracting text data by OCR processing of the original image data; extracting a name as the personal information from the text data; Recognizing an area of ​​the original image data that includes the name as a target area; The image processing device performs the anonymization process by making characters other than the initial letter of the character string constituting the name in the target area unrecognizable.

2. 2. The image processing device according to claim 1, wherein when the name in the target area is composed of a Japanese character string, the control unit performs the anonymization process by blacking out characters other than the initial character in the Japanese character string that constitutes the name in the target area.

3. When the name in the target area is composed of a Japanese character string including kanji characters, the control unit determines whether or not furigana is added to the kanji characters; When the furigana is added to the kanji, the control unit recognizes an alphabet character string obtained by converting the Japanese character string constituting the name in the target area into a romaji character string based on the furigana, The image processing device according to claim 1 , wherein the control unit performs the anonymization process by replacing the Japanese character string constituting the name in the target area with a character string composed of initial letters of the alphabetic character string.

4. 2. The image processing device according to claim 1, wherein when the name in the target area is composed of an alphabetic character string, the control unit performs the anonymization process by replacing the alphabetic character string that constitutes the name in the target area with a character string that is composed of the initial letters of the alphabetic character string.

5. The image processing device according to any one of claims 1 to 4, wherein the control unit determines separators present within the character strings constituting the name and recognizes the first character of each of the multiple character strings separated by the separators as the initial character.

6. an output unit that performs output processing of the image data for output; An image processing device according to any one of claims 1 to 4, wherein the output unit is at least one of a printing unit that performs the output process by printing an image based on the output image data onto a sheet, and a communication unit that performs the output process by transmitting the output image data to an external device.

Images