Reading setting creation system

Abstract

Aspects of non-limiting embodiments of the present disclosure relate to easily creating a reading setting of an image reading apparatus without causing an increase in man-hours due to registration of a preference and an increase in man-hours and a decrease in convenience due to selection of an appropriate preference from a large number of preferences.SOLUTION: A reading setting creation system that creates a reading setting of an image reading apparatus, the reading setting creation system comprising: an information receiving unit that receives information related to a document for which a reading setting input by a user is to be set; an image acquisition unit that acquires an image related to one or a plurality of documents from an external information processing system based on the information; and an image analysis unit that analyzes the image acquired by the image acquisition unit and creates an image reading setting based on a feature of the image.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to a system for creating reading settings for an image reading device. [Background technology]

[0002] As society becomes increasingly information-based, image reading devices that store paper-based information electronically have been used for a long time. Some image reading devices are equipped with an Auto Document Feeder (ADF). Image reading devices equipped with an ADF can continuously feed and read large volumes of documents, thereby improving work efficiency.

[0003] In image reading devices equipped with an ADF, it is common to determine scanning settings such as the color mode, resolution, and image processing content of the output image in advance before scanning, and then scan all documents using those settings. This is done not only because it is inefficient to set scanning settings for each sheet of a large number of documents, but also to prevent a decrease in productivity due to scanning documents with settings that contain more information than necessary. For example, if it is predetermined that the output image will be gray, only the luminance information of the document needs to be obtained during scanning, allowing for high-speed processing. However, if gray or color output is specified later, not only luminance information but also color information of the document must be obtained during scanning so that an appropriate image can be output regardless of the specified output, which increases the amount of data and slows down processing speed.

[0004] However, to determine the appropriate scan settings, it is necessary to determine the appropriate color mode, resolution, and image processing content for each document, which can be particularly difficult for users with little experience using image scanning devices. To reduce this difficulty, it is common practice to pre-register scan settings such as color mode, resolution, and image processing content as preferences, which are combinations of appropriate settings. This eliminates the need for users to set the color mode, resolution, image processing content, etc., thereby reducing the difficulty.

[0005] However, there are challenges in preparing preferences that match the documents actually used. For example, receipts are available in various sizes and formats, and there are also various types, such as whether they are stamped or not. Preparing preferences for each of these various types of receipts would be a huge burden. Furthermore, as the number of registered preferences increases, the burden on users increases, as they have to select the appropriate one from a large number of options.

[0006] The technologies of Patent Document 1 and Patent Document 2 propose a method of supporting the creation of scan settings by first scanning (pre-scanning) the document and analyzing the scanned image. However, while these methods can reduce the burden of creating scan settings, they have the problem of significantly reducing productivity because they require the document to be scanned once in advance. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Japanese Patent Application Laid-Open No. 2002-290725 [Patent Document 2] Japanese Patent Publication No. 2023-60966 Summary of the Invention [Problem to be solved by the invention]

[0008] The present invention aims to easily create reading settings for an image reading device without increasing the amount of work required to register preferences, or increasing the amount of work required to select appropriate preferences from a large number of preferences, or reducing convenience. [Means for solving the problem]

[0009] In view of the above, the reading setting creation system of the present invention is characterized by comprising an information receiving unit that receives information regarding the document for which the reading settings entered by the user are to be set, an image acquisition unit that acquires one or more images related to the document from an external information processing system based on the information, and an image analysis unit that analyzes the images acquired by the image acquisition unit and creates image reading settings based on the characteristics of the images. [Effects of the Invention]

[0010] According to the present invention, it is possible to easily create reading settings for an image reading device without increasing the amount of work required to register preferences, or increasing the amount of work required to select appropriate preferences from a large number of preferences, and without reducing convenience. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a system configuration diagram of a reading setting creation system according to a first embodiment of the present invention. [Figure 2] 1 is a block diagram of an information processing apparatus according to a first embodiment of the present invention. [Figure 3] 5 is a flowchart showing a procedure for creating a reading setting according to the first embodiment of the present invention. [Figure 4] FIG. 2 is a diagram showing user information according to the first embodiment of the present invention. [Figure 5] 4 is a flowchart of an image selection process according to the first embodiment of the present invention. [Figure 6] FIG. 2 is a conceptual diagram of image selection processing according to the first embodiment of the present invention. [Figure 7] 4 is a flowchart of a display image extraction process according to the first embodiment of the present invention. [Figure 8] 4 is a flowchart of an unrelated image deletion process according to the first embodiment of the present invention. [Figure 9] 5 is a flowchart of a read setting creation process according to the first embodiment of the present invention. [Figure 10] 5 is a flowchart of a reading setting candidate generation process according to the first embodiment of the present invention. [Figure 11]5 is a flowchart of a paper size determination process according to the first embodiment of the present invention. [Figure 12] 4 is a flowchart of a color mode and red dropout determination process according to the first embodiment of the present invention. [Figure 13] 4 is a flowchart of a database collation process according to the first embodiment of the present invention. [Figure 14] FIG. 3 is a diagram showing read setting data stored in a database B102 according to the first embodiment of the present invention. [Figure 15] FIG. 4 is a diagram showing extracted reading setting data according to the first embodiment of the present invention. [Figure 16] 6 is a flowchart of a same-department setting extraction process according to the first embodiment of the present invention. [Figure 17] FIG. 2 is a diagram showing a screen displayed by an application according to the first embodiment of the present invention. [Figure 18] FIG. 10 is a conceptual diagram showing a method for joining character strings according to a second embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments for carrying out the present invention will be described in detail with reference to the accompanying drawings. The following embodiments are examples for carrying out the present invention, and the present invention is not limited to the following embodiments. The present invention should be appropriately modified or changed depending on the configuration of the device in which the present invention is used and various conditions, without departing from the spirit of the present invention.

[0013] [First embodiment] <System configuration> First, the system configuration according to the first embodiment of the present invention will be described. Fig. 1 shows a schematic configuration of a reading setting creation system according to the present invention. This system includes an information processing terminal A101, a database B102, and an information processing server C103.

[0014] The information processing terminal A101 is an information processing device, and is connected to an image reading device (not shown) via a network, and can read an image by setting reading settings for the image reading device and issuing an image reading instruction. In this embodiment, the information processing terminal A101 has an application that creates reading settings for the image reading device, and is a device that creates reading settings.

[0015] The database B102 stores user information and information (read setting data) relating to previously executed read settings as a database.

[0016] The information processing server C103 provides an image search service. That is, when character string information is input, the information processing server C103 searches a database or the like for image data corresponding to the character string information, and returns the searched image data to the information processing terminal A101 that made the request.

[0017] The information processing terminal A101 and the database B102 are connected via a LAN (Local Area Network). The information processing terminal A101 is also connected to the information processing server C103 via the LAN and a WAN (Wide Area Network). Note that the above system configuration is an example, and any configuration may be used as long as the information processing terminal A101 and the database B102, and the information processing terminal A101 and the information processing server C103 can communicate with each other.

[0018] <Device configuration of information processing device> Next, an information processing terminal A101, a database B102, and an information processing server C103 according to the present invention will be described. The information processing terminal A101, the database B102, and the information processing server C103 are information processing devices. Each information processing device may be any device, such as a PC or a mobile terminal device, that is capable of executing the processes described below as being performed by the information processing device.

[0019] 2 is a block diagram of an information processing device. Here, the configuration of the information processing terminal A101 will be described. The information processing terminal A101 includes a CPU 201, a storage unit 202, a communication unit 203, a display unit 204, and an operation unit 205.

[0020] A CPU (Central Processing Unit) 201 executes various processes using computer programs and data stored in a storage unit 202, thereby controlling various functions of the information processing terminal A101.

[0021] The storage unit 202 is composed of a storage device such as a hard disk, a RAM (Random Access Memory), and a ROM (Read Only Memory). The storage device stores computer programs and data such as applications in this embodiment. The RAM has an area for temporarily storing computer programs and data loaded and expanded from the storage device, and an area for temporarily storing various data received from external devices via the communication unit 203. The RAM also has a work area used by the CPU 201 when executing various processes. In this way, the RAM can provide various storage areas as needed. The ROM stores setting data, a boot program, and the like for this device.

[0022] The communication unit 203 has a communication interface for communicating information with a connected external device. In this embodiment, the communication unit 203 has a wireless LAN as a communication interface, but the communication interface is not limited to this and may be another communication interface such as a wired LAN. In this embodiment, the external devices with which the communication unit 203 of the information processing terminal A101 communicates are a database B102 and an information processing server C103.

[0023] The display unit 204 is, for example, an organic EL or liquid crystal display, and displays the user interface of the programs and applications executed by the CPU 201.

[0024] The operation unit 205 includes a keyboard and a mouse, and accepts user operations for programs and applications executed by the CPU 201 .

[0025] <Creating scanning settings> The procedure for creating a reading setting by the reading setting creation system of this embodiment will be described below with reference to FIG.

[0026] First, in step S301, when the user starts an application pre-installed in the information processing terminal A101, the application executes login processing. In the login processing, the application displays a user name input screen (not shown) and requests the user to input a user name. When the user inputs a user name, the application references user information pre-registered in database B102 and determines whether the input user name is included in the user information. If the user name input by the user is included in the user information, the application stores the input user name in a predetermined area of ​​storage unit 202 and waits for input of a user operation, which will be described later. If the input user name is not included in the user information pre-registered in database B102, the application terminates processing.

[0027] Figure 4 shows user information in this embodiment. User information includes information about the user's name and affiliation (department, section), but is not limited to this and other information may also be stored. In this embodiment, the explanation will be given assuming that Sato Jiro has been entered as the user name. In this case, since the user information shown in FIG. 4 includes Sato Jiro, the input user name is stored in a predetermined area of ​​the storage unit 202 and the process waits.

[0028] In the first embodiment, the input of a user name is requested, and the system waits for user operation depending on whether the input user name matches the user information. However, this is not limited to this. For example, the system may request the input of a password at the same time as the user name, and wait for user operation by determining whether the user name and password match.

[0029] <Image selection process> Next, in step S302, the application executes an image selection process.

[0030] The detailed procedure of the image selection process will be described below. Fig. 5 is a flowchart showing the procedure of the image selection process. Fig. 6 shows a conceptual diagram of the image selection process in this embodiment.

[0031] In step S501, the application displays a message on the display unit 204 asking the user about the characteristics of the document to be read, and the user inputs the characteristics of the document to be read using the operation unit 205. In this embodiment, the description will be given assuming that the user inputs "receipt." As a result, the application acquires information about the characteristics of the document to be read that the user input.

[0032] In step S502, the application obtains image data corresponding to the characteristics of the document from the information processing server C103. Specifically, when the application transmits character string information indicating the characteristics of the document input by the user in step S501 to the information processing server C103 via the communication unit 203, the information processing server C103, which provides an image search service, searches for images corresponding to the character string information and transmits the found images to the application. In this embodiment, the application transmits character string information "receipt" to the information processing server C103, and the information processing server C103 obtains corresponding image data from the image search service based on the character string information and transmits one to multiple pieces of image data to the information processing terminal A101. Here, the description will be given assuming that two pieces of image data have been transmitted.

[0033] Note that the description of the character string information (search keywords) is based on the assumption that the user inputs the information as words, but it is also possible to extract character string information from text using, for example, a large-scale language model and use the extracted information for searching.

[0034] In step S503, the information processing terminal A101 executes a display image extraction process to extract image data desired by the user from the image data received in step S502. The display image extraction process will be described in detail later.

[0035] In step S504, the application displays the image data extracted in S503 on the display unit 204. If no image data is obtained as a result of the extraction in S503, the application displays a message on the display unit 204 indicating that the image data cannot be obtained, and ends the process.

[0036] In step S505, the application waits for a user operation. In this embodiment, the user can perform two operations: additional input of document characteristics and selection of a display image. However, the application may be configured to perform other operations, such as restarting from S501 if the document characteristics are input incorrectly.

[0037] In step S506, the application determines whether the user has added document characteristics. If it is determined that additional input has been made, the process proceeds to step S502, where the image is acquired again. If it is determined that additional input has not been made, the process proceeds to step S507.

[0038] In this embodiment, it is assumed that the user has additionally input the character string information "seal." Therefore, the process proceeds to step S502, and an image corresponding to the input character string information is acquired from the information processing server C103. At this point, the user has already input two pieces of character string information, "receipt" and "seal," so here, an image is acquired based on these two pieces of character string information.

[0039] Any method may be used to acquire an image based on multiple pieces of character string information, but in this embodiment, an image is acquired using character string information in which multiple pieces of character string information are joined with a space between them. That is, in this embodiment, an image is acquired based on the character string information "receipt seal."

[0040] In step S503, the information processing terminal A101 executes a display image extraction process for extracting image data desired by the user from specific image data of the image received in step S502.

[0041] In step S504, the application displays (presents) the extracted image on the display unit 204, and in step S405 waits for a user operation.

[0042] In step S506, the application determines whether the user has input additional document characteristics. In this embodiment, it is assumed that the user has selected a display image without inputting additional document characteristics, and the process proceeds to step S507.

[0043] In step S507, the application determines whether the user has selected an image to display. If it is determined that an image to display has been selected, the image selection process ends, and the process proceeds to the scan setting creation process in step S303 shown in Fig. 3. If it is determined that an image to display has not been selected, the process proceeds to step S505, where the application again waits for a user operation. In this case, the user has selected a displayed (presented) image, so the image selection process ends, and the process proceeds to step S303.

[0044] <Display image extraction processing> Here, the display image extraction process performed in step S503 will be described. Fig. 7 is a flowchart showing the procedure of the display image extraction process.

[0045] The display image extraction process in this embodiment uses an image search service provided by the information processing server C103 to obtain image data corresponding to character string information entered by the user. The image search service accurately searches for image data corresponding to the entered character string, but this accuracy is not perfect and incorrect image data may be detected. The display image extraction process is a process for removing the incorrectly detected image data and extracting only the image data desired by the user.

[0046] In the display image extraction process of this embodiment, it is determined whether an image contains content corresponding to the character string information entered by the user, and only images containing content corresponding to all of the character string information are extracted (AND processing). However, this is just one example, and any process that extracts images based on the character string information entered by the user may be used. For example, it may also be possible to extract images containing content corresponding to any of the character string information entered by the user (OR processing).

[0047] In step S701, the application prepares a variable IT in a predetermined area of ​​the storage unit 202 and sets its value to 1. In this embodiment, the application processes each piece of character string information. The variable IT serves as an index indicating which piece of character string information is to be processed.

[0048] In step S702, the application determines whether the value of variable IT is greater than the number of pieces of character string information entered by the user. If it is determined that it is greater, it is assumed that extraction of all pieces of character string information has been completed, and the process ends. If it is not determined that it is greater, the process proceeds to step S703.

[0049] In step S703, the application determines whether image data remains. If no image data remains, the process ends because no more image data can be extracted. If image data remains, the process proceeds to step S704.

[0050] In step S704, an unrelated image deletion process, which will be described later, is performed to refer to the value of the variable IT and delete images that are unrelated to the character string information of that value.

[0051] In step S705, the application adds 1 to the value of the variable IT, and the process proceeds to step S702.

[0052] In this way, in the display image extraction process, the application loops this process until the value of variable IT becomes larger than the number of pieces of character string information entered by the user, and when the value of variable IT becomes larger than the number of pieces of character string information entered by the user, that is, when extraction using all pieces of character string information is complete, the application ends this process and proceeds to step S503 shown in Fig. 5. This process prevents images unrelated to the character string information entered by the user from being displayed (presented) to the user.

[0053] <Delete unrelated images> Here, we will explain the irrelevant image deletion process for removing image data erroneously detected by the image search service, which is performed in step S503 in Fig. 7. Fig. 8 is a flowchart showing the procedure of the irrelevant image deletion process.

[0054] In step S801, the application prepares variables CI and II in a predetermined area of ​​the storage unit 202, and sets the number of remaining image data to the value of CI and the value of II to 1. In this embodiment, the application processes each image data item in sequence. The variables CI and II indicate the end condition and index of the sequential processing.

[0055] In step S802, the application determines whether the value of variable II is greater than the value of variable CI. If it is determined that it is greater, it is assumed that processing for all image data has been completed, the process ends, and the process proceeds to step S705 in Figure 7. If it is not determined that it is greater, the process proceeds to step S703.

[0056] In step S803, the application determines whether the IIth image data contains the content of the ITth character string information. Any method of determination may be used, but in this embodiment, object detection technology is used to obtain information indicating the type of object contained in the image data, and it is determined whether the ITth character string information is included in the obtained type information. If it is determined that the ITth character string information is included, the process proceeds to step S805, and if it is determined that the ITth character string information is not included, the process proceeds to step S804.

[0057] The above-described method using object detection technology is merely an example, and any method that determines the relationship between text information entered by a user and an image may be used. For example, a method may convert an image into text information using image captioning technology and compare the converted text information with the text information entered by the user. Alternatively, a method may perform optical character recognition (OCR) on image data and compare the text information obtained by the OCR process with the text information entered by the user. In particular, the language of the text obtained by the OCR process may be determined and compared with the language used to display the application or the language of the text information entered by the user. In this case, images whose determined language does not match the language used to display the application or the language of the text information entered by the user may be deleted and not displayed (presented) to the user. Alternatively, priority information may be associated with the image and saved so that images whose language does not match are given a lower priority when displayed (presented) to the user during image selection.

[0058] In step S804, the application deletes the IIth image data because it was determined in step S803 that this image is not related to the ITth character string information input by the user.

[0059] In step S805, the application adds 1 to the value of variable II, and the process proceeds to step S802.

[0060] In this way, the irrelevant image deletion process loops until the value of variable II becomes greater than the value of variable CI, and when the value of variable II becomes greater than the value of variable CI, i.e., when processing for all image data is completed, the process terminates and proceeds to step S705 shown in Figure 7.

[0061] <Read setting creation process> 3, in step S302, the application performs a read setting creation process to create a read setting for the image by analyzing the image. FIG. 9 is a flowchart showing the procedure of the read setting creation process.

[0062] In step S901, the application executes a read setting candidate creation process for the image data selected in the image selection process, and creates read setting candidates.

[0063] <Scanning setting candidate creation process> Next, the read setting candidate creation process performed in step S901 will be described. FIG. 10 is a flowchart showing the procedure of the read setting candidate creation process. Note that the read settings created in the read setting candidate creation process in this embodiment are color mode, paper size, skew correction (a function to correct the skew when a document is transported), resolution, character orientation detection (a function to rotate an image so that the characters are readable), and red dropout (a function to skip red in a document). Note that this embodiment is not limited to these read settings, and other read settings may be configured to be set.

[0064] In step S1001, the application detects the area in which the document is captured from the image data using a commonly used rectangle detection process. Document area information indicating the detected area is stored in a predetermined area of ​​the storage unit 202. If the detected area is not a rectangular parallelepiped or if the area cannot be detected, the application sets information indicating indefiniteness to the document area information and stores it in a predetermined area of ​​the storage unit 202.

[0065] In step S1002, the application determines the skew correction setting. Here, the application references the document area information stored in a predetermined area of ​​the storage unit 202 in step S1001, and if the document area information indicates indefiniteness, the document is not a rectangular parallelepiped, and there is a high possibility that the skew correction process will fail. Therefore, it is determined that skew correction is OFF. On the other hand, if the information does not indicate indefiniteness, it is determined that skew correction is ON.

[0066] In step S1003, the application references the document area information stored in a predetermined area of ​​the storage unit 202, extracts the image within this area, and performs keystone correction to generate a rectangular parallelepiped image. In the following processing, processing is performed on this keystone-corrected image data. Note that if the document area information stored in the predetermined area of ​​the storage unit 202 indicates that the document area is indefinite, the entire image area is extracted and keystone correction is not performed.

[0067] In step S1004, the application performs OCR processing on the image data to detect areas containing characters, and stores information on the average height and minimum height of the characters in a predetermined area of ​​the storage unit 202. If three characters are detected and their heights are 10 pixels, 10 pixels, and 16 pixels, respectively, 12 pixels is stored as the average height information and 10 pixels is stored as the minimum height information. Note that if no characters are detected by the OCR processing, information indicating "indeterminate" is stored in a predetermined area of ​​the storage unit 202.

[0068] In step S1005, the application executes a paper size determination process to determine the paper size setting. Fig. 11 is a flowchart showing the procedure for the paper size determination process.

[0069] In step S1101, the application determines whether the aspect ratio of the image data matches the square root of 2. Because the aspect ratio of commonly used paper sizes such as A4 and A5 is the square root of 2, if the aspect ratio of the image data does not match the square root of 2, it is highly likely that the document size is not commonly used. Therefore, if it is determined that the aspect ratio does not match the square root of 2, the process proceeds to step S1102, where the paper size is determined to be automatic. If it is determined that the aspect ratio matches, the process proceeds to step S1103.

[0070] In step S1103, the application refers to the storage in a predetermined area of ​​the storage unit 202 and checks whether information that is not indefinite is stored as the average character height. This is because the average character height will be used in subsequent processing. If information indicating indefinite is stored, the paper size cannot be determined, so the process proceeds to step S1102, where the paper size is determined to be automatic. If information that is not indefinite is stored, the process proceeds to step S1104.

[0071] In step S1104, the application determines whether the image width or height is larger. If it is determined that the height is larger, it is determined that the document is oriented vertically, and the process proceeds to step S1105. On the other hand, if it is determined that the width is larger, it is determined that the document is oriented horizontally, and the process proceeds to step S1108.

[0072] In step S1105, the application determines whether the paper is A4 or A5 by comparing the image height with the average character height information stored in a predetermined area of ​​storage unit 202 in step S1004. A typical document often uses a font of about 10 points, which translates to about 4 mm when printed. Since the height of an A4 size paper is 297 mm, the ratio of image height to character height is about 74:1 for A4 paper, meaning that the image height is 74 times the character height. On the other hand, for A5 paper, this ratio is about 52:1, meaning that the image height is 52 times the character height. Therefore, in this embodiment, the A4 and A5 sizes are determined based on whether the image height is greater than 60 times the character height.

[0073] If it is determined that the image height is greater than 60 times the character height, the process proceeds to step S1106, where the paper size is determined to be A4. If it is determined that the image height is not greater than 60 times the character height, the process proceeds to step S1107, where the paper size is determined to be A5.

[0074] In step S1108, the application determines the paper size from the image height and the average character height, similar to step S1105. However, because step S1108 is a process executed when the paper is landscape, the determination threshold differs from that of S1105. Since the height of A4R (A4 landscape) is 210 mm and the height of A5R (A5 landscape) is 148 mm, in this embodiment, A4R and A5R are determined based on whether the ratio of image height to character height is 45:1, i.e., whether the image height exceeds 45 times the character height.

[0075] If it is determined that the image height is greater than 45 times the character height, the process proceeds to step S1109, where the paper size is determined to be A4R. If it is determined that the image height is not greater than 45 times the character height, the process proceeds to step S1110, where the paper size is determined to be A5R.

[0076] In step S1006, the application determines the resolution setting. In this embodiment, the resolution is determined by comparing the information on the average character height stored in a predetermined area of ​​the storage unit 202 in step S1004 with the information on the minimum character height.

[0077] A document written in about 10-point characters can generally be scanned at a resolution of about 150 dpi (Dots Per Inch) to obtain an image in which the characters are legible. However, some documents contain warnings and other information written in characters smaller than 10 points, and such documents must be scanned at a higher resolution to obtain an image in which the characters are legible. For example, if the document contains 5-point characters, about half the normal size, it must be scanned at twice the resolution, or 400 dpi.

[0078] That is, the resolution can be calculated from the ratio of the average character height to the minimum character height. In this embodiment, the resolution setting is determined by the following formula 1. Resolution setting = 200 × average character size ÷ minimum character size Formula 1

[0079] However, depending on the image reading device, the settable resolution may be limited and it may not be possible to set an arbitrary resolution. In such cases, it is preferable to set the smallest possible resolution that is equal to or greater than the value calculated by Equation 1, in order to achieve both image quality and productivity.

[0080] In addition, if information indicating indeterminate is stored in a specified area of ​​the memory unit 202 as information on the average character height and information on the minimum character height, the above calculation cannot be performed, so a predetermined value such as 300 dpi is set.

[0081] In step S1007, the application determines the character orientation detection setting. Since character orientation detection processing is preferably performed on documents containing written text, character orientation detection is determined to be ON if the image contains text. That is, the character orientation detection processing setting is determined based on whether information indicating indefiniteness is stored as average character height information and minimum character height information in a predetermined area of ​​storage unit 202. If the stored information indicates indefiniteness, it is highly likely that the document does not contain text, and character orientation detection is determined to be OFF. On the other hand, if the information does not indicate indefiniteness, character orientation detection is determined to be ON.

[0082] In step S1008, the application detects the hue of the image data. Specifically, it calculates the hue for each pixel of the image data and creates a histogram of the calculated hue. Hue is a quantity that indicates the color tone of colors such as red and green, and creating this histogram makes it easy to determine what color information is contained in the image.

[0083] It is known that hue values ​​tend to vary widely for colors with low saturation, such as white and gray. Therefore, in this embodiment, when creating a hue histogram, pixels with saturation lower than a predetermined value are excluded from the histogram calculation. This allows for more accurate hue determination.

[0084] In step S1009, the application executes a color mode / red dropout determination process, and determines the color mode setting and red dropout setting based on the hue histogram created in step S1008.

[0085] FIG. 12 is a flowchart showing the procedure for the color mode and red dropout determination process.

[0086] In step S1201, the application references the hue histogram created in step S1008 and determines whether there are two or more peaks higher than a predetermined first threshold. If there are two or more peaks higher than the first threshold, there is a high possibility that the document was printed in multiple colors, so the process proceeds to step S1202, where it is determined that the color mode setting is color and the red dropout setting is OFF. If it is determined that there is one or fewer peaks higher than the first threshold, the process proceeds to step S1203.

[0087] In step S1203, the application refers to the hue histogram and determines whether there is one peak higher than the first threshold value. If there is one peak higher than the first threshold value, the process proceeds to step S1204.

[0088] Next, the application determines whether the color detected in the histogram should be red-dropped out. Generally, users tend to want to scan a document with black and red text in color, and to scan a document with black text and red lines in black and white with red-dropped out. In this embodiment, the application determines whether the color should be red-dropped out based on the position and height of the histogram.

[0089] In step S1204, the application determines whether the position of the peak higher than the first threshold corresponds to the hue red. If the position of the peak does not correspond to the hue red, it is determined that a color scan is to be performed because the color cannot be removed by red dropout, and the process proceeds to step S1202. If the position of the peak corresponds to the hue red, the process proceeds to step S1205.

[0090] In step S1205, the application determines whether red dropout should be performed based on the height of the histogram peak. Generally, there tends to be a small amount of red text in a document, while there is a large amount of red ruled lines and the like. Therefore, a second threshold value, which is set higher than the first threshold value, is used to determine whether red dropout should be performed. That is, if the height of the peak in the histogram that is higher than the first threshold value is equal to or less than the second threshold value, the color component is likely to be due to red text, and processing proceeds to step S1202. On the other hand, if the height is higher than the second threshold value, the color component is likely to be due to red ruled lines and the like, and processing proceeds to step S1206, where the color mode setting is determined to be black and white and the red dropout setting is determined to be red.

[0091] Step S1207 is executed when it is determined in step S1203 that the number of peaks higher than the first threshold is 0. In this case, since it is unlikely that highly saturated information is printed on the document, the process proceeds to step S1207, where it is determined that the color mode setting is black and white and the red dropout setting is OFF.

[0092] Once the color mode settings and red dropout settings have been determined in this manner, this process, that is, the process relating to step S1009, ends.

[0093] Through the above procedure, the reading settings of color mode, paper size, skew correction, resolution, character orientation detection, and red dropout are determined, the process in step S901 ends, and the process proceeds to step S902.

[0094] In this embodiment, the scan settings are determined using a so-called rule-based method, which is determined based on predetermined thresholds, as described above. However, the present invention is not limited to this method, and any method that determines scan settings from an image may be used. For example, a machine learning determination may be performed using an apparatus that has previously performed machine learning on the correspondence between images and scan settings.

[0095] Next, in step S902, the application performs a database matching process to obtain the most frequently used reading settings or reading settings that have been used by a particular organization or person.

[0096] <Database matching process> 13 is a flowchart showing the procedure of the database matching process. In this embodiment, the database matching process is used to acquire the most frequently used reading settings and reading settings that have been used by a specific organization or person.

[0097] In step S1301, the application uses the character string of the document characteristics input by the user in step S501 to search the read setting data stored in the database B 102, and extracts data containing the character string of the document characteristics.

[0098] Fig. 14 shows the read setting data stored in the database B 102. In this embodiment, since the user inputs the character string "receipt" in step S501, the data shown in Fig. 15 is extracted.

[0099] In this embodiment, only the character strings of the document characteristics input in step S501 are used, but it is also possible to use character strings additionally input in step S505. In that case, data including all character strings input by the user may be extracted, or data including a predetermined percentage or more of the character strings may be extracted.

[0100] In step S1302, the application extracts the most frequently used combination of scan settings from the scan setting data extracted in step S1301. In this embodiment, the most frequently used combination is color mode, automatic paper size, deskew ON, resolution 150 dpi, character orientation detection ON, and red dropout OFF, so this setting combination is extracted.

[0101] In step S1303, the application executes same department setting extraction processing to extract settings used by users in the same department or section as the user who created the reading settings.

[0102] The reason for extracting the reading settings used by users in the same department or section is that users in the same department or section are likely to be performing the same tasks, and the settings used by these users are likely to be reusable.

[0103] FIG. 16 is a flowchart showing the procedure of the database collation process.

[0104] In step S1601, the application uses the user name entered in step S301 as a key to obtain information about the department and section from the user information stored in database B 102. In this embodiment, since the user name entered in step S301 is Sato Jiro, the information obtained is that the department is the accounting department and the section is the accounting section.

[0105] In step S1602, the application again refers to the user information stored in database B 102 and extracts the user name that has the same department and section as those acquired in step S1601. In this embodiment, the user name Yamada Taro is extracted.

[0106] In step S1603, the application references the data used by Yamada Taro from the scan setting data extracted in step S1301. As a result, in this embodiment, the following combination is extracted: color mode is black and white, paper size is automatic, skew correction is ON, resolution is 200 dpi, character orientation detection is ON, and red dropout is ON.

[0107] In step S903, the application generates sample images for the reading settings extracted in the database matching process and the reading settings created in the reading setting candidate creation process, allowing the user to visually understand the images resulting from reading using these reading settings.

[0108] The sample image may be any image that allows the user to understand the results of the scan. It may be generated based on the image data selected in the image selection process, or it may be icon data that has been embedded in the application in advance.

[0109] In step S904, the application presents to the user the read settings extracted in the database matching process and the read settings created in the read setting candidate creation process. FIG. 17 is an example of a screen displayed by the application. Here, information indicating that the settings extracted in step S1302 are the most frequently used read settings, information indicating that the settings extracted in step S1303 are read settings that have been used by the referenced user (Yamada Taro) in the same department and section, and the read settings created in the read candidate creation process are displayed. When the user selects one of the read settings, the process proceeds to step S905.

[0110] It is possible that the scan settings desired by the user may not be included in the scan settings presented. Therefore, the application screen shown in Fig. 17 also provides a button that allows the user to manually set scan settings. The operation when this button is pressed is the same as that of conventional applications, so a detailed description is omitted.

[0111] In step S905, the application combines the user name entered by the user in step S301 with the read setting selected by the user, and adds the combined data to the read setting data in database B 102. As a result, the read setting selected by the user in the above procedure will be referenced in the read setting creation process from the next time onwards, which will improve the accuracy of the read setting creation process from the next time onwards.

[0112] According to the method described in this embodiment, the user simply inputs the characteristics of the document they want to read into the application and selects the appropriate image from the images presented, and candidate reading settings are automatically presented, allowing them to select the appropriate reading settings.

[0113] By presenting particularly frequently used reading settings or reading settings used by users in the same department or division, even users who are not familiar with the functions of image reading devices can easily select reading settings.

[0114] In this embodiment, only the most frequently used read settings and read settings used by users in the same department or section are extracted from the database B102, but other read settings may also be extracted. For example, read settings used in the past by the logged-in user may be extracted.

[0115] In the read setting candidate creation process in this embodiment, only one read setting candidate is created, but the present invention is not limited to this, and multiple read settings may be created as candidates. In this case, all the created candidates may be displayed in the application, or only some of the candidates may be displayed in the application. When only some of the candidates are displayed, the read settings may be compared with the read setting data stored in the database B102, and read settings that have been used in the past may be displayed preferentially.

[0116] In this embodiment, the application displays a so-called chat-style user interface as shown in Fig. 6, but this is just one example, and any interface that allows the user to input character string information and displays candidate image data may be used. For example, it may be a so-called search box that displays results when a keyword is entered.

[0117] In this embodiment, the application presents the user with images acquired from the information processing server C103 and requests the user to select an image, but the present invention is not limited to this. The application may automatically execute a read setting creation process for images acquired from the information processing server C103 and present only candidate read settings to the user. This method has the advantage of further reducing the user's workload, although there is a concern that appropriate read settings may not be created if an inappropriate image is acquired from the information processing server C103.

[0118] Furthermore, instead of the application presenting multiple candidate scan settings and requesting the user to select one, the application may automatically select the scan setting that is determined to be the most appropriate. Any method for determining appropriateness may be used, but for example, the application may compare the results created in the scan setting candidate creation process with the scan settings extracted from the scan setting data, and determine that the scan settings are appropriate if they match highly.

[0119] [Second embodiment] The second embodiment of the present invention differs from the first embodiment in the services provided by the information processing server C103.

[0120] In this embodiment, the information processing server C103 provides an image generation service. That is, when character string information is input, the information processing server C103 generates image data according to the character string information and returns the generated image data to the request source.

[0121] In this embodiment, the information processing server C103 provides an image generation service. That is, when character string information is input, the information processing server C103 generates image data according to the character string information and returns the generated image data to the request source.

[0122] While image generation services have concerns that the generated images may differ from the actual originals, they have the advantage of being able to flexibly generate images in response to requests and therefore be able to accommodate a wider range of inputs.

[0123] The configuration of the read setting creation system and the block diagram of the information processing terminal A101 in this embodiment are the same as those in the first embodiment.

[0124] The process of creating the read settings in this embodiment differs from the first embodiment in the process of acquiring an image corresponding to the document characteristics in the image selection process described in step S502.

[0125] In the first embodiment, in step S502, the application transmits character string information indicating the characteristics of the document to be read, which the user input in step S501, to the information processing server C103, and acquires image data corresponding to this character string information. However, in the second embodiment, the application transmits not only the character string information indicating the characteristics of the document to be read, which the user input in step S501, but also the user's affiliation information in combination.

[0126] That is, the application uses the user name entered by the user in step S301 as a key to extract department and section information from database B 102. The application then embeds the extracted department and section information, along with character string information indicating the characteristics of the document to be read, in the following format: "I am an employee of [department] working in [department name removed]. Please generate an image of [manuscript characteristics]."

[0127] 18 is a conceptual diagram showing a method for combining character string information in this embodiment. In this embodiment, the department is the accounting department, the section is the accounting section, and the document characteristic is "receipt," so the following character string is generated as a result of combining: "I'm an accountant in the accounting department. I'd like to generate an image of a receipt."

[0128] The application sends this combined character string to the information processing server C103, and receives the image data generated by the information processing server C103.

[0129] The method of joining character strings and the information included in the character strings are not limited to this, and may be the same character string information as in the first embodiment, for example. [Explanation of symbols]

[0130] 101 Information processing terminal A101 102 Database B102 103 Information Processing Server C103

Claims

1. A reading setting creation system for creating reading settings for an image reading device, comprising: an information receiving unit that receives information about a document to be set with the read settings input by a user; an image acquisition unit that acquires one or more images related to the document from an external information processing system based on the information; an image analysis unit that analyzes the image acquired by the image acquisition unit and creates image reading settings based on the characteristics of the image; A reading setting creation system comprising:

2. an image presentation unit that presents to a user one or more images acquired by the image acquisition unit; an image selection unit that selects one or more images designated by a user from the images presented on the image presentation unit; Furthermore, 2. The reading setting creation system according to claim 1, wherein the image presenting unit does not present the image to the user if the image acquired by the image acquiring unit does not include the information.

3. The reading setting creation system according to claim 2 , wherein the image presentation unit determines whether to present an image to the user based on the language of a character string contained in the image acquired by the image acquisition unit.

4. a setting presentation unit that presents one or more image reading settings to a user; a setting selection unit that selects an image reading setting designated by a user from the image reading settings presented by the setting presentation unit; The reading setting creation system according to claim 2 , further comprising:

5. The reading setting creation system includes: A database that links and stores user affiliation information and reading setting data Furthermore, The information receiving unit acquires user affiliation information, The scanning setting creation system according to claim 4 , wherein the setting presentation unit presents image scanning settings used by other users who have affiliation information related to the affiliation information of the user from the database.

Images