JP7023338B2 - Collection management system - Google Patents

Description

This disclosure relates to a collection management system.

In order to manage the collection of books, the library carries out inventory work several times a year to check whether the books in the library are in the designated place.

Several methods are known as methods for acquiring the bibliographic data of books placed on the bookshelf at the time of inventory. For example, a method of acquiring bibliographic data by reading a barcode attached to a book is known (see Patent Document 1). Further, for example, a method of acquiring bibliographic data by reading an IC tag attached to a book is known (see Patent Document 2).

Japanese Patent No. 6460207 Japanese Unexamined Patent Publication No. 2017-62130

The work of reading the barcode or IC tag attached to the book is time-consuming. For example, when reading a barcode or IC tag manually, the inventory work may take several days. In that case, it will be necessary to close the library for several days.

In addition, in order to read the barcode or IC tag, it is necessary to attach the barcode or IC tag containing the bibliographic data to the book in advance, but the work of attaching the barcode or IC tag to the book is also troublesome. It takes.

Further, in order to be able to read bibliographic data from an IC tag, a large amount of capital investment is required to prepare an environment in which the IC tag can be read.

An object of the present disclosure made in view of this viewpoint is to provide a collection management system capable of efficiently managing collections at low cost.

The book collection management system according to the embodiment of the present disclosure performs image analysis of a management server that stores data related to books held by the library and an image of a part of the book cover of the library. The analysis server comprises an analysis server, and the analysis server divides the range of the spine cover by image analysis for each of a plurality of books included in the image, and the book is divided by the image analysis for each book divided in the range of the spine. The information of the book is extracted, the data about the book stored in a part of the range of the book rack is acquired from the management server, the information of the book extracted by image analysis, and the information of the book rack acquired from the management server. Collate with data about books in some areas.

According to the collection management system according to the embodiment of the present disclosure, it is possible to efficiently manage the collection at low cost.

It is a figure which shows the structural example of the collection management system which concerns on embodiment of this disclosure. It is a block diagram which shows the configuration example of the management server which concerns on embodiment of this disclosure. It is a block diagram which shows the configuration example of the analysis server which concerns on embodiment of this disclosure. It is a block diagram which shows the structural example of the terminal apparatus which concerns on embodiment of this disclosure. It is a sequence diagram which shows an example of the operation of the collection management system which concerns on embodiment of this disclosure. It is a figure which shows an example of the screen display at the time of selecting a shelf. It is a figure which shows an example of how the photographed image is displayed. It is a figure which shows an example of a state in which an image in which a frame line is superimposed is displayed. It is a figure which shows an example of the appearance that the list of collation results is displayed. It is a figure which shows an example of the appearance that the details about one book are displayed.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

FIG. 1 is a diagram showing a configuration example of a collection management system 1 according to an embodiment of the present disclosure. The collection management system 1 is a system for managing books held in a library. The collection management system 1 includes a management server 10 and an analysis server 20.

The management server 10 and the analysis server 20 are connected to each other so as to be able to communicate with each other via the network 40. The network 40 may be a network capable of wireless communication or a network capable of wired communication. Alternatively, the network 40 may be a network including both a network capable of wireless communication and a network capable of wired communication.

The management server 10 and the analysis server 20 are communicably connected to the terminal device 30 via the network 40.

The management server 10 may be a general-purpose computer or a dedicated computer that functions as the management server 10. The management server 10 may be installed in the library or may be installed outside the library.

The analysis server 20 may be a general-purpose computer or a dedicated computer that functions as the analysis server 20. The analysis server 20 may be installed in the library or may be installed outside the library.

The terminal device 30 is a device having a shooting function and a communication function. The terminal device 30 may be, for example, a tablet or a smartphone. The terminal device 30 is operated by an inventory worker when performing inventory work in the library.

First, an outline of the present embodiment will be described with reference to FIG.

In the collection management system 1, the management server 10 stores data related to books held by the library. The terminal device 30 photographs a part of the bookshelf of the library during the inventory work. When the management server 10 receives the image taken by the terminal device 30, the management server 10 transmits the image to the analysis server 20. The analysis server 20 performs image analysis of the image received from the management server 10. The analysis server 20 compares the information extracted by the image analysis with the data related to the books held by the library received from the management server 10 and executes the collation process.

The configuration of the management server 10 according to the present embodiment will be described with reference to FIG. The management server 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

The communication unit 11 includes one or more communication interfaces capable of communicating with an external device via wireless or wired. The communication interface may be, for example, an interface for a LAN (Local Area Network). The communication unit 11 can communicate with the analysis server 20 and the terminal device 30 via the network 40.

The storage unit 12 includes, for example, a semiconductor memory, a magnetic memory, an optical memory, or the like. The storage unit 12 may function as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 12 stores arbitrary information used for the operation of the management server 10. For example, the storage unit 12 may store a system program, an application program, or the like. A part of the storage unit 12 may be installed outside the management server 10. In that case, a part of the storage unit 12 set externally is connected to the management server 10 via an arbitrary interface.

The storage unit 12 stores data on books held by the library. Data on books held by the library includes bibliographic data, collection data and shelf data. Bibliographic data is detailed data about each book in the library's collection, including, for example, titles, authors, publishers, ISBNs (International Standard Book Numbers), and spine images. The collection data is data indicating what books the library holds. That is, the collection data is data that lists all the books held by the library. Shelf data is information that indicates which books are in the collection of a particular part of the library shelves. Here, the "specific part of the bookshelf" may be, for example, "a specific shelf of the bookshelf". In this embodiment, "shelf" means a row of shelves. In addition, "bookcase" shall mean the entire bookshelf including a plurality of shelves. In the present embodiment, the "specific range of a specific part of the bookshelf" will be described below as "a specific shelf of the bookshelf". However, this is only an example, and the "range of a specific part of the bookshelf" may be a range narrower than a shelf for one row or a range extending over a plurality of shelves.

The control unit 13 may include, for example, one or more processors. In the present embodiment, the "processor" is a general-purpose processor, a dedicated processor specialized for a specific process, or the like, but is not limited thereto. The control unit 13 controls the operation of the entire management server 10. The details of the operation of the management server 10 will be described later.

The configuration of the analysis server 20 according to the present embodiment will be described with reference to FIG. The analysis server 20 includes a communication unit 21, a storage unit 22, and a control unit 23.

The communication unit 21 includes one or more communication interfaces capable of communicating with an external device via wireless or wired. The communication interface may be, for example, an interface for a LAN. The communication unit 21 can communicate with the management server 10 and the terminal device 30 via the network 40.

The storage unit 22 includes, for example, a semiconductor memory, a magnetic memory, an optical memory, or the like. The storage unit 22 may function as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 22 stores arbitrary information used for the operation of the analysis server 20. For example, the storage unit 22 may store a system program, an application program, or the like. A part of the storage unit 22 may be installed outside the analysis server 20. In that case, a part of the storage unit 22 set externally is connected to the analysis server 20 via an arbitrary interface.

The control unit 23 may include, for example, one or more processors. The control unit 23 controls the operation of the entire analysis server 20. The details of the operation of the analysis server 20 will be described later.

The configuration of the terminal device 30 according to the present embodiment will be described with reference to FIG. The terminal device 30 includes a camera 31, a display unit 32, an input unit 33, a communication unit 34, a storage unit 35, and a control unit 36.

The camera 31 can capture a part of the bookshelf of the library. That is, the camera 31 can photograph a specific shelf of the bookshelf.

The display unit 32 is an arbitrary display. The display unit 32 may be, for example, a liquid crystal display, an organic EL (Electro-Luminescence) display, or the like.

The input unit 33 includes at least one input interface. The input interface may be, for example, a physical key, a capacitance key, a pointing device, a touch screen or a microphone integrally provided with a display, or the like.

The communication unit 34 includes one or more communication interfaces capable of communicating with an external device via wireless or wired. The communication interface is, for example, an interface compatible with mobile communication standards such as LTE (Long Term Evolution), 4G, or 5G, an interface compatible with short-range wireless communication such as Bluetooth (registered trademark), or a LAN interface. good. The communication unit 34 can communicate with the management server 10 and the analysis server 20 via the network 40.

The storage unit 35 includes, for example, a semiconductor memory, a magnetic memory, an optical memory, or the like. The storage unit 35 may function as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 35 stores arbitrary information used for the operation of the terminal device 30. For example, the storage unit 35 may store a system program, an application program, or the like. A part of the storage unit 35 may be installed outside the terminal device 30. In that case, a part of the storage unit 35 set externally is connected to the terminal device 30 via an arbitrary interface.

The control unit 36 may include, for example, one or more processors. The control unit 36 controls the operation of the entire terminal device 30. The details of the operation of the terminal device 30 will be described later.

An example of the operation of the collection management system 1 according to the present embodiment will be described with reference to the sequence diagram shown in FIG. The operation shown in FIG. 5 is an operation executed by the collection management system 1 during the inventory work of the library.

In step S101 of FIG. 5, the terminal device 30 accepts the input to the input unit 33 by the worker and designates the target range to be the target of the image analysis. Here, the scope is, for example, a specific shelf in a bookshelf in a library. The terminal device 30 may, for example, activate an application for accessing the collection management system 1 and select a shelf on the application. The application for accessing the collection management system 1 may be stored in the storage unit 35 of the terminal device 30. Alternatively, the application for accessing the collection management system 1 may be an application executed on the WEB server. In this case, the terminal device 30 executes an application for accessing the collection management system 1 on the WEB browser.

FIG. 6 shows an example in which a screen for selecting a shelf is displayed on the display unit 32 of the terminal device 30. The worker operates the shelf selection button 201 shown in FIG. 6 to select a shelf. The shelf selection button 201 may be, for example, a button on which shelves can be selected in a slider format. FIG. 6 shows how “shelf 1” is selected. When the decision button 202 displayed as "data acquisition" in FIG. 6 is pressed, the selection of "shelf 1" is confirmed.

In step S102 of FIG. 5, the terminal device 30 transmits the information of the target range specified in step S101 to the management server 10. For example, when "shelf 1" is selected in step S101, the terminal device 30 transmits "shelf 1" to the management server 10 as information in the target range.

When the control unit 13 of the management server 10 receives the information of the target range from the terminal device 30, the control unit 13 extracts the data related to the books placed in the received target range from the storage unit 12. For example, when the target range is the “shelf 1”, the control unit 13 extracts data related to the books placed on the “shelf 1” from the storage unit 12.

In step S103 of FIG. 5, the management server 10 transmits data related to books extracted from the storage unit 12 in the target range to the analysis server 20.

In step S104 of FIG. 5, the camera 31 of the terminal device 30 photographs the target range specified in step S101 by the operation by the worker. For example, when "shelf 1" is selected in step S101, the camera 31 takes a picture of "shelf 1". Here, taking a picture of "shelf 1" means taking a picture of a plurality of books placed on "shelf 1".

FIG. 7 shows an example of how an image taken by the camera 31 is displayed on the display unit 32 of the terminal device 30. When "shelf 1" is photographed as the target range, the photographed image includes images of a plurality of books placed on the shelf 1. Since the camera 31 captures the state in which the plurality of books are placed on the "shelf 1" as they are, the spine covers of the plurality of books are shown in the image.

In step S105 of FIG. 5, the terminal device 30 transmits the captured image to the management server 10. For example, when the "send" button 203 is pressed on the screen shown in FIG. 7, the terminal device 30 transmits the captured image to the management server 10.

In step S106 of FIG. 5, the management server 10 transmits the image received from the terminal device 30 to the analysis server 20.

In step S107 of FIG. 5, the analysis server 20 divides the range of the spine cover by image analysis for each of the plurality of books included in the image received from the management server 10.

The control unit 23 of the analysis server 20 performs image analysis on the image received from the management server 10 and partitions the range of the spine of a plurality of books included in the image. The analysis server 20 may perform image analysis using, for example, a learning model learned by machine learning, and partition the range of the spine of a plurality of books included in the image. The learning model for partitioning the range of the spine of a plurality of books included in the image may be stored in the storage unit 22 of the analysis server 20.

In step S108 of FIG. 5, the analysis server 20 extracts book information by image analysis for each book partitioned within the range of the spine.

The control unit 23 of the analysis server 20 analyzes the image of the range of the partitioned spine and extracts the character information described in the range of the partitioned spine. For example, the control unit 23 executes OCR (Optical Character Recognition) on the image of the range of the partitioned spine to extract the character information described in the range of the partitioned spine.

In step S109 of FIG. 5, the analysis server 20 compares the information of the book extracted in step S108 with the data related to the book placed in the target range acquired in step S103, and executes the collation process. The collation process executed by the analysis server 20 is a process including the following matching degree calculation process and determination process.

The control unit 23 of the analysis server 20 has, for example, about the character information described in the range of the spine extracted in step S108, and the characters included in the data related to the book placed in the target range acquired in step S103. Calculate the degree of matching with the information. For example, when the degree of coincidence is equal to or higher than a predetermined threshold value, the control unit 23 has the character information described in the range of the spine extracted in step S108 placed in the target range acquired in step S103. It may be determined that it "matches" the character information contained in the data related to. Further, in the control unit 23, for example, when the degree of matching is less than a predetermined threshold value, the character information described in the range of the spine cover extracted in step S108 is placed in the target range acquired in step S103. It may be determined that the text information contained in the data related to the book "does not match".

The control unit 23 executes a matching degree calculation process and a determination process for all the books for which the range of the spine can be divided in step S107.

When executing the matching degree calculation process and the determination process, the control unit 23 may execute the matching degree calculation process and the determination process using the learning model learned by machine learning. The learning model used in the matching degree calculation process and the determination process may be stored in the storage unit 22 of the analysis server 20.

When extracting the spine cover information in step S108, the control unit 23 may extract the image information of the spine cover instead of the character information or together with the character information. In this case, the control unit 23 may compare the image information of the spine cover with the image information of the spine cover of the book in the target range received in step S103, and execute the collation process. Further, the control unit 23 combines the comparison of image information and the comparison of character information for collation processing, for example, for comparing the character information of a book determined to be "mismatch" in the comparison of image information. May be executed.

When the control unit 23 extracts the image information of the spine in step S108 and executes the collation process based on the image information in step S109, the control unit 23 uses a large number of spine images to obtain a learning model learned by machine learning. You may use it to execute the matching degree calculation process and the determination process. The learning model learned by machine learning using a large number of spine images may be stored in the storage unit 22 of the analysis server 20.

In step S110 of FIG. 5, the analysis server 20 transmits the result of the collation process executed in step S109 (hereinafter, may be simply referred to as “collation result”) to the management server 10. The collation results include information about all the books that could demarcate the range of the spine.

The collation result may include, for example, the following information.
-Bibliographic data of books judged to be "matching" or "mismatching" -Character information recognized by OCR-Matching degree-Matching degree judgment result-Coordinates of the range of the spine

In step S111 of FIG. 5, the management server 10 transmits the collation result received from the analysis server 20 to the terminal device 30.

In step S112 of FIG. 5, the terminal device 30 can display the image based on the collation result received from the management server 10 on the display unit 32.

8 to 10 show an example of how the terminal device 30 displays an image based on the collation result received in step S111 on the display unit 32. The data for displaying an image as shown in FIGS. 8 to 10 may be generated by the analysis server 20 before step S110 and included in the collation result, or the management server 10 may generate the data in step S111. It may be generated before and included in the collation result.

FIG. 8 shows how a frame is superimposed and displayed on the captured image. In the image shown in FIG. 8, the book in which the range of the spine is divided by the analysis server 20 in step S107 is surrounded by the solid border 204 or the broken line border 205 in the image shown in FIG. That is, the book in which the range of the spine is surrounded by the solid line 204 or the broken line 205 is the book whose spine is recognized by the analysis server 20 in step S107.

In the example shown in FIG. 8, the spine of the book determined to be “matching” in the collation process in step S109 is surrounded by the solid border line 204. The spine of the book determined to be "mismatched" by the collation process in step S109 is surrounded by the broken line frame line 205.

In FIG. 8, it is an example that the range of the spine is surrounded by the solid line 204 and the broken line 205. As for the frame line 204 and the frame line 205, it is sufficient that the book determined to be "matching" and the book determined to be "mismatching" can be distinguished as a result of the collation process in step S109. For example, the spine of a book determined to be "matching" may be surrounded by a solid blue border, and the spine of a book determined to be "mismatching" may be surrounded by a solid red border. ..

In FIG. 8, a book not surrounded by either the solid line 204 or the broken line 205 indicates that the book could not be divided into the range of the spine in the process of step S107. For example, if the image taken by the terminal device 30 is unclear due to reasons such as being out of focus, the image may include a book in which the analysis server 20 cannot partition the range of the spine.

The terminal device 30 can display a list of collation results on the display unit 32. FIG. 9 shows an example of how the terminal device 30 displays a list of collation results on the display unit 32. For example, when the button 206 of the "result list" is pressed on the screen shown in FIG. 8, the terminal device 30 displays the screen of the result list as shown in FIG.

The terminal device 30 displays a list of collation results as a list, for example, as shown in FIG. The list of collation results may include "judgment", "this ID" and "title" as items, for example, as shown in FIG. “Determination” indicates the determination result of the collation process in step S109. The "this ID" and the "title" are a part of the bibliographic data included in the collation result.

The terminal device 30 may display the image shown in FIG. 8 when the button 207 of the "image analysis result" is pressed on the screen showing the list of collation results as shown in FIG.

The terminal device 30 may display the detailed information about the selected book among the books included in the collation result on the display unit 32. FIG. 10 shows an example of how the terminal device 30 displays the detailed information of the recognized book on the display unit 32. For example, in the screen shown in FIG. 8, when either the book surrounded by the solid line 204 or the broken line 205 is selected, the terminal device 30 is as shown in FIG. 10 for the selected book. Display detailed information. Alternatively, for example, on the screen shown in FIG. 9, when one book is selected from the list of collation results, the terminal device 30 displays detailed information as shown in FIG. 10 for the selected book. do.

When displaying the detailed information as shown in FIG. 10 on the display unit 32, the terminal device 30 is, for example, which of the entire image 208 taken by the terminal device 30 and the book included in the entire image 208. Displays a mark 209 indicating whether is selected, an enlarged image 210 of the spine of the selected book, and information 211 about the selected book. The information 211 may include, for example, "title", "author", "OCR", "matching degree", "determination result", and the like as items. "Title" and "Author" are part of the bibliographic data of the selected book. “OCR” is a character string recognized by OCR in step S108. The “matching degree” is the matching degree calculated in step S109. The “determination result” is the determination result of the degree of agreement in step S109.

The terminal device 30 may display the image shown in FIG. 8 when the button 212 of the “image analysis result” is pressed on the screen as shown in FIG. The terminal device 30 may display the image shown in FIG. 9 when the button 213 of the "result list" is pressed on the screen shown in FIG.

In step S113 of FIG. 5, the management server 10 creates a collation result list based on the collation result received from the analysis server 20. The management server 10 may execute the process of step S113 in parallel with the process of step S111.

When the control unit 13 of the management server 10 receives the collation result from the analysis server 20, the control unit 13 compares the data related to the books stored in the storage unit 12 with respect to the collation result, and obtains a collation result list. create.

The collation result list includes the following lists: -Discovery list-Undiscovered list-Out-of-range list-Unknown list Here, the "discovery list" is found among the books that should be in the target range specified in step S101. A list of books. The “undiscovered list” is a list of books that should not be found in the target range specified in step S101. The "out-of-range list" is a book owned by the library among the books whose spine range is divided in step S107, but should be placed in a place other than the target range specified in step S101. A list of books. The "unknown list" is a list of books whose spine is divided in step S107 and which is not registered as a book held in the library.

In step S114 of FIG. 5, the management server 10 stores the collation result list in the storage unit 12.

The collection management system 1 can execute the inventory work by repeating the processes of steps S101 to S114 for all the shelves of the bookshelf in the library.

The user of the collection management system 1 can confirm the collation result list stored in the management server 10 in step S114 via the terminal device 30. As a result of checking the collation result list, when it is determined that there may be a problem such as an out-of-focus image in the image taken for a specific target range, the user determines that the target range has a problem such as out of focus. The collation result list can be updated by performing the process of S114 again.

According to the collection management system 1 according to the present embodiment, the analysis server 20 divides the range of the spine cover by image analysis for each of a plurality of books included in the captured image in a part of the bookshelf of the library. , The information of the book is extracted by image analysis for each book divided within the range of the spine. Further, the analysis server 20 acquires data on books stored in a part of the bookshelf from the management server 10, and the information of the books extracted by image analysis and a part of the bookshelf acquired from the management server 10. Collate with data about books in the range. In this way, since the analysis server 20 collectively executes image analysis on a plurality of books included in the image, the collection management system 1 can efficiently execute the collation process. Further, since the collection management system 1 can execute the inventory work based on the image taken by the terminal device 30, it does not require expensive equipment such as equipment necessary for reading the IC tag, for example. Therefore, the collection management system 1 according to the present embodiment can efficiently manage the collection at low cost.

Further, according to the collection management system 1 according to the present embodiment, since the collection management can be performed efficiently, the period of inventory work can be shortened, and the closed days of the library due to the inventory work can be shortened. Can be done.

Further, according to the collection management system 1 according to the present embodiment, since the collection management can be performed efficiently, it requires less manpower than the collection management performed by reading a barcode or an IC tag, and inventory work is performed. It is possible to reduce the labor cost at the time.

The present disclosure is not limited to the embodiments described above. For example, the plurality of blocks described in the block diagram may be integrated, or one block may be divided. Instead of executing the plurality of steps described in the flowchart in chronological order according to the description, they may be executed in parallel or in a different order according to the processing capacity of the device that executes each step, or as necessary. Other changes are possible without departing from the spirit of this disclosure.

In the present embodiment, the management server 10 and the analysis server 20 have been described as being communicably connected via the network 40. However, the management server 10 and the analysis server 20 may be connected by a dedicated communication line. In this case, the management server 10 may be communicably connected to the terminal device 30 via the network 40, and the analysis server 20 may not be connected to the network 40.

In the present embodiment, the worker operates the terminal device 30 to take a picture of the shelf, but the terminal device 30 provided in the robot such as a drone may automatically take a picture of the shelf. With such a configuration, the terminal device 30 can automatically photograph the shelves of the entire library, for example, at night. Further, the collection management system 1 can automatically execute the collation process at night using the image taken by the terminal device 30.

In the present embodiment, the worker operates the terminal device 30 to take a picture of the shelf, but a fixed camera installed in front of the bookshelf or a camera moving in front of the bookshelf constantly takes a picture of the shelf. May be good. With such a configuration, the terminal device 30 can constantly acquire the image of the shelf and can always execute the collation process. That is, the collection management system 1 can execute the collation process of the captured image of the shelf in real time.

In the present embodiment, the analysis server 20 has been described as executing the OCR, but the OCR may be executed by an external device. In this case, the analysis server 20 transmits the image information to the external device, and receives the result of the OCR executed for the image information from the external device.

In the present embodiment, the display example in the display unit 32 shown in FIGS. 6 to 10 is merely an example. The display of the display unit 32 is not limited to the examples shown in FIGS. 6 to 10.

In the present embodiment, the analysis server 20 has been described as executing the collation process shown in step S109 of FIG. 5, but the collation process shown in step S109 may be executed by the management server 10.

The processing executed by the analysis server 20 in the present embodiment may be shared and executed by a plurality of servers. For example, the process of step S107 and step S108 shown in FIG. 5 may be executed by the first analysis server, and the process of step S109 shown in FIG. 5 may be executed by the second analysis server.

The image captured by the terminal device 30 in the present embodiment may be a moving image. In this case, the analysis server 20 may execute the processes of steps S107 to S109 shown in FIG. 5 using the still image cut out from the moving image. The process of cutting out a still image from a moving image may be executed by the terminal device 30 or may be executed by the analysis server 20.

In the present embodiment, the case where the collection management system 1 is used in a library has been described as an example, but the collection management system 1 can be used in a facility other than the library as long as it is a facility that holds books. .. The collection management system 1 can also be used in facilities that hold books other than libraries, such as bookstores and warehouses.

The information of the back cover image analyzed by the collection management system 1 in the present embodiment may be stored in the management server 10 or the analysis server 20 as information that can be used for the public service. The image information of the image of the spine that has been image-analyzed may be stored in the management server 10 or the analysis server 20 so as to be accessible from the homepage of the library, for example.

1 Collection management system 10 Management server 11 Communication unit 12 Storage unit 13 Control unit 20 Analysis server 21 Communication unit 22 Storage unit 23 Control unit 30 Terminal device 31 Camera 32 Display unit 33 Input unit 34 Communication unit 35 Storage unit 36 Control unit 40 Network

Claims (7)

A management server that stores data about books held by the library,
It is equipped with an analysis server that performs image analysis of images taken in a part of the bookshelf of the library.
The analysis server is
The range of the spine was divided by image analysis for each of the plurality of books included in the image.
For each book divided within the range of the spine, the information of the book is extracted by image analysis.
Data about books stored in a part of the bookshelf is acquired from the management server, and
The information of the book extracted by image analysis is collated with the data related to the book stored in a part of the bookshelf acquired from the management server.
A frame line surrounding the range of the spine is superimposed and displayed on the image obtained by capturing a part of the range of the bookshelf.
A collection management system in which a frame line surrounding a book determined to match the collation results and a frame line surrounding a book determined to be inconsistent are set as different forms of the frame line . In the collection management system according to claim 1,
The analysis server sends the collation result to the management server,
The management server is a collection management system that creates a collation result list based on the collation result and stores the collation result list. In the collection management system according to claim 1 or 2 ,
The analysis server is a collection management system that extracts character information on the spine as information on the book for each book partitioned within the range of the spine. In the collection management system according to any one of claims 1 to 3 ,
The analysis server is a collection management system that extracts image information of the spine as information of the book for each book partitioned within the range of the spine. In the collection management system according to claim 4 ,
When collating the extracted image information of the spine with the data related to the book, the analysis server executes the collation using a learning model learned by machine learning using a large number of spine images. Management system. In the collection management system according to any one of claims 1 to 5 ,
The image is a collection management system that is an image cut out from an image taken as a moving image. A management server that stores data about books held by the facility that holds the books, and
It is equipped with an analysis server that performs image analysis of images taken in a part of the bookshelf of the facility that holds the book.
The analysis server is
The range of the spine was divided by image analysis for each of the plurality of books included in the image.
For each book divided within the range of the spine, the information of the book is extracted by image analysis.
Data about books stored in a part of the bookshelf is acquired from the management server, and
The information of the book extracted by image analysis is collated with the data related to the book stored in a part of the bookshelf acquired from the management server.
A frame line surrounding the range of the spine is superimposed and displayed on the image obtained by capturing a part of the range of the bookshelf.
A collection management system in which a frame line surrounding a book determined to match the collation results and a frame line surrounding a book determined to be inconsistent are set as different forms of the frame line .

Images