Method and system for labeling book title pages

Abstract

The present invention provides a label pasting method and system for a book title page, wherein the method comprises the following steps: photographing the cover of a target book to obtain the first characteristic information of the cover; controlling a book turning device to open the target book page by page, and photographing each page to obtain a target detection image corresponding to each page; using a segmentation model to segment the target detection image into a text range, a non-text range, and a blank range; extracting text information in the text range and non-text information in the non-text range; comparing the non-text information with the first characteristic information, and comparing the text information with the corresponding title page characteristic information, and judging whether the corresponding page is a title page according to the comparison result; if yes, selecting a label range within the blank range, and controlling a label pasting device to paste the label within the label range. Thus, the book title page can be accurately detected, and the label can be accurately pasted within the blank range of the title page.

Description

Technical Field

[0001] The invention relates to the technical field of book collection and editing, and in particular to a label pasting method for a book title page and a label pasting system for a book title page. Background Art

[0002] Since the number of books in a library is usually very large, and the process of borrowing and returning books is also very cumbersome and prone to errors, in order to manage books more conveniently and efficiently, it is usually necessary to print collection codes, RFID tags or stamps on the pages or covers of books during the book collection and editing process to facilitate the management of books.

[0003] In the related art, when a label is pasted on the title page of a book, the label is often pasted on other pages because the title page cannot be accurately identified, which brings a lot of inconvenience to the book management work. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method for sticking labels on a book title page, which can accurately detect the book title page and stick the labels accurately within the blank area of ​​the title page.

[0005] The technical solution adopted by the present invention is as follows:

[0006] A label pasting method for a book title page comprises the following steps: photographing a cover of a target book to obtain first characteristic information of the cover; controlling a book turning device to open the target book page by page, and photographing each page to obtain a target detection image corresponding to each page; using a segmentation model to segment the target detection image into a text range, a non-text range and a blank range; extracting text information in the text range and non-text information in the non-text range; comparing the non-text information with the first characteristic information, and comparing the text information with corresponding title page characteristic information, and judging whether the corresponding page is a title page according to the comparison result; if yes, selecting a label range in the blank range, and controlling a label pasting device to paste a label in the label range.

[0007] In one embodiment of the present invention, a segmentation model is used to segment the target detection image into a text range, a non-text range and a blank range, including: building the segmentation model; inputting the target detection image into the segmentation model to output a range label value for each minimum image unit in the target detection image; comparing the range label value of each minimum image unit with a first set label value and a second set label value, respectively, and taking each minimum image unit corresponding to a range label value greater than or equal to the first set label value as the non-text range, and taking each minimum image unit corresponding to a range label value greater than or equal to the second set label value and less than the first set label value as the text range, and taking each minimum image unit corresponding to a range label value less than the second set label value as the blank range, wherein the first set label value is greater than the second set label value.

[0008] In one embodiment of the present invention, the expression of the partition model is:

[0009]

[0010] Among them, f n is the brightness value of the nth smallest image unit in the target detection image, f' is the standard deviation of the brightness values ​​of each smallest image unit in the target detection image, and f a is the average value of the brightness value of each minimum image unit in the target detection image, max() means taking the maximum value, and min() means taking the minimum value.

[0011] In one embodiment of the present invention, extracting text information in the text range includes the following steps: obtaining the brightness value of the smallest image unit occupied by each text in the text range, and generating a brightness matrix corresponding to each text; performing a short-time Fourier transform on the target detection image, and multiplying the transformation result with the rank of the brightness matrix corresponding to each text to obtain a feature vector value of each text; building a text reader, and inputting the feature vector value of each text into the text reader respectively to obtain the corresponding text information.

[0012] In one embodiment of the present invention, the text reader is built based on the following cost function:

[0013]

[0014] Where W is the corresponding cost function, p is the transformation result, and Y m is the sum of the eigenvalues ​​of the brightness matrix of the mth text, χ mis the feature vector value of the mth text, k1 is the penalty factor of the text reader, L1 is the Euclidean metric between the text and the reference text, and M is the number of texts.

[0015] In one embodiment of the present invention, extracting the non-text information within the non-text range includes: building a non-text reader based on the following cost function:

[0016]

[0017] Wherein, k2 is the penalty factor of the non-text reader, and L2 is the Euclidean metric between the non-text and the reference non-text; the non-text is input into the non-text reader to obtain the corresponding non-text information.

[0018] A label pasting system for a book title page comprises: a first acquisition module, the first acquisition module is used to take a photo of a cover of a target book to obtain first characteristic information of the cover; a second acquisition module, the second acquisition module is used to control a book turning device to open the target book page by page and take a photo of each page to obtain a target detection image corresponding to each page; a segmentation module, the segmentation module is used to segment the target detection image into a text range, a non-text range and a blank range using a segmentation model; an extraction module, the extraction module is used to extract text information in the text range and non-text information in the non-text range; a judgment module, the judgment module is used to compare the non-text information with the first characteristic information, compare the text information with the corresponding title page characteristic information, and judge whether the corresponding page is a title page according to the comparison result; and a control module, the control module is used to select a label range in the blank range when judging that the corresponding page is a title page, and control a label pasting device to paste a label in the label range.

[0019] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned label sticking method for a book title page is implemented.

[0020] A non-temporary computer-readable storage medium stores a computer program, which implements the above-mentioned label sticking method for a book title page when executed by a processor.

[0021] Beneficial effects of the present invention:

[0022] The invention can accurately detect the title page of a book and accurately stick the label in the blank range of the title page. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1It is a flow chart of a method for attaching a label to a book title page according to an embodiment of the present invention;

[0024] Figure 2 The figure is a block diagram of a system for attaching labels to a book title page according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Figure 1 The present invention is a flowchart of a method for attaching a label to a book title page according to an embodiment of the present invention.

[0027] like Figure 1 As shown, the label pasting method for the book title page of the embodiment of the present invention may include the following steps:

[0028] S1, taking a photo of the cover of a target book to obtain first characteristic information of the cover.

[0029] The first characteristic information may include picture information, for example, a LOGO (logotype) corresponding to the book content.

[0030] S2, controlling the book turning device to open the target book page by page, and photographing each page to obtain a target detection image corresponding to each page of the book.

[0031] S3, uses a segmentation model to segment the target detection image into text range, non-text range and blank range.

[0032] In one embodiment of the present invention, a segmentation model is used to segment a target detection image into a text range, a non-text range and a blank range, including: building a segmentation model; inputting the target detection image into the segmentation model to output a range label value for each minimum image unit in the target detection image; comparing the range label value of each minimum image unit with a first set label value and a second set label value, respectively, and taking each minimum image unit corresponding to a range label value greater than or equal to the first set label value as a non-text range, and taking each minimum image unit corresponding to a range label value greater than or equal to the second set label value and less than the first set label value as a text range, and taking each minimum image unit corresponding to a range label value less than the second set label value as a blank range, wherein the first set label value is greater than the second set label value.

[0033] Specifically, first, a partition model can be built based on the expression of the partition model, where the expression of the partition model is:

[0034]

[0035] Among them, f n is the brightness value of the nth smallest image unit in the target detection image, f' is the standard deviation of the brightness values ​​of each smallest image unit in the target detection image, and f a It is the average value of the brightness value of each minimum image unit in the target detection image. max() means taking the maximum value, and min() means taking the minimum value.

[0036] Secondly, the target detection image is input into the segmentation model to output the range label value of each minimum image unit in the target detection image. Then, the range label value of each minimum image unit is compared with the first set label value and the second set label value respectively, and divided according to the comparison result. Among them, each minimum image unit corresponding to the range label value greater than or equal to the first set label value is regarded as a non-text range, and each minimum image unit corresponding to the range label value greater than or equal to the second set label value and less than the first set label value is regarded as a text range, and each minimum image unit corresponding to the range label value less than the second set label value is regarded as a blank range. Among them, the first set label value and the second set label value can be calibrated according to actual conditions.

[0037] S4, extracting text information in the text range and non-text information in the non-text range.

[0038] In one embodiment of the present invention, extracting text information in a text range includes the following steps: first, obtaining the brightness value of the minimum image unit occupied by each text in the text range, and generating a brightness matrix corresponding to each text. Secondly, performing a short-time Fourier transform on the target detection image, and multiplying the transformation result with the rank of the brightness matrix corresponding to each text to obtain a feature vector value of each text. Finally, building a text reader, and inputting the feature vector value of each text into the text reader respectively to obtain the corresponding text information.

[0039] It should be noted that, in one embodiment of the present invention, a text reader can be built based on the following cost function:

[0040]

[0041] Among them, W is the corresponding cost function, p is the transformation result, and Y m is the sum of the eigenvalues ​​of the brightness matrix of the mth text, χ mis the feature vector value of the mth text, k1 is the penalty factor of the text reader, L1 is the Euclidean metric between the text and the reference text, and M is the number of texts.

[0042] In one embodiment of the present invention, extracting non-text information within a non-text range may include the following steps:

[0043] First, build a non-text reader based on the following cost function:

[0044]

[0045] Among them, k2 is the penalty factor of the non-text reader, and L2 is the Euclidean measure of the non-text and the reference non-text.

[0046] Then, the non-text is input into the non-text reader to obtain corresponding non-text information.

[0047] S5, comparing the non-text information with the first characteristic information, and comparing the text information with the corresponding title page characteristic information, and determining whether the corresponding page is a title page according to the comparison result.

[0048] Specifically, based on the different levels of complexity of information in the text range and the non-text range, the present invention first uses a segmentation model to segment the target detection image into a text range, a non-text range, and a blank range, and then uses different readers to read information from the text range and the non-text range, thereby ensuring accurate reading of the text information in the extracted text range and the non-text information in the non-text range. Finally, the non-text information is compared with the first feature information, and the text information is compared with the corresponding title page feature information to determine whether the corresponding page is a title page. Among them, if the non-text information matches the first feature information, and / or the text information matches the corresponding title page feature information (the name of the book, the name of the publisher, the version number, the publication time, etc.), the corresponding page is determined to be a title page. In this way, the title page of the book can be accurately detected.

[0049] S6, if yes, select a label range in the blank range, and control the label pasting device to paste the label in the label range.

[0050] Specifically, the text range and the non-text range are excluded from the target detection image as the blank range, an appropriate area range is selected from the blank range as the selected label range, and the label pasting device is controlled to paste the label within the label range.

[0051] In summary, according to the label pasting method for the title page of a book of an embodiment of the present invention, the cover of the target book is photographed to obtain the first characteristic information of the cover, and the book turning device is controlled to open the target book page by page, and each page is photographed to obtain the target detection image corresponding to each page of the book, and the target detection image is segmented into a text range, a non-text range and a blank range using a segmentation model, and the text information in the text range and the non-text information in the non-text range are extracted, and the non-text information is compared with the first characteristic information, and the text information is compared with the corresponding title page characteristic information, and it is determined whether the corresponding page is a title page according to the comparison result, if yes, the label range is selected in the blank range, and the label pasting device is controlled to paste the label in the label range. In this way, the title page of the book can be accurately detected, and the label can be accurately pasted in the blank range of the title page.

[0052] Corresponding to the label sticking method for a book title page of the above embodiment, the present invention also provides a label sticking system for a book title page.

[0053] like Figure 2 As shown, the label sticking system for the book title page according to the embodiment of the present invention may include: a first acquisition module 100, a second acquisition module 200, a segmentation module 300, an extraction module 400, a determination module 500 and a control module 600.

[0054] Among them, the first acquisition module 100 is used to take a photo of the cover of the target book to obtain the first characteristic information of the cover; the second acquisition module 200 is used to control the book turning device to open the target book page by page, and take a photo of each page to obtain the target detection image corresponding to each page of the book; the segmentation module 300 is used to use the segmentation model to segment the target detection image into a text range, a non-text range and a blank range; the extraction module 400 is used to extract the text information in the text range and the non-text information in the non-text range; the judgment module 500 is used to compare the non-text information with the first characteristic information, and compare the text information with the corresponding title page characteristic information, and judge whether the corresponding page is a title page according to the comparison result; the control module 600 is used to select a label range in the blank range when judging that the corresponding page is a title page, and control the label pasting device to paste the label in the label range.

[0055] In one embodiment of the present invention, the segmentation module 300 is specifically used to: build a segmentation model; input the target detection image into the segmentation model to output the range label value of each minimum image unit in the target detection image; compare the range label value of each minimum image unit with the first set label value and the second set label value respectively, and take each minimum image unit corresponding to the range label value greater than or equal to the first set label value as a non-text range, and take each minimum image unit corresponding to the range label value greater than or equal to the second set label value and less than the first set label value as a text range, and take each minimum image unit corresponding to the range label value less than the second set label value as a blank range, wherein the first set label value is greater than the second set label value.

[0056] In one embodiment of the present invention, the expression of the partition model is:

[0057]

[0058] Among them, f n is the brightness value of the nth smallest image unit in the target detection image, f' is the standard deviation of the brightness values ​​of each smallest image unit in the target detection image, and f a It is the average value of the brightness value of each minimum image unit in the target detection image. max() means taking the maximum value, and min() means taking the minimum value.

[0059] In one embodiment of the present invention, the extraction module 400 is specifically used to: obtain the brightness value of the smallest image unit occupied by each text within the text range, and generate a brightness matrix corresponding to each text; perform a short-time Fourier transform on the target detection image, and multiply the transformation result with the rank of the brightness matrix corresponding to each text to obtain the feature vector value of each text; build a text reader, and input the feature vector value of each text into the text reader respectively to obtain the corresponding text information.

[0060] In one embodiment of the present invention, a text reader is built based on the following cost function:

[0061]

[0062] Among them, W is the corresponding cost function, p is the transformation result, and Y m is the sum of the eigenvalues ​​of the brightness matrix of the mth text, χ m is the feature vector value of the mth text, k1 is the penalty factor of the text reader, L1 is the Euclidean metric between the text and the reference text, and M is the number of texts.

[0063] In one embodiment of the present invention, the extraction module 400 is further used to build a non-text reader based on the following cost function:

[0064]

[0065] Wherein, k2 is the penalty factor of the non-text reader, and L2 is the Euclidean metric between the non-text and the reference non-text; the non-text is input into the non-text reader to obtain the corresponding non-text information.

[0066] It should be noted that a more specific embodiment of the label sticking system for a book title page according to an embodiment of the present invention can refer to the embodiment of the label sticking method for a book title page described above, and will not be described in detail here to avoid redundancy.

[0067] According to the label pasting system for the title page of a book of an embodiment of the present invention, the cover of the target book is photographed by the first acquisition module to obtain the first characteristic information of the cover, and the book turning device is controlled by the second acquisition module to open the target book page by page, and each page is photographed to obtain the target detection image corresponding to each page of the book, and the target detection image is divided into a text range, a non-text range and a blank range by using a segmentation model by the segmentation module, and the text information in the text range and the non-text information in the non-text range are extracted by the extraction module, and the non-text information is compared with the first characteristic information by the judgment module, and the text information is compared with the corresponding title page characteristic information, and it is judged whether the corresponding page is the title page according to the comparison result, and when the corresponding page is judged to be the title page, the control module selects the label range in the blank range, and controls the label pasting device to paste the label in the label range. Thus, the title page of the book can be accurately detected, and the label can be accurately pasted in the blank range of the title page.

[0068] Corresponding to the above embodiment, the present invention also proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the above-mentioned method for sticking labels on the title page of a book is implemented.

[0069] The computer device according to the embodiment of the present invention can accurately detect the title page of the book and accurately paste the label within the blank area of ​​the title page.

[0070] Corresponding to the above embodiment, the present invention further proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned label sticking method for a book title page is implemented.

[0071] According to the non-transitory computer-readable storage medium of the embodiment of the present invention, it is possible to accurately detect the title page of a book and accurately paste the label within the blank area of ​​the title page.

[0072] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0073] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0074] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0075] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0076] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0077] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0078] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0079] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0080] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0081] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for labeling a book title page, characterized in that: The following steps are involved: Taking a photo of the cover of the target book to obtain first characteristic information of the cover; Controlling the book turning device to open the target book page by page, and photographing each page to obtain a target detection image corresponding to each page of the book; The target detection image is segmented into a text range, a non-text range and a blank range using a segmentation model; wherein the segmentation model is expressed as: Among them, f n is the brightness value of the nth smallest image unit in the target detection image, f is the standard deviation of the brightness values ​​of each smallest image unit in the target detection image, and f a is the average value of the brightness value of each minimum image unit in the target detection image, max() means taking the maximum value, and min() means taking the minimum value; Extracting text information in the text range and non-text information in the non-text range; Comparing the non-text information with the first characteristic information, and comparing the text information with the corresponding title page characteristic information, and determining whether the corresponding page is a title page according to the comparison result; If yes, a label range is selected within the blank range, and the label pasting device is controlled to paste the label within the label range.

2. The label sticking method for the title page of a book according to claim 1, characterized in that: The target detection image is segmented into a text range, a non-text range and a blank range using a segmentation model, including: Building the segmentation model; Inputting the target detection image into the segmentation model to output a range label value of each minimum image unit in the target detection image; The range label value of each minimum image unit is compared with the first set label value and the second set label value respectively, and each minimum image unit corresponding to the range label value greater than or equal to the first set label value is taken as the non-text range, and each minimum image unit corresponding to the range label value greater than or equal to the second set label value and less than the first set label value is taken as the text range, and each minimum image unit corresponding to the range label value less than the second set label value is taken as the blank range, wherein the first set label value is greater than the second set label value.

3. The label sticking method for the title page of a book according to claim 1, characterized in that: Extracting text information in the text range includes the following steps: Obtaining the brightness value of the smallest image unit occupied by each text within the text range, and generating a brightness matrix corresponding to each text; Performing a short-time Fourier transform on the target detection image, and performing a product operation on the transform result and the rank of the brightness matrix corresponding to each text to obtain a feature vector value of each text; A text reader is constructed, and the feature vector value of each text is respectively input into the text reader to obtain corresponding text information.

4. The label sticking method for the title page of a book according to claim 3, characterized in that: The text reader is built based on the following cost function: Where W is the corresponding cost function, p is the transformation result, and Y m is the sum of the eigenvalues ​​of the brightness matrix of the mth text, χ m is the feature vector value of the mth text, k1 is the penalty factor of the text reader, L1 is the Euclidean metric between the text and the reference text, and M is the number of texts.

5. The label sticking method for the title page of a book according to claim 4, characterized in that: Extracting non-text information within the non-text range includes: Build a non-text reader based on the following cost function: Wherein, k2 is the penalty factor of the non-text reader, and L2 is the Euclidean measure of the non-text and the reference non-text; The non-text is input into the non-text reader to obtain corresponding non-text information.

6. A label pasting system for a book title page, characterized in that: include: A first acquisition module, the first acquisition module is used to take a photo of the cover of the target book to obtain first characteristic information of the cover; a second acquisition module, the second acquisition module is used to control the book turning device to open the target book page by page, and to take a picture of each page to obtain a target detection image corresponding to each page; A segmentation module, the segmentation module is used to segment the target detection image into a text range, a non-text range and a blank range using a segmentation model; wherein the expression of the segmentation model is: Among them, f n is the brightness value of the nth smallest image unit in the target detection image, f is the standard deviation of the brightness values ​​of each smallest image unit in the target detection image, and f a is the average value of the brightness value of each minimum image unit in the target detection image, max() means taking the maximum value, and min() means taking the minimum value; An extraction module, the extraction module is used to extract text information in the text range and non-text information in the non-text range; A judgment module, the judgment module is used to compare the non-text information with the first characteristic information, and compare the text information with the corresponding title page characteristic information, and judge whether the corresponding page is a title page according to the comparison result; The control module is used to select a label range within the blank range when determining that the corresponding page is a title page, and control the label pasting device to paste the label within the label range.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for attaching labels to the title page of a book according to any one of claims 1 to 5 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a label sticking method for a book title page according to any one of claims 1 to 5 is implemented.

Images