Book name page identification method and system

Abstract

The invention discloses a book name page identification method and system, and the method comprises the following steps: shooting a book name page to obtain a name page image; regions containing key information in the name page image are removed, N candidate identification regions are selected from the remaining regions, the size of each candidate identification region is larger than or equal to the size of a marker, N is an integer larger than or equal to 2, and the marker comprises a seal or a label; respectively calculating wrinkle degree values of the N candidate identification areas, and extracting a target identification area from the N candidate identification areas according to the wrinkle degree values; and marking the marker in the target identification area. According to the identification method of the book name page, when the book name page is identified, the situation that identification is carried out in the wrinkled area can be effectively avoided, and therefore the identification quality is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of book management, and in particular to a method and system for marking a book title page. Background Art

[0002] In the related art, in order to conveniently and efficiently manage library books, editing robots are usually used to mark the title pages of books. For example, collection codes, RFID tags, and other labels that facilitate book management are printed on the title pages of books, or library collection stamps are stamped on them.

[0003] However, when managing old books, some old books may have wrinkled title pages. Therefore, when marking the title pages, stamps or labels are often placed on the wrinkled areas, which greatly affects the marking quality. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a marking method for a book title page, which can effectively avoid marking in the wrinkled area when marking the book title page, thereby greatly improving the marking quality.

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

[0006] A method for marking a book title page comprises the following steps: photographing the book title page to obtain a title page image; removing an area containing key information in the title page image, and selecting N candidate marking areas from the remaining areas, wherein the size of each candidate marking area is greater than or equal to the size of a marking object, N is an integer greater than or equal to 2, and the marking object includes a seal or a label; calculating the wrinkle degree values ​​of the N candidate marking areas respectively, and extracting a target marking area from the N candidate marking areas according to the wrinkle degree values; and marking the marking object in the target marking area.

[0007] In one embodiment of the present invention, calculating the wrinkle degree value of the candidate identification area includes the following steps: marking abnormal areas from the candidate identification area; calculating the discrete degree value of the brightness value of the overall minimum image unit in each abnormal area, and judging whether the abnormal area is a wrinkle area based on the discrete degree value; calculating the total area of ​​each wrinkle area to obtain the wrinkle area, and calculating the ratio of the wrinkle area area to the area of ​​the corresponding candidate identification area to obtain the wrinkle degree value.

[0008] In one embodiment of the present invention, marking an abnormal area from the candidate identification area includes the following steps: calculating the average brightness value of the minimum image unit of each row in the candidate identification area to obtain a first average value; calculating the average brightness value of each minimum image unit in the candidate identification area to obtain a second average value; performing a difference operation between the first average value and the second average value of each row and taking an absolute value to obtain a first absolute value; comparing the first absolute value of each row with a first threshold value, and selecting rows whose first absolute value is greater than the first threshold value from all rows of the candidate identification area as candidate abnormal areas according to the comparison result; calculating the brightness value of each minimum image unit in each candidate abnormal area, performing a difference operation between the brightness value of each minimum image unit in the candidate abnormal area and the second average value and taking an absolute value to obtain a second absolute value; comparing the second absolute value with a second threshold value, and counting the number of minimum image units whose second absolute value is greater than the second threshold value in each candidate abnormal area; selecting the candidate abnormal area whose number of minimum image units whose second absolute value is greater than the second threshold value is greater than a third threshold value from each candidate abnormal area and marking it as the abnormal area.

[0009] In one embodiment of the present invention, calculating the discrete degree value of the brightness value of the overall minimum image unit in the abnormal area includes the following steps: obtaining the brightness value of each minimum image unit in the abnormal area, and calculating the average value of the brightness value of each minimum image unit in the abnormal area to obtain a third average value; calculating the discrete degree value by the following formula:

[0010]

[0011] Where K is the discrete degree value, x i is the brightness value of the i-th minimum image unit in the abnormal area, X is the third average value, and M is the number of minimum image units in the abnormal area.

[0012] In one embodiment of the present invention, judging whether the abnormal area is a wrinkle area according to the discrete degree value includes the following steps: comparing the discrete degree value of each abnormal area with a fourth threshold value respectively; judging the abnormal area whose discrete degree value is greater than the fourth threshold value as the wrinkle area.

[0013] In one embodiment of the present invention, extracting the target identification region from the N candidate identification regions according to the wrinkle degree value includes: taking the candidate identification region with the smallest wrinkle degree value as the target identification region.

[0014] A system for marking a book title page comprises: a first acquisition module, the first acquisition module is used to photograph the book title page to obtain a title page image; a second acquisition module, the second acquisition module is used to eliminate the area containing key information in the title page image, and select N candidate marking areas from the remaining area, wherein the size of each candidate marking area is greater than or equal to the size of a marking object, N is an integer greater than or equal to 2, and the marking object includes a seal or a label; an extraction module, the extraction module is used to calculate the wrinkle degree values ​​of the N candidate marking areas respectively, and extract a target marking area from the N candidate marking areas according to the wrinkle degree values; and an identification module, the identification module is used to identify the marking object in the target marking area.

[0015] 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 method for marking a book title page is implemented.

[0016] A non-temporary computer-readable storage medium stores a computer program, which implements the above-mentioned method for marking a book title page when executed by a processor.

[0017] Beneficial effects of the present invention:

[0018] When marking a book title page, the present invention can effectively avoid marking in a wrinkled area, thereby greatly improving the marking quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart of a method for marking a book title page according to an embodiment of the present invention;

[0020] Figure 2 The figure is a block diagram of a system for marking a book title page according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] 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.

[0022] like Figure 1 As shown, the method for marking a book title page according to an embodiment of the present invention may include the following steps:

[0023] S1, photographing the title page of a book to obtain a title page image.

[0024] Herein, a photographing device (eg, a camera, etc.) may be used to photograph the title page of the book to obtain an image of the title page.

[0025] S2, removing the region containing key information in the title page image, and selecting N candidate identification regions from the remaining region, wherein the size of each candidate identification region is greater than or equal to the size of the identification object, N is an integer greater than or equal to 2, and the identification object includes a seal or a label.

[0026] Among them, the key information may include graphic information in the title page of the book, such as the book title, publisher name, etc., to avoid the situation where the seal or label covers this information, so that readers can clearly know it. After removing the area of ​​key information in the title page image, the remaining area is divided to select N candidate identification areas, where the size of each candidate identification area is greater than or equal to the size of the marker, to ensure that the marker can be identified in the candidate identification area, where N can be calibrated according to actual conditions.

[0027] S3, respectively calculating the wrinkle degree values ​​of the N candidate identification regions, and extracting the target identification region from the N candidate identification regions according to the wrinkle degree values.

[0028] In one embodiment of the present invention, calculating the wrinkle degree value of the candidate identification area may include the following steps:

[0029] S310: Mark abnormal areas from candidate identification areas.

[0030] In one embodiment of the present invention, marking an abnormal area from a candidate identification area includes the following steps:

[0031] S311, calculating an average value of brightness values ​​of minimum image units in each row in the candidate identification area to obtain a first average value.

[0032] S312: Calculate the average value of the brightness values ​​of each minimum image unit in the candidate identification area to obtain a second average value.

[0033] Among them, as a possible implementation, the sum of the brightness values ​​of each minimum image unit in the candidate identification area can be calculated first, and then the sum of the brightness values ​​of each minimum image unit in the candidate identification area is divided by the number of minimum image units in the candidate identification area to obtain the second average value; as another possible implementation, the sum of the average values ​​of the minimum image units in each row can be calculated first, and then the sum of the average values ​​of the minimum image units in each row is divided by the number of rows to obtain the second average value.

[0034] S313, performing a difference operation on the first average value and the second average value of each row respectively and taking the absolute value to obtain a first absolute value.

[0035] S314 compares the first absolute value of each row with the first threshold, and selects rows whose first absolute values ​​are greater than the first threshold from all rows of the candidate identification region as candidate abnormal regions according to the comparison result.

[0036] The first threshold value may be calibrated according to actual conditions.

[0037] S315, respectively calculating the brightness value of each minimum image unit in each candidate abnormal region, and performing a difference operation between the brightness value of each minimum image unit in the candidate abnormal region and the second average value and taking the absolute value to obtain a second absolute value.

[0038] S315: Compare the second absolute value with the second threshold, and count the number of minimum image units in each candidate abnormal region whose second absolute value is greater than the second threshold.

[0039] The second threshold value can be calibrated according to actual conditions.

[0040] S316: Select from each candidate abnormal region a candidate abnormal region whose number of minimum image units whose second absolute value is greater than the second threshold and is greater than a third threshold and mark it as an abnormal region.

[0041] The third threshold value can be calibrated according to actual conditions. S320: Calculate the discrete degree value of the brightness value of the overall minimum image unit in each abnormal area, and determine whether the abnormal area is a wrinkle area according to the discrete degree value.

[0042] In one embodiment of the present invention, calculating the discrete degree value of the brightness value of the overall minimum image unit in the abnormal area may include the following steps:

[0043] S321, obtaining the brightness value of each minimum image unit in the abnormal area, and calculating the average value of the brightness value of each minimum image unit in the abnormal area to obtain a third average value.

[0044] S322, calculate the discrete degree value by the following formula:

[0045]

[0046] Among them, K is the discrete degree value, x i is the brightness value of the i-th minimum image unit in the abnormal area, X is the third average value, and M is the number of minimum image units in the abnormal area.

[0047] In one embodiment of the present invention, judging whether an abnormal region is a wrinkle region according to the discreteness value includes the following steps: comparing the discreteness value of each abnormal region with a fourth threshold value, and then judging the abnormal region whose discreteness value is greater than the fourth threshold value as a wrinkle region. The fourth threshold value can be calibrated according to actual conditions.

[0048] Thus, according to the distribution of the brightness values ​​of each minimum image unit in the candidate identification area, the wrinkle area can be accurately located. S330, calculate the total area of ​​each wrinkle area to obtain the wrinkle area area, and calculate the ratio of the wrinkle area area to the area of ​​the corresponding candidate identification area to obtain the wrinkle degree value.

[0049] Specifically, after locating the wrinkle regions in the candidate identification region, the total area of ​​each wrinkle region can be calculated to obtain the wrinkle region area, and then the ratio of the wrinkle region area to the area of ​​the corresponding candidate identification region can be calculated to obtain the wrinkle degree value. Further, after obtaining the wrinkle degree value, the wrinkle degree values ​​corresponding to each candidate identification region can be compared, and the candidate identification region with the smallest wrinkle degree value can be selected as the target identification region.

[0050] S4, marking the marker in the target marking area.

[0051] Therefore, when marking the title page of a book, the area with a larger wrinkle degree value is first accurately located from the candidate marking area, and then the marker is added in the target marking area avoiding the wrinkle area, thereby greatly improving the marking quality.

[0052] In summary, according to the marking method of the book title page of the embodiment of the present invention, the book title page is photographed to obtain the title page image, the area containing key information in the title page image is eliminated, and N candidate marking areas are selected from the remaining area, and the wrinkle degree values ​​of the N candidate marking areas are respectively calculated, and the target marking area is extracted from the N candidate marking areas according to the wrinkle degree values, and the marker is marked in the target marking area. Therefore, when marking the book title page, it is possible to effectively avoid marking in the wrinkled area, thereby greatly improving the marking quality.

[0053] Corresponding to the method for marking the title page of a book in the above-mentioned embodiment, the present invention further proposes a system for marking the title page of a book.

[0054] like Figure 2 As shown, the book title page identification system of the embodiment of the present invention may include: a first acquisition module 100 , a second acquisition module 200 , an extraction module 300 and an identification module 400 .

[0055] Among them, the first acquisition module 100 is used to photograph the title page of the book to obtain the title page image; the second acquisition module 200 is used to eliminate the area containing key information in the title page image, and select N candidate identification areas from the remaining area, wherein the size of each candidate identification area is greater than or equal to the size of the identification object, N is an integer greater than or equal to 2, and the identification object includes a seal or a label; the extraction module 300 is used to calculate the wrinkle degree values ​​of the N candidate identification areas respectively, and extract the target identification area from the N candidate identification areas according to the wrinkle degree values; the identification module 400 is used to mark the identification object in the target identification area.

[0056] In one embodiment of the present invention, the extraction module 300 calculates the wrinkle degree value of the candidate identification area, specifically including: marking the abnormal area from the candidate identification area; calculating the discrete degree value of the brightness value of the overall minimum image unit in each abnormal area, and judging whether the abnormal area is a wrinkle area according to the discrete degree value; calculating the total area of ​​each wrinkle area to obtain the wrinkle area area, and calculating the ratio of the wrinkle area area to the area of ​​the corresponding candidate identification area to obtain the wrinkle degree value.

[0057] In one embodiment of the present invention, the extraction module 300 marks the abnormal area from the candidate identification area, specifically including: calculating the average brightness value of the minimum image unit of each row in the candidate identification area to obtain a first average value; calculating the average brightness value of each minimum image unit in the candidate identification area to obtain a second average value; performing a difference operation between the first average value and the second average value of each row and taking an absolute value to obtain a first absolute value; comparing the first absolute value of each row with a first threshold value, and selecting rows with a first absolute value greater than the first threshold value from all rows of the candidate identification area as candidate abnormal areas according to the comparison result; calculating the brightness value of each minimum image unit in each candidate abnormal area, performing a difference operation between the brightness value of each minimum image unit in the candidate abnormal area and the second average value and taking an absolute value to obtain a second absolute value; comparing the second absolute value with the second threshold value, and counting the number of minimum image units in each candidate abnormal area whose second absolute value is greater than the second threshold value; selecting candidate abnormal areas whose number of minimum image units whose second absolute value is greater than the second threshold value is greater than a third threshold value from each candidate abnormal area and marking them as abnormal areas.

[0058] In one embodiment of the present invention, the extraction module 300 calculates the discrete degree value of the brightness value of the overall minimum image unit in the abnormal area, specifically including: obtaining the brightness value of each minimum image unit in the abnormal area, and calculating the average value of the brightness value of each minimum image unit in the abnormal area to obtain a third average value; calculating the discrete degree value by the following formula:

[0059]

[0060] Among them, K is the discrete degree value, x i is the brightness value of the i-th minimum image unit in the abnormal area, X is the third average value, and M is the number of minimum image units in the abnormal area.

[0061] In one embodiment of the present invention, the extraction module 300 determines whether the abnormal area is a wrinkle area according to the discrete degree value, specifically including: comparing the discrete degree value of each abnormal area with a fourth threshold value; and determining the abnormal area with a discrete degree value greater than the fourth threshold value as a wrinkle area.

[0062] In the same embodiment of the present invention, the extraction module 300 extracts the target identification region from the N candidate identification regions according to the wrinkle degree value, specifically including: taking the candidate identification region with the smallest wrinkle degree value as the target identification region.

[0063] It should be noted that for details not disclosed in the book title page marking system of the embodiment of the present invention, please refer to the details disclosed in the book title page marking method of the embodiment of the present invention, and the specific details will not be described in detail here.

[0064] According to the book title page marking system of the embodiment of the present invention, the book title page is photographed by the first acquisition module to obtain the title page image, and the area containing key information in the title page image is eliminated by the second acquisition module, and N candidate marking areas are selected from the remaining areas, and the extraction module calculates the wrinkle degree values ​​of the N candidate marking areas respectively, and extracts the target marking area from the N candidate marking areas according to the wrinkle degree values, and the marking module marks the marker in the target marking area. Therefore, when marking the book title page, it is possible to effectively avoid marking in the wrinkled area, thereby greatly improving the marking quality.

[0065] Corresponding to the above embodiment, the present invention also provides a computer device.

[0066] The computer device of the embodiment of the present invention includes 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 method for marking the title page of a book of the above embodiment is implemented.

[0067] The computer device according to the embodiment of the present invention can effectively avoid marking in the wrinkled area when marking the title page of a book, thereby greatly improving the marking quality.

[0068] Corresponding to the above embodiment, the present invention also proposes a non-transitory computer-readable storage medium.

[0069] The non-transitory computer-readable storage medium of the embodiment of the present invention stores a computer program, and when the program is executed by a processor, the above-mentioned method for marking a book title page is implemented.

[0070] The non-transitory computer-readable storage medium according to the embodiment of the present invention can effectively avoid marking in the wrinkled area when marking the title page of a book, thereby greatly improving the marking quality.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] 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 marking a book title page, characterized in that: The following steps are involved: Photographing the title page of the book to obtain a title page image; Eliminate the region containing key information in the title page image, and select N candidate identification regions from the remaining region, wherein the size of each candidate identification region is greater than or equal to the size of the identification object, N is an integer greater than or equal to 2, and the identification object includes a seal or a label; Calculating the wrinkle degree values ​​of the N candidate identification regions respectively, and extracting the target identification region from the N candidate identification regions according to the wrinkle degree values; The marker is marked in the target marking area.

2. The method for marking a book title page according to claim 1, characterized in that: Calculating the wrinkle degree value of the candidate identification area includes the following steps: Marking an abnormal area from the candidate identification area; Calculating the discrete degree value of the brightness value of the overall minimum image unit in each of the abnormal regions, and judging whether the abnormal region is a wrinkle region according to the discrete degree value; The total area of ​​each of the wrinkle regions is calculated to obtain the wrinkle region area, and the ratio of the wrinkle region area to the area of ​​the corresponding candidate identification region is calculated to obtain the wrinkle degree value.

3. The method for marking a book title page according to claim 2, characterized in that: Marking an abnormal area from the candidate identification area includes the following steps: Calculating an average value of brightness values ​​of minimum image units in each row of the candidate identification area to obtain a first average value; Calculating an average value of brightness values ​​of each minimum image unit in the candidate identification area to obtain a second average value; Perform a difference operation on the first average value and the second average value of each row respectively and take the absolute value to obtain a first absolute value; Compare the first absolute value of each row with a first threshold value, and select rows whose first absolute value is greater than the first threshold value from all rows of the candidate identification area as candidate abnormal areas according to the comparison result; Calculating the brightness value of each minimum image unit in each of the candidate abnormal regions respectively, and performing a difference operation between the brightness value of each minimum image unit in the candidate abnormal region and the second average value respectively and taking the absolute value to obtain a second absolute value; Comparing the second absolute value with a second threshold, and respectively counting the number of minimum image units in each of the candidate abnormal regions whose second absolute value is greater than the second threshold; The candidate abnormal region whose number of minimum image units whose second absolute value is greater than the second threshold is greater than a third threshold is selected from each of the candidate abnormal regions and marked as the abnormal region.

4. The method for marking a book title page according to claim 3, characterized in that: Calculating the discrete degree value of the brightness value of the overall minimum image unit in the abnormal area includes the following steps: Acquire the brightness value of each minimum image unit in the abnormal area, and calculate the average value of the brightness value of each minimum image unit in the abnormal area to obtain a third average value; The discrete degree value is calculated by the following formula: Wherein, K is the discrete degree value, x i is the brightness value of the i-th minimum image unit in the abnormal area, X is the third average value, and M is the number of minimum image units in the abnormal area.

5. The method for marking a book title page according to claim 4, characterized in that: Judging whether the abnormal area is a wrinkle area according to the discrete degree value includes the following steps: Comparing the discrete degree value of each abnormal area with a fourth threshold value respectively; The abnormal region whose discrete degree value is greater than the fourth threshold is determined as the wrinkle region.

6. The method for marking a book title page according to claim 1, characterized in that: Extracting the target identification area from the N candidate identification areas according to the wrinkle degree value includes: The candidate identification area with the smallest wrinkle degree value is used as the target identification area.

7. A book title page marking system, characterized in that: include: A first acquisition module, the first acquisition module is used to photograph the title page of the book to obtain a title page image; A second acquisition module, the second acquisition module is used to remove the area containing key information in the title page image, and select N candidate identification areas from the remaining area, wherein the size of each candidate identification area is greater than or equal to the size of the identification object, N is an integer greater than or equal to 2, and the identification object includes a seal or a label; An extraction module, the extraction module is used to calculate the wrinkle degree values ​​of the N candidate identification areas respectively, and extract the target identification area from the N candidate identification areas according to the wrinkle degree values; An identification module is used to identify the identification object in the target identification area.

8. 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 marking a book title page according to any one of claims 1-6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for marking a book title page according to any one of claims 1 to 6 is implemented.

Images