Information digital processing method

Abstract

The invention provides an information digital processing method, and relates to the technical field of data processing, and the method comprises the following steps: S1, collecting information data, and directly recognizing and reading to obtain recognizable text data; s2, scanning non-text data to obtain initial recognition text data corresponding to a corresponding scanning position; s3, querying radical information of each character in the initial recognition text data, and checking and analyzing each piece of radical information at the scanning position to obtain matched confirmation text data; and S4, inserting the confirmation text data into the recognizable text data to obtain digital processing result data. According to the method, text digital recognition processing under the condition that the information data are of different types can be accurately achieved, whether components are accurate or not can be accurately inquired according to individuation of writing, and the accuracy of character conversion by the information is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for digitalizing information. Background Art

[0002] With the continuous development of document processing technology, document data will contain a large amount of readable text content and some other formats, such as picture text, picture tables, picture tables, formulas and tables that cannot be directly recognized in the form of pictures, formula formats, and table formats, which will make the recognition of document information data difficult and inaccurate.

[0003] Therefore, when the existing document information data is recognized and processed, it is difficult to accurately identify the text content of non-text data. Moreover, due to the personalized writing of text characters, such as running script, cursive script, etc., the recognized radicals may not be accurate enough, which will lead to a large number of text recognition errors in the recognition results. Summary of the invention

[0004] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide an information digitization processing method for solving the problem in the prior art that, when identifying and processing document information data, it is difficult to accurately identify the text content of non-text data, and due to the personalized writing of text, a large number of text recognition errors are caused.

[0005] To achieve the above-mentioned purpose and other related purposes, the present invention provides a method for digitalizing information, comprising the following steps:

[0006] S1: Collect information data and directly identify and read to obtain recognizable text data;

[0007] S2: Scan the non-text data to obtain initial recognition text data corresponding to the corresponding scanning position;

[0008] S3: querying the radical information of each character in the initial recognition text data, and performing verification and analysis on each radical information at the scanning position to obtain matching confirmation text data;

[0009] S4: inserting the confirmation text data into the recognizable text data to obtain digital processing result data.

[0010] In one embodiment of the present invention, in S1, collecting information data includes:

[0011] The information data to be read is obtained, and the information data is divided into data in which characters can be directly recognized and other data in which characters cannot be directly recognized.

[0012] In one embodiment of the present invention, in S1, directly identifying and reading to obtain recognizable text data includes:

[0013] The data capable of directly recognizing characters are read in the order of the information data to obtain the recognizable text data.

[0014] In one embodiment of the present invention, in S2, scanning non-text data includes:

[0015] When the data of the characters that cannot be directly recognized are divided, the coordinate area of ​​the corresponding position that cannot be directly recognized is obtained as the non-text data area, and the image of the non-text data area is controlled to be intercepted for scanning.

[0016] In one embodiment of the present invention, in S2, obtaining the initial recognition text data corresponding to the corresponding scanning position includes:

[0017] A processing number corresponding to each scan is established, and the processing number is bound to the coordinate area and the initial recognition text data obtained by the scan.

[0018] In one embodiment of the present invention, in S3, querying the radical information of each character in the initial recognition text data includes:

[0019] Each character in the initial recognition text data is retrieved, and the radical information of each character is analyzed, and all writing image information corresponding to each radical information is obtained.

[0020] In one embodiment of the present invention, in S3, each of the radical information is verified and analyzed at the scanning position, including:

[0021] According to the radical arrangement order in the initial recognized text data, the image of the corresponding non-text data area is scanned again to determine whether the graphic information obtained by the re-scanning corresponds to the radical information of the text. If so, the initial recognized text data is output; if not, the control is to re-query the radical corresponding to the re-scan.

[0022] In one embodiment of the present invention, determining whether the graphic information obtained by rescanning corresponds to the radical information of the character includes:

[0023] The graphic information obtained by scanning again is compared with each of the written image information corresponding to the radical information to determine whether the similarity between the two meets the preset requirements.

[0024] In one embodiment of the present invention, in S3, controlling to re-query and re-scan the corresponding radicals includes:

[0025] The corresponding radical is scanned again for comparison and analysis in the radical database to find a radical that reaches a preset similarity, and the found radical is combined with the rest of the character, and the character is determined based on the combination.

[0026] In one embodiment of the present invention, determining the text according to the combination includes:

[0027] Determine whether the graphic obtained by the combination is a pre-stored text. If not, control the mark to be displayed. If so, directly generate the text obtained by the combination.

[0028] As described above, an information digitization processing method of the present invention has the following beneficial effects: by analyzing the document information data according to the needs, the readable data is directly classified and read, that is, the recognizable text data is obtained. As another part of the document information data, that is, non-text data. It is necessary to perform image interception analysis on the area where the non-text data is located. Specifically, by performing initial recognition on the intercepted image, the initial recognition text data is obtained. Then the radical analysis is performed on the initial recognition text data to determine all the writing methods of the current radical, such as the image of cursive script, official script, etc., and then the intercepted area is scanned again to compare the radicals of the two, so that it can be accurately analyzed whether the initial recognition text data is accurate. If it is not accurate, the radical is controlled to be adjusted and replaced, and it is determined whether the combined image after replacement is a normal text. If not, the mark output display is controlled. If it is a normal text, the normal text is directly output to form an accurate information digitization processing result. Through the above method, the text digitization recognition processing of information data in different types can be realized more accurately, and it can also be realized according to the personalization of writing, and the accurate query of the radical is accurate, which ensures the accuracy of the conversion of information to text. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The figure is a flow chart of the digital processing method of the present invention. DETAILED DESCRIPTION

[0030] The following is an explanation of the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the features in the following embodiments and the embodiments can be combined with each other without conflict. It should also be understood that the terms used in the embodiments of the present invention are intended to describe specific embodiments, rather than to limit the scope of protection of the present invention. The test methods for which specific conditions are not specified in the following examples are usually carried out under conventional conditions or according to the conditions recommended by the manufacturers.

[0031] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention, so they have no substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size should still fall within the scope of the technical content disclosed by the present invention without affecting the effects and purposes that can be achieved by the present invention. At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" quoted in this specification are only for the convenience of description, and are not used to limit the scope of the implementation of the present invention. The change or adjustment of their relative relationship should also be regarded as the scope of the implementation of the present invention without substantially changing the technical content.

[0032] See also Figure 1 The present invention provides a method for digitalizing information, comprising the following steps:

[0033] S1: Collect information data and directly identify and read to obtain recognizable text data;

[0034] S2: Scan the non-text data to obtain initial recognition text data corresponding to the corresponding scanning position;

[0035] S3: querying the radical information of each character in the initial recognition text data, and performing verification and analysis on each radical information at the scanning position to obtain matching confirmation text data;

[0036] S4: inserting the confirmation text data into the recognizable text data to obtain digital processing result data.

[0037] It is not difficult to find from the above content that in the process of digital identification and processing of the data content of the document data, it is necessary to convert the document data into the corresponding processing format first. Then collect the information data in the document data, and divide the information data into recognizable text data and non-text data. Among them, non-text data includes unrecognizable text data, formula data, table data, etc. By directly reading the recognizable text data of the information data first. And in the reading process, non-text data will also be read. Then, when the non-text data is scanned, the initial recognition text data is obtained by recording the scanning position and the initial recognition corresponding to the scanning position. In order to verify the accuracy of the initial recognition text data, the radical information of the initial recognition text data is queried again. And according to the radical situation, the aforementioned scanning position is scanned again for verification and analysis, and then it is determined whether the initial recognition text data obtained by the initial scan is accurate. And after determining whether it is accurate, the confirmation text data is obtained, and the confirmation text data is inserted into the corresponding read recognizable text data, so as to realize the digital processing result of the information data.

[0038] Wherein, in step S1, collecting information data includes:

[0039] The information data to be read is obtained, and the information data is divided into data in which characters can be directly recognized and other data in which characters cannot be directly recognized.

[0040] In one embodiment of the present invention, when collecting information data, there may be multiple types of information data in the document, namely, data that can be directly recognized and read by the processing system, and other data including text data that cannot be directly recognized, formula data, table data, etc., and all data in the information data are recognized and processed.

[0041] Furthermore, in step S1, directly identifying and reading to obtain recognizable text data includes:

[0042] The data capable of directly recognizing characters are read in the order of the information data to obtain the recognizable text data.

[0043] In one embodiment of the present invention, when directly reading recognizable text data, in order to ensure that the final digitally processed data can maintain the order of the original information data, it is necessary to read the directly recognizable characters corresponding to each area in order, that is, to obtain recognizable text data. It is worth noting that when the initial recognition text data is interspersed in the sequentially arranged directly recognizable characters, the corresponding position of the initial recognition text data will also be recorded in the recognizable text data, so that it can be interspersed in the corresponding order after the initial recognition text data is obtained.

[0044] Specifically, in step S2, scanning non-text data includes:

[0045] When the data of the characters that cannot be directly recognized are divided, the coordinate area of ​​the corresponding position that cannot be directly recognized is obtained as the non-text data area, and the image of the non-text data area is controlled to be intercepted for scanning.

[0046] In one embodiment of the present invention, when scanning non-text data, it is necessary to divide the data of the characters that cannot be directly recognized. That is, when the data of the characters that cannot be directly recognized is scanned, the coordinate area of ​​the corresponding area recognized as the characters that cannot be directly recognized is obtained, and then used as the non-text data area. In other words, when the non-text data area is obtained, it is also necessary to capture the image of the non-text data area, and in order to realize the recognition, the image is scanned again to obtain the initial recognition text data.

[0047] Furthermore, in step S2, the initial recognition text data corresponding to the corresponding scanning position is obtained, including:

[0048] A processing number corresponding to each scan is established, and the processing number is bound to the coordinate area and the initial recognition text data obtained by the scan.

[0049] In one embodiment of the present invention, when obtaining the initial recognition text data, in order to better process the data, during scanning, a processing number corresponding to each image scan is established, and each processing number, coordinate area and the scanned initial recognition text data are bound, thereby obtaining a bound processing number-coordinate area-initial recognition text data. Then, according to one of the three, the other two types of data information can be quickly obtained for quick query.

[0050] Next, in step S3, the radical information of each character in the initial recognition text data is queried, including:

[0051] Each character in the initial recognition text data is retrieved, and the radical information of each character is analyzed, and all writing image information corresponding to each radical information is obtained.

[0052] In one embodiment of the present invention, when querying the character radicals of the initial recognition text data, in order to better realize the analysis, each character corresponding to the scanned initial recognition text data is retrieved first, and then the radical information of each character is analyzed. After obtaining the radical information, according to the calligraphy writing characteristics corresponding to the radical, all the image information of the calligraphy corresponding to the corresponding radical information is retrieved, so as to determine whether the image captured in the current information data conforms to the radical corresponding to the initial recognition text data.

[0053] Furthermore, in step S3, each of the radical information is verified and analyzed at the scanning position, including:

[0054] According to the radical arrangement order in the initial recognized text data, the image of the corresponding non-text data area is scanned again to determine whether the graphic information obtained by the re-scanning corresponds to the radical information of the text. If so, the initial recognized text data is output; if not, the control is to re-query the radical corresponding to the re-scan.

[0055] In one embodiment of the present invention, when analyzing and checking the radical information, it is necessary to obtain a re-scanning method for the radical based on the arrangement of the position of the radical corresponding to the text in the initial recognition text data. For example, when the radical is a left-right structure, the left radical will be recognized from left to right, or the right radical will be recognized from right to left. When the radical is an upper-lower structure, the upper radical will be recognized from top to bottom, or the lower radical will be recognized from bottom to top. Or when there is no radical, the captured image will be scanned and recognized again as a whole according to the corresponding stroke order. The graphic information obtained after the re-scan is compared with the position radical corresponding to the initial recognition text data. If it corresponds, the initial recognition text data is output. If it does not correspond, the control is to re-query and re-scan the corresponding radical.

[0056] Specifically, determining whether the graphic information obtained by rescanning corresponds to the radical information of the character includes:

[0057] The graphic information obtained by scanning again is compared with each of the written image information corresponding to the radical information to determine whether the similarity between the two meets the preset requirements.

[0058] In one embodiment of the present invention, after the graphic information is obtained by rescanning, the graphic data is compared with the position radical corresponding to the initial recognition text data, and it is determined whether the similarity of the radical meets the preset requirement. If it does, the initial recognition text data is output, and if it does not, the control is to re-query the radical corresponding to the rescan.

[0059] Next, in step S3, controlling to re-query and re-scan the corresponding radicals includes:

[0060] The corresponding radical is scanned again for comparison and analysis in the radical database to find a radical that reaches a preset similarity, and the found radical is combined with the rest of the character, and the character is determined based on the combination.

[0061] In one embodiment of the present invention, when the radicals of the scanned image need not be controlled to be re-queried, the radical database is queried by using the re-scanned radicals. The radical database stores all the radical big data such as left radicals, right radicals, upper radicals or lower radicals. It is determined whether the scanned radicals have a preset similarity with the radical data. If so, the corresponding radicals are controlled to be output and re-integrated with the other re-scanned radicals to obtain the combined text. It is then determined whether the combined text is normal text.

[0062] Further, determining the text according to the combination includes:

[0063] Determine whether the graphic obtained by the combination is a pre-stored text. If not, control the mark to be displayed. If so, directly generate the text obtained by the combination.

[0064] In one embodiment of the present invention, when judging whether the text is normal text, the combined position graphic is judged to be the same as the pre-stored text determined to be text. If they are the same, the output of the combined text is controlled. If they are not the same, it means that the text is wrong, and it is necessary to mark and display the text corresponding to the combined image, such as highlighting, for warning.

[0065] The present invention also provides an information digital processing system, comprising:

[0066] A text recognition unit is used to collect information data and directly recognize and read the recognizable text data;

[0067] An initial recognition unit, used for scanning non-text data to obtain initial recognition text data corresponding to a corresponding scanning position;

[0068] A text confirmation unit, used for querying the radical information of each character in the initial recognition text data, checking and analyzing each radical information at the scanning position, and obtaining matching confirmation text data; and

[0069] The result output unit is used to insert the confirmation text data into the recognizable text data to obtain the digital processing result data

[0070] In summary, the present invention directly classifies and reads readable poems according to the document information data analyzed as needed, thereby obtaining recognizable text data. As for the other part of the document information data, namely, non-text data, it is necessary to perform image interception analysis on the area where the non-text data is located. Specifically, by performing initial recognition on the intercepted image, the initial recognition text data is obtained. After performing radical analysis on the initial recognition text data, all writing methods of the current radical, such as images of cursive script, official script, etc., are determined, and then the intercepted area is scanned again to compare the radicals of the two, it is possible to accurately analyze whether the initial recognition text data is accurate. If it is inaccurate, the radical is controlled to be adjusted and replaced, and it is determined whether the combined image after replacement is normal text. If not, the mark output display is controlled. If it is normal text, the normal text is controlled to be directly output to form an accurate information digitization processing result. Therefore, the present invention effectively overcomes various shortcomings in the prior art and has a high industrial utilization value.

[0071] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for digitalizing information, characterized in that: The method comprises the following steps: S1: Collect information data and directly identify and read to obtain recognizable text data; S2: Scan the non-text data to obtain initial recognition text data corresponding to the corresponding scanning position; S3: querying the radical information of each character in the initial recognition text data, and performing verification and analysis on each radical information at the scanning position to obtain matching confirmation text data; S4: inserting the confirmation text data into the recognizable text data to obtain digital processing result data.

2. The information digital processing method according to claim 1, characterized in that: In S1, collecting information data includes: The information data to be read is obtained, and the information data is divided into data in which characters can be directly recognized and other data in which characters cannot be directly recognized.

3. The information digital processing method according to claim 2, characterized in that: In S1, directly identifying and reading to obtain recognizable text data includes: The data capable of directly recognizing characters are read in the order of the information data to obtain the recognizable text data.

4. The information digital processing method according to claim 2, characterized in that: In S2, scanning non-text data includes: When the data of the characters that cannot be directly recognized are divided, the coordinate area of ​​the corresponding position that cannot be directly recognized is obtained as the non-text data area, and the image of the non-text data area is controlled to be intercepted for scanning.

5. The information digital processing method according to claim 4, characterized in that: In S2, the initial recognition text data corresponding to the corresponding scanning position is obtained, including: A processing number corresponding to each scan is established, and the processing number is bound to the coordinate area and the initial recognition text data obtained by the scan.

6. The information digital processing method according to claim 4, characterized in that: In S3, querying the radical information of each character in the initial recognition text data includes: Each character in the initial recognition text data is retrieved, and the radical information of each character is analyzed, and all writing image information corresponding to each radical information is obtained.

7. The information digital processing method according to claim 6, characterized in that: In S3, each of the radical information is verified and analyzed at the scanning position, including: According to the radical arrangement order in the initial recognized text data, the image of the corresponding non-text data area is scanned again to determine whether the graphic information obtained by the re-scanning corresponds to the radical information of the text. If so, the initial recognized text data is output; if not, the control is to re-query the radical corresponding to the re-scan.

8. The information digital processing method according to claim 7, characterized in that: Determining whether the graphic information obtained by scanning again corresponds to the radical information of the character includes: The graphic information obtained by scanning again is compared with each of the written image information corresponding to the radical information to determine whether the similarity between the two meets the preset requirements.

9. The information digital processing method according to claim 8, characterized in that: In S3, controlling to re-query and re-scan the corresponding radicals includes: The corresponding radical is scanned again for comparison and analysis in the radical database to find a radical that reaches a preset similarity, and the found radical is combined with the rest of the character, and the character is determined based on the combination.

10. The information digital processing method according to claim 9, characterized in that: Determining the text according to the combination includes: Determine whether the graphic obtained by the combination is a pre-stored text. If not, control the mark to be displayed. If so, directly generate the text obtained by the combination.

Images