JP2005208978A - Document filing device and document filing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To solve the problem that since the intention of a user is not necessarily reflected on sectioning processing results obtained with physical featured values as a reference, it is necessary for a user to visually confirm all the processing results of automatic sectioning. <P>SOLUTION: Featured values unique to document data are extracted from document data to be inputted by a document inputting part 11 by a featured value extracting part 12, and inter-document sectioning likelihood is evaluated by a sectioning position evaluating part 13 based on the extracted featured values, and the part whose possibility of the sectioning of a document is high is displayed on, for example, a CRT picture so as to be presented to a user based on the evaluation result by a user interface part 15. The user visually confirms the presented part, and when the part is the sectioning of the document, the user applies the instruction of the result to the device side. Then, the device side decides that the part is the sectioning of the document, and stores the document data in a document storing part 14 by associating the document data with the degree of the sectioning likelihood. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a document filing device and a document filing method, and more particularly to a document filing device and a document filing method for storing document data in a storage device and reusing the stored document data.

  In recent years, when a document composed of one or more paper originals is efficiently digitized over a plurality of copies, a process of continuously reading the originals using a scanner device having an automatic paper feed function has been widely performed. . At this time, in order to manage the read document image data (document data) for each document, it is necessary to detect a break between the documents using some method.

  In order to detect a break between documents, conventionally, a specific document separator document (for example, a blank sheet) is inserted between documents before scanning a plurality of document documents, The document separation document is recognized, and the image data of the document is registered in units of documents (for example, see Patent Document 1). In addition, a document separator mark is added to the back side of the document to be used as a document separator in advance, and the document separator mark is recognized by reading both sides of the document with a scanner device, and the image data of the document is registered in document units. (For example, refer to Patent Document 2).

  However, inserting a specific document separation document or adding a document separation mark on the back of the document in this way is a manual operation, which places a heavy burden on the user and is inefficient. In particular, when the number of documents is large, or when the number of pages of each document is large, the operation itself becomes difficult.

  For this reason, a plurality of documents are collectively read by a scanner device having an automatic paper feed function, a feature amount of the read document image is calculated, and a document unit break is determined based on the calculated feature amount. (For example, refer to Patent Document 3). According to this method, it is possible to automatically determine a document break without inserting a document separator document (for example, a blank document) between each document in advance or modifying a document to be a document separator. The burden on the user can be greatly reduced.

JP-A-1-162474 JP-A-7-287747 Japanese Patent Laid-Open No. 2002-24258

  However, in the prior art according to Patent Document 3, separation processing is performed based on physical feature amounts, and the separation result does not necessarily reflect the user's intention, so what kind of document separation the user has made? Therefore, it is necessary to visually confirm all the processing results of the automatic separation, and it is necessary to manually correct by finding an automatic separation error after visual confirmation. Furthermore, there is a possibility that the user himself makes a mistake in the separation position.

  The present invention has been made in view of the above problems, and its purpose is to make the work easier than when the user performs all the work by himself and confirm all the processing results of the automatic separation visually. An object of the present invention is to provide a document filing apparatus and a document filing method that do not need to be performed.

  In order to achieve the above object, according to the present invention, the degree of delimitation between documents of input document data is evaluated, and a portion that is highly likely to be a break in the document is presented to the user based on the evaluation result. When there is an instruction to confirm the presented location as a document break, the input document data is stored in association with the degree of delimiter.

  In a document filing device that stores document data in a storage device and reuses the stored document data, the device side is likely to be a break between documents based on the degree of delimitation between documents for the user. Present the location. The user confirms this visually, for example, and when it is determined that the presentation location is a break in the document, by giving an instruction to that effect, the apparatus side determines that the presentation location is a break in the document.

  According to the present invention, since the user only has to determine whether or not the location presented by the apparatus is a break in the document, the work is easier than the case where the user performs all the work himself and the user's intention is also Since it is reflected, it is not necessary to visually confirm all the processing results of automatic separation.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a block diagram illustrating a configuration example of a document filing apparatus according to an embodiment of the present invention. As is apparent from FIG. 1, the document filing apparatus according to this embodiment includes a document input unit 11, a feature amount extraction unit 12, a break position evaluation unit 13, a document storage unit 14, a user interface unit 15, and a document output unit 16. These components are connected to each other via a bus line 17.

  The document input unit 11 acquires document data from the input document and inputs it as document data to be registered in the document filing apparatus. Here, the input document data includes, for example, image data obtained by scanning from a printed material, image data taken by a digital camera, or a file created by application software. Correspondingly, as the document input unit 11, for example, a scanner device and its control means, a read / write device such as a magnetic disk or a memory card and its control means, data transfer for transferring data via a network, etc. A means for rasterizing a file created by a device or application software into a bitmap image is used.

  The feature quantity extraction unit 12 extracts a quantity (hereinafter referred to as “feature quantity”) indicating a characteristic unique to the document data from the document data in order to evaluate the similarity between the documents. Extraction means and format feature amount extraction means are provided. The image feature quantity extraction means, for example, from the input document data or image data obtained by rasterizing the document data, for example, the color tone, aspect ratio, luminance and color distribution state, edge distribution state, flatness of the entire image. A feature amount of the document data such as an area distribution state is extracted.

The image feature quantity extraction means according to this example is represented by an Ij-dimensional vector (j = 1, 2,..., N, where 1 ≦ Ij, 1 ≦ n, n is an integer) for each image data. It is comprised so that the feature-value of a kind may be extracted. Specifically, for example, as shown in FIG. 2, after the document data is converted into a luminance / color-difference color space L ^* a ^* b ^* , the document data of each color plane is reduced to vertical x horizontal y pixels. A pixel value obtained as a feature value is extracted as an (x × y × 3) dimensional vector. Details of the format feature amount extraction means will be described later.

  The delimiter position evaluation unit 13 extracts the “cover degree” and “back cover” in the continuous document data based on the feature amounts extracted by the feature amount extraction unit 12 and stored in the document storage unit 14 in association with the document data. An index value indicating the degree of delimitation between documents such as “degree” or “degree of document break” is obtained.

  The index value here is, for example, a feature associated with two consecutive document data if the feature amount of each document data is a vector expression (hereinafter, this feature amount is referred to as a “feature vector”). It is a value evaluated based on the Euclidean distance between vectors. Specifically, as shown in FIG. 3A, the case where the Euclidean distance between the feature vectors is small is evaluated as “cover degree” and “document break degree” being small, and as shown in FIG. In addition, the case where the Euclidean distance between feature vectors is long is evaluated as “cover degree” and “document break degree” being large. However, the definition of the distance between feature vectors is not limited to the Euclidean distance.

  In addition, the “cover degree” of the index value indicates the degree of being the first page (cover) of the document, and the “back cover degree” indicates the degree of being the last page (back cover) of the document. In general, the front cover has large text headlines, large blank areas, right-aligned, left-aligned, etc., and the back cover has characters only on the top of the page, Since there is a large blank at the bottom of the page, the feature amount is different from that of a body page where a certain amount of characters of a certain size exist.

  The document storage unit 14 divides the input document data between documents such as n types of feature values extracted by the feature value extraction unit 12, “cover degree”, “back cover degree”, or “document break degree”. It is stored and stored in association with an index value indicating the degree of likelihood and a delimiter position, and is realized by a mass storage device such as a hard disk drive or a DVD (Digital Versatile Disc) -RAM / ± RW / ± R drive.

  The user interface unit 15 displays continuously input document data in a predetermined format, and also displays index values such as “cover degree”, “back cover degree”, or “document break degree” in a predetermined format. Display means for input, and input means for the user to input a document unit break. The display means includes, for example, a CRT (Cathode Ray Tube) and its control means, and the input means includes, for example, a touch panel installed on the CRT screen and its control means.

  The document output unit 16 outputs document data instructed to be output in a predetermined format. For example, a CRT (Cathode Ray Tube) and its control means, a printer device and its control means, a magnetic disk, a memory card, etc. The read / write device and its control means, or a data transfer device that exchanges data via a network or the like. That is, the document output unit 17 outputs, for example, a document printed on paper, image data output to a CRT, or a file formatted by HTML (Hyper Text Markup Language) as an output result.

  Here, the format feature quantity extraction means constituting the feature quantity extraction unit 12 together with the above-described image feature quantity extraction means will be described. This format feature quantity extraction means compares two document images not for the images themselves but also for the similarity of so-called document format features such as character height, character spacing, line spacing, vertical writing and horizontal writing. Such a comparison method is effective for determining whether document images for a certain two pages belong to the same document or different different documents.

  This is because, since it is common for one document to have a uniform appearance, page image groups having the same document format characteristics as described above can be considered to belong to the same document. On the other hand, between the page images belonging to different documents, it is extremely rare that the features of the document format described above are equal unless the documents are intentionally created in the same document format.

  A technique for obtaining document format features such as character height, character spacing, and line spacing from a document image input by a scanner device or the like is well known. In general, even for pages belonging to the same document, the font size, line spacing, and the like differ depending on the part constituting the document, such as the title line, summary section, and body. Therefore, even if the document format features described above are extracted, the values differ depending on the parts constituting the document and are generally not consistent. If the values of the format characteristics are not consistent, it is difficult to determine whether the document images for two pages belong to the same document or to different documents by comparing the characteristics of the document formats.

  Therefore, as shown in FIG. 4, the page image is divided into a plurality of areas, for example, a title part, a summary part, and a text part, and the text part is also divided into a plurality of areas. Next, the feature amount of the document format such as character height, character spacing, line spacing, vertical writing / horizontal writing, etc. is obtained for each of the divided areas. For each feature quantity, the most frequently occurring value is obtained based on the majority rule, and this is used as the feature quantity of the page. In general, the title and summary sections occupy a small area, so using the most frequently used feature value eliminates the influence of the title and summary parts on the feature value. Can be obtained.

In this way, a feature vector of one document format can be obtained from one page image. As an example, the feature vector V of this document format is
V = (Character height, character spacing, line spacing, {vertical writing: 0, horizontal writing: 1})
It is represented by When comparing the two page images A and B based on the features of the document format, the feature vectors of the page images A and B obtained as described above are set as VA and VB, respectively, and the two feature vectors VA and VB are used. Find the distance D between them.
D = ‖VA-VB‖
However, ‖V‖ represents the norm of the vector V. In the above formula, it is determined that the two page images are more similar as the distance D is smaller.

  Next, a procedure for separating document data between documents in the document filing apparatus according to this embodiment having the above-described configuration will be described with reference to the flowchart of FIG.

  For example, the user sets a paper document consisting of one or more pages in an ADF (Automatic Document Feeder). At this time, the paper document may be either a single document (consisting of one or more pages) or a plurality of documents (comprising one or more pages). Also, when setting a paper document, the user need not be aware of document separation. The paper document set in the ADF is sent to the scanner device page by page by the ADF. At this time, the scanner device functions as the document input unit 11 in FIG. That is, from the document input unit 11, the same number of document data as the number of pages of the paper document set in the ADF is input to the document filing device.

  When document data is input from the document input unit 11 (step S11), whether the input document data has already been extracted with a feature amount and is stored in the document storage unit 14 in association with the feature amount. It is determined whether or not (step S12). If the input document data is document data for which feature amounts have not yet been extracted, the feature amount is extracted from the input document data by the feature amount extraction unit 12 (step S13), and then the process proceeds to step S14. To do. If the input document data is already extracted document data, the process directly proceeds to step S14. In other words, the process for extracting the feature amount is not performed on the document data in which the feature amount has already been extracted from the input document data and is stored in the document storage unit 14 in association with the feature amount and the attribute information.

  Next, based on the feature amount extracted by the feature amount extraction unit 12, the “cover degree”, “back cover degree”, or “document cover degree” in the continuously input document data or the accumulated continuous document data is determined. An index value such as “degree of break” is obtained by the delimiter position evaluation unit 13 (step S14), and then continuously input document data or a continuous document stored in the document storage unit 14 based on the obtained index value. Data is displayed in a predetermined format on, for example, a CRT screen of the user interface unit 15 (step S15).

  When displaying continuously input document data or continuous document data stored in the document storage unit 14, for example, as shown in FIG. 6, thumbnails of document data (reduced images) are displayed. Document data with a "cover degree" and "back cover degree" larger than a predetermined reference value is a large thumbnail, and document data with a "cover degree" and "back cover degree" less than a predetermined reference value is a small thumbnail. When the “document break degree” is larger than the predetermined reference value, the interval D between the thumbnails is sparse (large), and when the “document break degree” is less than the predetermined reference value, the interval between the thumbnails is displayed. Display d dense (small). In addition, for places where “the degree of document break” is extremely larger than a predetermined reference value, the front and rear thumbnails are highlighted (indicated by hatching in the figure), and this is clearly indicated.

  The user visually confirms when the continuously input document data or the continuous document data stored in the document storage unit 14 is displayed in a predetermined format on the CRT screen of the user interface unit 15. . At this time, the display state of the thumbnail of the document data can be changed by a user operation. For example, the user can perform a drag operation on a thumbnail of any document data in any direction by simulating that continuously input document data or accumulated continuous document data is connected with a predetermined spring constant. can do.

  Therefore, in the state where the continuously input document data or the continuous document data stored in the document storage unit 14 is displayed in a predetermined format on the CRT screen of the user interface unit 15, the thumbnail of the document data is displayed by the user. It is determined whether or not there has been an operation to change the display state (step S16). If the user drags a thumbnail of arbitrary document data in an arbitrary direction, it does not move only the thumbnail that was dragged, but instead of moving the thumbnails of the document data arranged in line according to a predetermined spring constant. The movement is simulated, the layout is calculated so that the positions and intervals of the thumbnails of the arranged document data change in real time (step S17), and then the process returns to step S15.

  To explain with a specific example, on the CRT screen of the user interface unit 15, as shown in FIG. 7A, the user drags a thumbnail of arbitrary document data (indicated by an arrow in the figure) When a drag operation for moving in an arbitrary direction is performed, only the thumbnails that have been dragged are not moved, but as shown in FIG. 7B, the document data arranged and linked according to a predetermined spring constant are arranged. Display thumbnail positions and intervals so that they change in real time.

  In the state in which the continuously input document data or the continuous document data stored in the document storage unit 14 is displayed as thumbnails on the CRT screen of the user interface unit 15, if the user does not change the thumbnail display, Judging from the thumbnail display, it is determined whether or not there is a break in the document (step S18). That is, when there is a break in the document, the user performs an operation for determining that the portion is a break in the document. As a result, the separation confirmation process is performed in which the input document data and the delimiter position are associated with each other and stored in the document storage unit 14 (step S19).

  On the other hand, as shown in FIG. 8 (A), although it is clearly displayed on the CRT screen of the user interface unit 15 such as highlighting that “the degree of document break” is larger than a predetermined reference value, If it is not a break in the document, the user performs an operation for determining that the part is continuous. As a result, as shown in FIG. 8B, a continuous determination process is performed in which the continuously input document data is stored in the document storage unit 14 as it is (step S20).

  Note that the spring constant between the document data may be a constant value, or may correspond to an index value such as “cover cover degree”, “back cover degree”, or “document break degree”, which differs for each interval. Different values may be set.

  In addition, a visible or invisible virtual fixed point is provided on the screen on which the document data is arranged, and the movement of the thumbnail of the document data is simulated so that the fixed point and the document data are connected with a predetermined spring constant. Alternatively, a predetermined resistance value may be given between the document data or between the document data and the screen on which the document data is arranged to simulate the movement of the thumbnail of the document data. A predetermined mass may be given to the data to simulate the movement of the thumbnail of the document data.

  In the above-described embodiment, a case has been described in which the characteristic amount unique to the document data is extracted from the input document data, and the degree of separation is evaluated based on the extracted characteristic amount. It is not limited to. As another evaluation method, for example, a document image is captured by an OCR (Optical Character Reader), the similarity of the contents of the document is evaluated, and the degree of separation is evaluated based on the similarity. A method is mentioned.

It is a block diagram which shows the structural example of the document filing apparatus which concerns on one Embodiment of this invention. It is a conceptual diagram of feature amount extraction. It is a conceptual diagram of similarity evaluation. It is a figure which shows the state which divided | segmented the page image into the several area | region when extracting the feature-value of a document format. It is a flowchart which shows the procedure of the separation process between the documents of document data. It is explanatory drawing (the 1) of the separation process between the documents of document data. It is explanatory drawing (the 2) of the separation process between the documents of document data. It is explanatory drawing (the 3) of the separation process between the documents of document data.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 11 ... Document input part, 12 ... Feature-value extraction part, 13 ... Separation position evaluation part, 14 ... Document storage part, 15 ... User interface, 16 ... Document output part

Claims (9)

A document input means for inputting document data;
Evaluation means for evaluating the delimitation between documents of the document data input by the document input means;
Presenting means for presenting a portion that is likely to be a break in the document based on the evaluation result of the evaluation means;
Storage for storing the document data input by the document input unit in association with the degree of demarcation evaluated by the evaluation unit when there is an instruction to determine the location presented by the presentation unit as a break in the document And a document filing apparatus. A feature amount extracting unit that extracts a feature amount specific to the document data from the document data input by the document input unit;
The document filing apparatus according to claim 1, wherein the evaluation unit evaluates the delimitation based on the feature amount extracted by the feature amount extraction unit. The document filing apparatus according to claim 1, wherein the degree of separation is a cover degree, a back cover degree, or a document break degree. The presenting means uses a large thumbnail for document data having a cover degree or back cover degree greater than a predetermined reference value, and is small for document data having the cover degree or back cover degree equal to or less than the predetermined reference value. The document filing apparatus according to claim 3, wherein the document filing apparatus is displayed as a thumbnail. The presenting means narrows the interval between thumbnails when the degree of breaks in the document is larger than a predetermined reference value, and closes the interval between thumbnails when the degree of breaks in the document is less than the predetermined reference value. The document filing apparatus according to claim 4, wherein the document filing apparatus is displayed. The evaluation means is characterized in that, when evaluating the degree of separation between documents of document data, a feature serving as a reference in performing the evaluation is extracted from data obtained by capturing at least a part of the document data as an image. The document filing apparatus according to claim 1. A first step of evaluating the delimiter between documents of input document data;
A second step of presenting a portion that is likely to be a break in the document based on the evaluation result in the first step;
A third step of storing the input document data in association with the degree of delimitation by the evaluation in the first step when there is an instruction to determine the location presented in the second step as a document break; And a document filing method. The said 1st step WHEREIN: The feature-value peculiar to the said document data is extracted from the said input document data, The degree of the said division | segmentation is evaluated based on this extracted feature-value. Document filing method. In the first step, when evaluating the degree of separation between documents of document data, a feature serving as a reference in performing the evaluation is extracted from data obtained by capturing at least a part of the document data as an image. The document filing method according to claim 7.

Images