JPH06162256A - Ocr system and ocr input paper generating method - Google Patents

Abstract

PURPOSE:To provide the OCR system can easily design OCR input paper, can easily change the designed input paper, and can print a block copy of the input paper designed by a printed attached to the own device. CONSTITUTION:By displaying an OCR input paper generation guidance on a display part 8, and designating and inputting paper size and length and width displayed in the guidance, necessary items including a use work, and size of an input character of a character recognition field, the number of input digits, a space of characters, etc., from an operating part 7, a layout of an input character frame of OCR input form is automatically generated, an automatically generated result is displayed on the display part 8, and also, from a printer 5, a block copy of the OCR input paper is subjected to printing output, and by using this block copy, the OCR input paper is generated.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an OCR system and an OCR input sheet preparation method which can easily design and prepare an OCR input sheet and can easily manage operations such as data input and recognition processing from the prepared input sheet. is there.

[0002]

2. Description of the Related Art In recent years, handwriting character input / processing technology based on OCR has been developed, and recognition of handwriting characters to a considerable extent has become possible. However, characters can be recognized only when they are written in a predetermined frame, and it is also necessary to limit the character size and the character type in order to secure a sufficient recognition rate. .

Therefore, when operating the OCR system, how to design a rational OCR input sheet is an important factor. However, conventionally, most of the design of this OCR input paper relies on manual work. First, the user and the system provider repeatedly hold meetings,
As the first step, the input items were tentatively decided, and where to lay out each input item on the input paper was decided. Then, as a second step, a block copy of the input paper having the layout thus decided was created and brought to the user.

For the first time, the user can understand the actual condition of the OCR input sheet. Therefore, in the third step, the user determines whether or not the work can actually be used under this version, and if it is determined that further changes are necessary, return to the first step again. become. On the other hand, if it is judged that this layout is sufficient, it is officially decided to use it as a block copy. Then, as a fourth step, this is printed to create a plurality of input sheets and delivered to the user to start up the actual OCR system.

[0005]

However, in the case of large-scale processing in which one OCR input sheet is used in a very large amount, the above steps may be taken, but one kind of OCR input sheet requires a large amount of OCR input. If the above is not done, a great deal of labor and cost will be required to produce the block copy, and the practically convenient OCR system cannot be used. For this reason, if it is absolutely necessary to use the standardized general-purpose OCR input paper.

Furthermore, as a result of the use, even if a partial change is desired, the above-mentioned many steps have to be taken again. From the above points, the actual OCR
Actually, even users who have introduced the system have been patience with the problem and are using it.

[0007]

The present invention has been made for the purpose of solving the above-mentioned problems, and has the following structure as one means for solving the above-mentioned problems. That is, in an OCR system capable of creating an OCR input sheet, key input means for inputting instruction information of the OCR input sheet, and display means for displaying instruction input guidance and instruction input result by the key input means, An automatic layout means for automatically laying out input data items on an OCR input sheet based on an instruction input by the key input means; and a printing means for printing out an array result by the automatic array means,
The instruction input using the key input means is selection input of required items and input of required numerical values.

Further, for example, an external storage device for storing the array result of which the layout by the automatic arrangement means is completed is further provided. Alternatively, the printing unit includes a printing position error correcting unit capable of correcting the output position by a minute distance, and can print out the block of the OCR input paper. For example, the reading means for reading the OCR entry information written on the OCR input sheet created based on the block copy printed by the printing means, the recognizing means for recognizing the reading result by the reading means, and the recognizing means. And a managing means for managing the number of recognized cases in batches for each predetermined number. At this time, the read image by the reading unit and the recognition candidate by the recognizing unit are arranged at adjacent positions, and the print state is printed out by the printing unit so that the read state can be recognized.

[0009]

In the above structure, the OCR input paper preparation guidance is displayed on the display means, and at least the paper size, the length and the width, and the application are selected from the items displayed in the guidance by the key input means, and at least the character recognition is performed. The layout of the input character frame of the OCR input paper is automatically created by instructing the size of the input character of the field, the number of input digits, and the character interval by numerical input from the key input means, and the result of the automatic creation is displayed. In addition to displaying on the display unit, the printing unit prints out the block of the OCR input sheet, and the OCR input sheet is created using the block.

As a result, even a general user can easily design the OCR input sheet by his / her own work, and can easily recognize the actual state of the input sheet upon completion of the design. In addition, it is easy to change the designed input paper, which is easy to use.
CR system can be provided. Further, a proofreading galley of an input sheet can be printed by a printer attached to the apparatus and a reading test can be performed using the proofreading galley, and an OCR system can be provided in which the designed input sheet can be easily corrected.

[0011]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment according to the present invention will be described in detail below with reference to the drawings. FIG. 1 is a system configuration diagram of an embodiment according to the present invention. The OCR system of this embodiment is an OC
The OCR form, which is an R input sheet, is designed and printed, and input and processing by the OCR form in which handwritten characters are input are possible.

In FIG. 1, 1 is a CPU which controls the entire operation of this embodiment according to a program, which will be described later, stored in the memory 2, 2 is a memory for recording programs related to OCR processing, which will be described later, 3 is processing data, etc. Hard disk device, which is an external storage device capable of recording a large amount of data, 4 is an OC
Sukiyana that reads the OCR characters etc. written on the R form, 5
Is a printer that prints out the OCR form and prints out the processing results, 6 is a communication control unit that controls the interface with the network 10, 7 is an operation unit for inputting various instructions, and 8 is a processing result and input. A display unit for displaying the result, and 9 is a flexible disk (FD) device, which is used for storing the prepared form data in the FD medium or for reading the stored form data into the system. To do. A line network 10 is connected to a LAN or another communication device that performs facsimile communication or the like.

Schematic OCR of the present embodiment having the above configuration
The processing operation will be described below. However, the present invention is not a system for performing only the OCR processing described below, but can be applied to general office computers or personal computers.
Of course, the CR processing program may be installed and executed. FIG. 2 is a schematic OCR of this embodiment.
3 is a flow chart showing a processing operation. The schematic OCR processing operation of this embodiment will be described below with reference to FIG.

First, in steps S1 to S3, various items are selected and necessary numerical values are input in accordance with the guidance displayed on the display screen of the display unit 8, and a process for designing an OCR form as an input sheet is performed. . That is, first, in step S1, with reference to the guide display on the display unit 8, the operation unit 7
Specify the input character and size of the input OCR paper. Specifically, first, the cursor is moved by inputting an instruction from the operation unit 7, and the paper size (vertical) and the horizontal and vertical sizes of the input paper to be designed displayed on the display screen of the display unit 8 are selected. Then, based on this selection, the specified value provided by the system (a control file that determines the positional relationship in which the data in the form can be arranged) is confirmed.

If the specified value is acceptable, the specified display value is selected. Here, if there is a specified value to be corrected, only the necessary part is corrected using the correction function, and a new user specified value file is created. Then step S2
Similarly, the input data item of each part is designated and input from the operation unit 7. The designation input states described above are sequentially displayed on the display screen of the display unit 8, and the designation input is sequentially performed while confirming the designation state by referring to the display screen. To be more specific, specify the business in which the form to be input is used, and explain / title, definition of character recognition field, etc. (input character size, input digit number, character spacing, recognized character type, frame type, input instruction character) (Relationship with etc.)

When the above instruction is input, the CPU 1 automatically creates an OCR input form based on the designated data in the subsequent step S3. This is, for example, the layout of the input character frame and the input instruction character including the combination of the data items automatically, and the result of the layout displayed on the display unit 8.
The form created by the first designation is a temporary form, and the created form is displayed on the display unit 8 in a form close to the actual print output pattern. Therefore, referring to this display, if the layout is satisfied, the form created by the printer 5 is printed out. This printout can be performed in the form of block copy or in the form of an actual OCR form. Here, in the case of further correction, the position of the correction item is moved to an arbitrary position by the operation unit 7 on the display screen of the display unit 8 and the result is displayed again on the screen or the print result or the like is displayed. The above-mentioned processing is repeated again with reference.

In printing the block copy, the print output position can be adjusted in units of 0.1 mm for each input item in order to correct the printing accuracy of each printer attached to the system. Therefore, it is possible to print out the block copy of the form for which printing accuracy is required from any printer. In this way, when the design of the form is completed and the printing of the block copy is completed, the block with the completed design can be ordered from the printer of the OCR data input sheet as shown in step S101. When the OCR sheet printed in step S102 is delivered, the work process based on the actual OCR input is performed in the process of step S5.

If the form design is completed for the time being, in the process of step S5, test data and the like are entered using the form printed out and read from the scanner 4.
Then, the input recognition processing of the read data from the scanner 4 is performed. Then, it is determined whether or not the form designed in steps S1 to S3 can be used as it is, and if there is any improvement, the form designing process performed prior to step S1 is performed again. In the present embodiment, it is possible to easily design the form and correct the designed form by selecting items on the display screen of the display unit 8 and inputting a few numerical values. Moreover, the form calibrated immediately in step S3 is used. It can be printed out and retested immediately.

Here, in the processing of recognizing the OCR input data in the business after step S5, etc., step S
For example, the recognition support data file created in step S52 is used for the HDD3 or FD by using the recognition support data in the recognition processing of various OCR inputs that are prepared in advance or registered in consideration of the features of the input person, for example. Device 9
The OCR input is recognized by referring to the recognition support data file using the recognition support data in the recognition processing of the various OCR inputs.

In the present embodiment, when recognizing a handwritten character input, the characteristics of the character that the input person may input may be registered in advance and registered as the recognition support data in step S51. Therefore, the recognition support data file used in the recognition processing of the OCR input can be easily created. This support file includes a dictionary for each designated item, a feature dictionary for each person, an external character dictionary, and the like.

In the present embodiment, in this OCR processing operation, a face sheet in which management items are described in batch (form grouping) units is used in order to efficiently convert a large variety of OCR forms into data without processing errors. This sheet can be used for input processing and the subsequent data processing status can be managed by this sheet. Therefore, it is possible to selectively manage either sequential calibration / collective calibration or any of them as needed.

Then, in step S6, a calibration galley is output if necessary, and the calibration process in step S7 can be performed. In step S8, the correction-required data is displayed on the display unit 8 based on the calibration result, and necessary data maintenance is performed.
In step S9, a school completion data record file is created. Then, in step S10, it is registered in the HDD 3.

As described above, according to the present embodiment, the design of the form which is the OCR input sheet, the production of the block copy, the input of the OCR data, the recognition processing of the input data, and the OC are performed by one machine.
All business processing based on R input, without incorporating any computer program, therefore special knowledge,
It can be performed without skill. Next, an OCR input data sheet (form) peculiar to the present embodiment during each of the above-mentioned processes
Various support functions are provided in order to smoothly carry out the design process and the work using the OCR input data sheet. Hereinafter, details of typical functions of this embodiment will be described.

In the present embodiment, these functions are sequentially selected in accordance with the guide displayed on the display screen of the display unit 8 and the necessary numerical values are simply input, whereby the design of the form is automatically completed. It is configured so that you can create a composition. That is, first, the process selection menu screen shown in FIG. 3 is displayed,
The various processes shown on the process selection screen are selectively executed.

As shown in FIG. 3, in the present embodiment, a default value file management function, a form design function, a copy-making function,
It is equipped with recognition support function, data input function, data maintenance function, and other optional functions.
One of these functions will be selected and executed as needed. [Defined Value File Management] The specified value file management of this embodiment can be used in the OCR system of this embodiment A8.
It manages a file in which various prescribed values of standard paper surface for various vertical and horizontal forms (OCR data sheets) of size to A4 size and B6 size to B4 size are determined. . Therefore, when designing a form, the user first uses this management function to define the character size, character spacing, line spacing, field-to-field spacing, and the positional relationship between the field and the outer circumference that can be arranged on the paper. It will be.

In the present embodiment, among the definition of the specified values, the design is performed using the same specified values for the presence / absence of FID, the size of the form, and the orientation of the form (vertical direction up / down, horizontal direction up / down). Business forms can be treated as the same group. It is only necessary to confirm the specified value provided by the system and perform designated selection as necessary by moving the cursor from the operation unit 7. This is a function to be used in a timely manner in the case of the next form design.

[Form design] The form design is a new format O
It is a subsystem for setting and defining a record item format of an input data item of a new OCR data form when data is input using a CR data sheet. Then, at the same time as defining the record item format, it is possible to optimally arrange the record item in the OCR data form according to a simple automatic arrangement rule.

After the definition is completed, the automatic arrangement position can be moved to a position desired by the user. In the present embodiment, at the time of designing this form, the new OCR data sheet to be created by the user is automatically set in which form format and what kind of work data. Therefore, it is not necessary to record the data in a ledger or the like each time, and the data read and processed for the subsequent data input is automatically managed.

In this form design, first, the arrangement of reference marks is determined, and then the character recognition field area is determined. Then, the relationship between each character recognition field and the frame is determined, and the relationship between the input instruction character and the character recognition field in the character recognition field is determined. Due to this relationship, the layout of the character recognition field may be limited, and when displaying the input instruction character next to the character recognition field, it is possible to arrange it over multiple lines.However, the input instruction character may be placed above and below the character recognition field. When displaying, there are restrictions on the number of layout lines.

Examples of reference mark arrangement positions and reference marks from the end of the form are shown in FIGS. 4 and 5.
Details of the contents and values of the positions indicated by the characters in FIG. 4 are shown in FIG. Similarly, FIGS. 6 and 7 show examples of the character recognition field arrangement positions and the distances between the fields from the end of the form. Details of the contents and values of the positions indicated by the characters in FIG. 6 are shown in FIG.

FIG. 8 shows an example of specifying the position of the character recognition field frame. Nine kinds of frames shown in FIG. 9 are prepared, and the frame layout can be easily performed only by designating each line type. It should be noted that each of the above layouts can be specified with the precision within each individual unit shown as each value, and the layout of each part is automatically arranged only by inputting the numerical value corresponding to the position indicated by each alphanumeric character. It can be performed. However, the thickness of the frame line can be specified by the number of dots.

Along with the designation of this frame, the layout of input instruction characters (instruction of the type of data to be written in the corresponding character recognition field) at the time of OCR input is also designated. As an example of the layout of the input instruction characters, it is possible to specify any one of upper, lower, left and right of the character recognition field, an interval, or the like. FIG. 10 shows a print example of the OCR input sheet on which the form is designed in this way. Here, an example is shown in which the frame is a square with a line type of 7, and the input instruction character is arranged in the frame above the character recognition field.

[Preparation of Block] In this embodiment, a function of printing a data sheet on paper is defined for the purpose of printing the OCR data sheet form defined in the above-mentioned form design in preparing the block. Items for displaying data on the display screen of the display unit 8 when the data sheet is read are defined.

In order to print a block copy, first, the model chart of the paper size and orientation to be used is output, and then the measured values are registered to print the block copy, for example, a dropout plate, a black plate, or a completed plate. Print each desired number. At this time, as an auxiliary function, in order to output the block copy regardless of the printing accuracy of the printer 5, the printout position can be corrected in units of (1/10) mm to correct the error. It is configured like. This correction function is prepared for each size and orientation of the block paper.

Therefore, when creating a block using sheets of the same size, the correction value once specified can be used as it is. These correction values may be stored in the FD or the HDD 3. Align the black plate of the block with the registration mark [+] on the drop-out color plate or the completed plate, and write the specified data in the frame and cut it to the specified paper size accurately with the registration mark.
After doing a read test and confirming that it works properly,
The items are automatically displayed on the display screen of the display unit 8 and the items to be displayed here are selected. Items that do not need to be displayed can be omitted.

For example, when the data items of the master-slave relationship that need to be recognized appear in the sixth and seventh columns of one screen, division is automatically prohibited and the data is repeated to the next screen. Control such as lowering is performed. [Recognition Support] This is particularly effective in the case where the writer (entrant) of the handwritten character has a habit of writing unique characters, and the recognition rate cannot be increased by normal recognition. In such a case, in this embodiment,
The handwriting is registered only for the writer, and a recognition correction file is created and registered so that recognition can be performed as accurately as possible. In this registration, it is not necessary to create a troublesome OCR form, and a free format data sheet can be used. In this embodiment, the function of reading a character image by OCR is used so that the external character font can be automatically registered by the division code. For this purpose, a dedicated external character font registration sheet is prepared.

[Data input] A function of reading actual business data using the form created as described above.
It is configured so that batch lot management can be performed by creating a bundle of a large amount of data for any given number of data. In this case, batch management can be selected from a method of writing an instruction on the face control sheet and a method of inputting control instruction data from the operation unit 7.

The present embodiment is not limited to this batch processing, and it is possible to select a job directly from the screen and input data without performing batch batch management. Further, when inputting data, it is possible to set a recognition file in which personal handwriting is registered and recognize the data. Furthermore, as a data input method, 1
Sequential input for immediate correction while displaying each item on the screen,
You can select to input only the data first and batch input to make corrections again after creating the file.

[Data Maintenance] The data maintenance provides various functions for managing data update to the OCR data sheet record file.
It has the following functions. (1) Read image information and recognition result (recognition candidate)
Check list function that prints out the text code information strings of the above (printed example of this check list is shown in FIG. 11).
Shown in).

(2) Read data correction function. (3) A function of creating completed data in an MS-DOS format data file and recording it in the FD. (4) A function of displaying the status of the read data on the display unit 8 and displaying the batch status for grasping the status and changing and correcting the status.

In the present embodiment, any access can be easily performed on a job-batch basis. As described above, according to the present embodiment, a series of software development from OCR form design to operation management can be easily performed only by selecting items displayed on the display screen of the display unit 8 and simple numerical input. You can

In particular, in designing a form, a graphical layout diagram can be obtained by inputting prescribed values for designing the form in accordance with a guide from the display section 8.
The result can be output to a printer. Therefore, O
It is also possible to use it as a composition of a CR form.

[0043]

As described above, according to the present invention, the OC
A series of software development from R form design to operation management can be easily performed by simply selecting the items displayed on the display screen and inputting simple numerical values. In addition, in designing a form, a block copy of the OCR form can be easily printed out by inputting a prescribed value for designing the form.

[Brief description of drawings]

FIG. 1 is a block diagram of an OCR system according to an embodiment of the present invention.

FIG. 2 is a flow chart showing the form design and OCR recognition processing of this embodiment.

FIG. 3 is a diagram showing a display example of a process selection menu on the display unit in the present embodiment.

FIG. 4 is a diagram for explaining the basics when arranging a reference mark according to the present embodiment.

FIG. 5 is a diagram for explaining the basics when arranging the reference marks of the present embodiment.

FIG. 6 is a diagram for explaining the basics when a character field area is arranged in this embodiment.

FIG. 7 is a diagram for explaining the basics when arranging a character field area according to the present embodiment.

FIG. 8 is a diagram illustrating an example of specifying a position for a character recognition field of a frame according to the present exemplary embodiment.

FIG. 9 is a diagram for explaining an example of specifying a position for a character recognition field of a frame according to the present embodiment.

FIG. 10 is a diagram showing an example of a form design in the present embodiment.

FIG. 11 is a diagram showing an example in which read image information and a text code information string of a recognition result (recognition candidate) are arranged and printed out.

[Explanation of symbols]

 1 CPU 2 memory 3 hard disk device HDD 4 scanner 5 printer 6 communication control unit 7 operation unit 8 display unit 9 flexible disk (FD) device 10 line network

Claims (6)

[Claims] 1. An OCR system capable of creating an OCR input sheet, comprising: a key input unit for inputting instruction information of the OCR input sheet; and a display for displaying an instruction input guidance and an instruction input result by the key input unit. Means for automatically laying out input data items on an OCR input sheet based on an instruction input by the key input means, and a printing means for printing out the arrangement result by the automatic arrangement means, The OCR system is characterized in that the instruction input by the key input means is selection input of necessary items and input of necessary numerical values. 2. The OCR system according to claim 1, further comprising an external storage device for storing an array result for which layout by the automatic placement means is completed.
R system. 3. The OCR system according to claim 1, wherein the printing means includes a printing position error correcting means capable of correcting the output position by a minute distance, and is capable of printing out the block copy of the OCR input paper. OCR system. 4. The OCR system according to claim 3, wherein the OCR is created based on a block printed by a printing means.
A reading means for reading the OCR entry information written on the input sheet; a recognizing means for recognizing the reading result by the reading means; and a managing means for managing the number of cases recognized by the recognizing means in batches every predetermined number and controlling the batch. O
CR system. 5. An OCR characterized in that an image read by the reading means and a recognition candidate by the recognizing means are arranged adjacent to each other and printed out by the printing means so that the reading status can be recognized. system. 6. The O in the OCR system according to claim 1.
A CR input paper creation method, wherein the OCR input paper creation guidance is displayed on the display means, and at least the paper size, the vertical and horizontal directions, and the operation to be used are selected from the items displayed in the guidance using the key input means, and at least the characters are displayed. The layout of the input character frame of the OCR input sheet is automatically created by instructing the size of the input character of the recognition field, the number of input digits, and the character interval by numerical input from the key input means, and the result of the automatic creation Is displayed on the display means, the printing means prints out a block copy of the OCR input sheet, and the OCR input sheet is created using the block copy.
How to create input form.