JP3923034B2 - Symbol encircling judgment device, symbol encircling judgment method, program, and recording medium - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a symbol encircling determination apparatus, a symbol encircling determination method, a program, and a recording medium for recognizing (determining) a selection state of an option of a method of encircling symbols such as numbers in a document image read from an image scanner or the like It is about.
[0002]
[Prior art]
In various form sheets, there is not only a portion for entering characters, but also a “circled choice” portion for selecting an item by enclosing the characters in a circle.
[0003]
Conventionally, the determination of the selection state of such a circled-type option is performed by using an image without a circle in advance as a standard image, as in the invention in Japanese Patent Laid-Open No. 10-187865 (Patent Document 1). It is stored so that it is determined whether or not it is circled by comparison with the input image.
[0004]
In the invention disclosed in Japanese Patent Laid-Open No. 2002-183663 (Patent Document 2), an image recorded in an option part of a read form is extracted using a recognition dictionary in which “circled numbers” are registered, A technique for calculating the degree of similarity between an image pattern of “circled numbers” and determining whether or not the option is circled by determining whether the number is a “circled number” based on the calculated similarity It is.
[0005]
[Patent Document 1]
JP-A-10-187865
[0006]
[Patent Document 2]
JP 2002-183663 A
[0007]
[Problems to be solved by the invention]
In the technique of Patent Document 1 described above, since it is necessary to store a “circled option” part (an option part of an unfilled form) as a standard image for each form, the operation becomes complicated and the standard Image management is required, and there are drawbacks such as being very complicated. When there is no unfilled (unselected) form (when there is only a filled form), the above-described standard image cannot be stored, and as a result, the selection state cannot be determined. There were disadvantages such as.
[0008]
In addition, in the technique of Patent Document 2 described above, a standard image for each form is not necessary, but since it is a technique using a recognition dictionary, it is easily affected by the shape of a circle surrounding a symbol or noise when reading a form. There was a problem. Specifically, since OCR (Optical Character Reader) is used using a recognition dictionary for circled numbers and uncircled numbers, it is easily affected by the shape of circles surrounding the symbols and noise, and the degree of similarity with the above recognition dictionary Decreases, and as a result, the recognition rate is lowered.
[0009]
The present invention has been made to solve the above-described problems, and an object of the present invention is to cut out a determination target area including a predetermined symbol from the image data, and use the cut-out area as a band-shaped area in a predetermined direction. A line segment in each band-like area divided into two is searched and counted, and when the band-like areas in which the number of line segments in the counted band-like area is equal to or greater than the first specified value are continuous, A predetermined area such as a form by counting the number of belt-shaped areas that are counted and comparing the counted number of band-shaped areas with a first threshold value to determine whether or not the symbol is surrounded by a predetermined figure. It is possible to easily determine whether or not a predetermined symbol in a form or the like is surrounded by a predetermined figure such as a circle without storing and managing the image as a standard image. Improved symbol box format It is to provide an apparatus and a symbol enclosed determining method and program and recording medium.
[0010]
[Means for Solving the Problems]
According to a first aspect of the present invention, there is provided a symbol enclosing determination device for recognizing whether or not a predetermined symbol included in image data is surrounded by a predetermined figure, and a determination target region including the predetermined symbol from the image data Identifying means (CPU 101 shown in FIG. 1, step S502 in FIG. 5, steps S602, S603 in FIG. 7, step S702 in FIG. 10), and the determination target area specified by the specifying means as a band-like area in a predetermined direction The first counting means (CPU 101 shown in FIG. 1, step S504 in FIG. 5, step S606 in FIG. 7) and the first counting means count the number of line segments by searching in each band-like area divided into two. A second counting hand that counts the number of continuous band-like areas when the number of line-shaped areas that are equal to or greater than the first specified value is continuous. (The CPU 101 shown in FIG. 1, step S507 in FIG. 5, and step S609 in FIG. 7) and the number of strip regions counted by the second counting means and the first threshold value are compared, whereby the symbol is predetermined. It is characterized by comprising determination means (CPU 101 shown in FIG. 1, steps S510 to S512 in FIG. 5, steps S612 to S614 in FIG. 7) for determining whether or not it is surrounded by a figure.
[0011]
According to a second aspect of the present invention, there is provided first calculation means (the CPU 101 shown in FIG. 1, step S509 in FIG. 5, step S611 in FIG. 7) for calculating the first threshold value based on the resolution of the image data. Furthermore, it is characterized by having.
[0012]
According to a third aspect of the present invention, there is provided a third counting means (CPU 101 shown in FIG. 1, FIG. 1) for counting the total number of rows in which the number of line segments counted by the first counting means is equal to or greater than a first specified value. 5 in step S507 and step S609 in FIG. 7), and the determination means compares the number of strip regions counted by the second count means with the first threshold value, and the third count. Based on the total number of strip-like areas counted by the means and the comparison result between the second threshold value, it is determined whether or not the symbol is surrounded by a predetermined figure (steps S510 to S512, FIG. 7 in FIG. 5). Steps S612 to S614).
[0013]
According to a fourth aspect of the present invention, there is provided second calculation means (the CPU 101 shown in FIG. 1, step S509 in FIG. 5, step S611 in FIG. 7) for calculating the second threshold value based on the resolution of the image data. Furthermore, it is characterized by having.
[0014]
The fifth invention of the present invention further comprises storage means (RAM 102 shown in FIG. 1) for storing the maximum value of the number of band-like areas counted by the second counting means, and in the determination means, the storage means The maximum value of the number of strip-shaped areas stored is compared with the first threshold (steps S510 to S512 in FIG. 5 and steps S612 to S614 in FIG. 7).
[0015]
The sixth invention of the present invention further comprises noise removing means (CPU 101 shown in FIG. 1, step S604 in FIG. 7) for removing noise from the determination target area specified by the specifying means. .
[0016]
In a seventh aspect of the present invention, the predetermined symbol intersects with a band-like region that is continuous for the number of the first thresholds with a width equal to or greater than a predetermined value, or the first symbol Stipulated value -2 "symbol having a curve as a constituent element (for example, the symbols" 0 "to" 9 "of the Arabic numerals include the Arabic numerals when the first specified value is" 3 ") When the determination target region is divided into horizontal rows, “3-1” (that is, two) or “3-2” (that is, one) where two or more pixels intersect with each other in a row. ), Which corresponds to a symbol that can be determined by the symbol enclosing determination device of the present invention.
[0017]
The eighth invention of the present invention is characterized in that the predetermined symbol is an Arabic numeral.
[0018]
According to a ninth aspect of the present invention, the first specified value is “3” or “5”.
[0019]
The tenth aspect of the present invention recognizes whether or not a predetermined symbol included in image data is surrounded by a predetermined figure. In information processing equipment for In the symbol box judgment method, The first counting means includes the predetermined symbol in the image data A first counting step (step S504 in FIG. 5 and step S606 in FIG. 7) for searching the inside of each band-like area obtained by dividing the determination target area into band-like areas in a predetermined direction and counting the number of line segments; The second counting means is A second counting step (in FIG. 5) that counts the number of the continuous band-like regions when the number of line-segments counted in the first counting step is continuous. Step S507, Step S609 in FIG. The judging means A determination step (steps S510 to S512 in FIG. 5) for determining whether or not the symbol is surrounded by a predetermined figure by comparing the number of strip-like regions counted in the second counting step with a first threshold value. , Steps S612 to S614 in FIG. 7.
[0020]
An eleventh aspect of the present invention is the symbol encircling determination method described in the tenth aspect. Information processing equipment Execution Make It is the program for this.
[0021]
The twelfth aspect of the present invention is the first aspect 1 Described in the invention A computer-readable recording medium on which a program is recorded It is characterized by that.
[0022]
DETAILED DESCRIPTION OF THE INVENTION
[First Embodiment]
FIG. 1 is a block diagram showing a configuration of a symbol enclosing determination apparatus showing a first embodiment of the present invention.
[0023]
In the figure, reference numeral 101 denotes a CPU which controls the entire apparatus. Reference numeral 102 denotes a RAM which is used as a work area for the CPU 101 and is also used for storing a form image read by the image scanner 108 or the like. A ROM 103 stores a program for controlling the apparatus. Reference numeral 104 denotes an external storage device such as a magnetic disk (hard disk, floppy (registered trademark) disk), magneto-optical disk (MO), or optical disk (CD-ROM, DVD-ROM). It should be noted that the determination program for the selection status of the circled options shown in the flowchart described later executed by the CPU 101 is stored in the ROM 102 or the external storage device 104. Reference numeral 105 denotes a display for displaying image data of a form read from the image scanner 108 or the like. Reference numeral 106 denotes a keyboard, and 107 denotes a pointing device such as a mouse. Reference numeral 108 denotes an image forming apparatus such as an image scanner, which may be built in the apparatus or externally connected to the apparatus. When externally connected, it is connected to the apparatus via an interface such as USB or IEEE1394.
[0024]
Hereinafter, with reference to FIG. 2 and FIG. 3, the selection state determination method of the circled option will be described.
[0025]
2 and 3 are schematic diagrams showing examples of symbols corresponding to options determined by the symbol surrounding determination device of the present invention. FIG. 2 corresponds to a state where selection is not made in a circle. Corresponds to a state where selection is made in a circle.
[0026]
As shown in FIG. 2, the numerical character portion is a black pixel, and the other portions are white pixels. When the pixels arranged in the horizontal direction are viewed as one row (band-like region obtained by dividing the determination target region including option symbols in a predetermined direction) as in 201 to 205, 206 to 210 are included in each row. As can be seen, several continuous black pixels (line segments) are seen.
[0027]
Usually, pre-printed characters and handwritten circles are composed of black pixel lines of at least a few dots, so non-continuous black pixels (for example, black pixels of only one dot) are considered noise. You can ignore it.
[0028]
Similarly to the above, when looking at each row of a numeral image surrounded by a circle as shown in FIG. 3, there are always three or more line segments, such as 311 to 315, where there are numbers.
[0029]
For numbers that are not circled, the number of line segments in each row is usually 1 or 2 and there are only a few 3 rows in some numbers.
[0030]
In the type number “6” as shown in FIG. 4, there are only three rows indicated by 403 in the portion 402 where the portion 401 is enlarged.
[0031]
Therefore, if the total number of lines including three or more lines and the number of consecutive lines included in each line is a certain number or more, it can be determined that the line is surrounded by a circle.
[0032]
Note that the reason for determining that the number of line segments included in each row is circled when the total number of lines and the number of consecutive lines is equal to or greater than a certain value is to improve recognition accuracy. Unless both the total number and the continuous number are equal to or greater than a certain value, it is not impossible to determine that they are surrounded by a circle. That is, if either one of the total number or the continuous number is equal to or greater than a certain value, it can be determined that it is surrounded by a circle.
[0033]
FIG. 5 is a flowchart showing an example of the first control process in the symbol enclosing determination apparatus of the present invention, and corresponds to the process of determining the selection state of the option of enclosing the symbols in circles. Note that the processing in this flowchart is executed by the CPU 101 shown in FIG. 1 based on a program stored in the ROM 102, the external storage device 104, or other recording medium. S501 to S512 indicate each step.
[0034]
First, in step S501, an image (form image data) read by a device such as the image scanner 108 is stored in the external storage device 104, the RAM 102, or the like. In addition, you may memorize | store in other recording media (The external storage device etc. which a file server connected with this apparatus via a network include).
[0035]
Next, in step S502, the coordinates of the determination target area (option position coordinates) are acquired from the image data of the form read in S501 and stored in the external storage device 104 or the RAM 102, and stored in the work area such as the RAM 102. . Thereafter, the determination target area is identified from the coordinates of the determination target area (cutout process), and the process proceeds to S503.
[0036]
Note that the coordinates of the determination target area are specified by operating the pointing device 107 such as a mouse (for example, 600 in the figure) in the window system user interface shown in FIG. 6 for the form image read in S501. It can be performed by a method of storing in the external storage device 104 or the like.
[0037]
Next, in step S503 to step S508, the rules in the row are determined in all rows (top row to bottom row) of the determination target region (option region) specified based on the coordinates of the determination target region acquired in step S502. The number of line segments having a length equal to or greater than a value (for example, 2 dots) is counted (S504), whether or not there are three or more line segments is determined (S505), and it is determined that there are three or more line segments. If so, the total number and the number of consecutive lines with three or more line segments are counted up (S507). On the other hand, if it is determined that there are not three or more line segments, the process resets the number of consecutive lines with three or more line segments (S506).
[0038]
When the number of consecutive lines having three or more line segments is reset in step S506, the maximum value of the number of consecutive lines having three or more line segments is stored in the work area in the RAM 102, and the memory is stored. The maximum value obtained is used in the determination in step S510, which will be described later, as the number of consecutive rows having three or more line segments.
[0039]
Here, the total number of lines having three or more line segments used for determining that they are surrounded by a circle and the threshold value for the continuous number are changed according to the resolution of the image to be determined. A fixed value may be prepared from the beginning and stored in the RAM 102, ROM 103, external storage device 104, or other recording medium.
[0040]
In step S509, the threshold value is calculated from the resolution of the image. For example, the threshold for the continuous number is 1 point (1/72 inch = approximately 4 lines at 300 DPI), and the threshold for the total number is 4 points (1/18 inch = approximately 17 lines at 300 DPI). To change. When a fixed value is prepared, the fixed value is read from the external storage device 104 or the like.
[0041]
Next, in step S510, it is determined whether or not the total number of rows and the number of consecutive lines having the above three or more line segments are both equal to or greater than the threshold value. In S512, it is determined that the option is circled (that is, selected), and the process ends.
[0042]
On the other hand, if it is determined in step S510 that at least one of the total number of rows and the number of consecutive lines having the three or more line segments is less than the threshold value, the option is circled in step S511. It is determined that there is no (that is, not selected), and the process ends.
[0043]
In the present embodiment, it is determined whether or not the total number of rows and the number of consecutive lines having the above three or more line segments are both equal to or greater than the threshold value. In S512, it is determined that the option is circled (that is, selected), but this is to improve recognition accuracy. If both are not equal to or greater than the threshold value, the option is circled. It does not mean that it cannot be judged whether or not That is, if it is determined that either the total number of rows or the number of consecutive lines having three or more line segments is equal to or greater than the threshold value, the option is circled in step S512 (ie, It may be determined that the process has been selected), and the process may be terminated.
[0044]
Similarly, in the second to fifth embodiments to be described later, when it is determined that either one of the total number of rows having three or more line segments or the continuous number is greater than or equal to the threshold value, the option is round. It goes without saying that it is possible to adopt a configuration in which it is determined that the frame is surrounded (that is, selected) and the circled circle determination process is terminated.
[0045]
In the above flow chart, the option is circled depending on whether the total number of lines having three or more line segments having a length equal to or longer than the specified value in the line and the continuous number is equal to or greater than a threshold value (see FIG. In other words, for example, when the number of options is in parentheses, for example, “(6)”, the length of the line is longer than the specified value in the line. Assume that determination is made using the total number of lines having five or more line segments and the number of continuous lines.
[0046]
[Second Embodiment]
In the present embodiment, a process for removing the image noise is further provided in the selection processing of the option selection state of the method of enclosing the symbols shown in the first embodiment in a circle. The embodiment will be described below.
[0047]
FIG. 7 is a flowchart showing an example of the second control process in the symbol enclosing determination apparatus of the present invention, and corresponds to the determination process of the selection state of the option of the method of enclosing the symbols in the second embodiment of the present invention. . Note that the processing in this flowchart is executed by the CPU 101 shown in FIG. 1 based on a program stored in the ROM 102, the external storage device 104, or other recording medium. S601 to S614 indicate each step.
[0048]
Note that steps S601 and S602 shown in FIG. 7 are the same steps as S501 and S502 shown in FIG.
[0049]
After acquiring the position coordinates of the options in step S602, in step S603, the determination target area portion is extracted from the position coordinates of the form image data (processing for cutting out image data) and stored in the work area such as the RAM 102.
[0050]
Next, in step S604, noise is removed from the extracted image of the determination target area. For this noise removal processing, a known noise removal processing method in which an isolated black pixel (for example, a black pixel having only one dot surrounding a white pixel) is determined and removed as noise can be used.
[0051]
Then, after the noise removal processing in step S604, the process proceeds to steps S605 to S614, where the total number of lines having three or more line segments having a length equal to or longer than the specified value in all lines and the number of consecutive lines are counted, and whether or not selection is made is determined. Processing to determine is performed.
[0052]
Hereinafter, steps S605 to S614 are the same as steps S503 to S512 shown in FIG.
[0053]
According to the present embodiment, the process of removing the image noise (steps S603 and S604) is provided in the determination process of the selection state of the option of the method of enclosing the symbols shown in the first embodiment in a circle. The determination accuracy of the selection status of the circled options can be significantly improved without being affected by image noise generated when the form image is read by the image scanner 108 or the like.
[0054]
[Third Embodiment]
In the first embodiment, the configuration in which the selection state is determined using one option symbol as a determination region in the option of selecting an item by enclosing the symbol in a circle has been described. However, a plurality of option symbols are arranged vertically. In this case, the selection state may be determined using a region including the plurality of option symbols as a determination region. The embodiment will be described below.
[0055]
FIG. 8 is a schematic diagram showing an example of an option determination area in the third embodiment of the present invention.
[0056]
In the present embodiment, as shown in the figure, in the option of selecting an item by enclosing the numbers in circles, when a plurality of option numbers are arranged vertically, the plurality of option symbols are displayed as 801 in FIG. As shown by the dotted frame, the region to be determined is collectively included.
[0057]
Then, as shown in FIG. 9 to be described later, a plurality of option symbols are obtained by extracting a region including each option symbol from a determination target region including a plurality of option symbols and determining a selection state of each of the extracted regions. It is assumed that the selection state in the determination target area including the is determined.
[0058]
Hereinafter, a method for determining a selection state by extracting a region including each option symbol from the determination target region including a plurality of option symbols described above will be described with reference to FIG.
[0059]
FIG. 9 is a schematic diagram illustrating processing for extracting a region including each option symbol from the determination target region including a plurality of option symbols and determining the selection state in the third embodiment of the present invention.
[0060]
The processing in FIG. 9 is executed by the CPU 101 based on a program stored in the ROM 102, the external storage device 104, or other recording medium, as described in the flowchart in FIG.
[0061]
As shown in FIG. 9, the determination target area includes continuous rows (901, 902, 903, 904, and 905 in the figure) having no black pixels and option symbols such as numbers or circled black pixels surrounding it. Are divided into consecutive lines (906, 907, 908, and 909 in the figure).
[0062]
Therefore, an area 906 from the line after the end of the continuous line 901 having no black pixel to the start of the line 902 having no next black pixel is extracted (extracted) as the first option, and the first embodiment or Assume that the determination is made by the method for determining the selection state of the circled options shown in the second embodiment.
[0063]
When the determination result in the extracted area (area 906 where black pixels exist) is “not selected”, the area 907 where the next black pixels exist is cut out (extracted) and determined.
[0064]
This is repeated up to the area 909, and it is determined that the index of the area where the black pixel exists when the determination result is “selected” (the option number counted from the top) is selected. To do.
[0065]
FIG. 10 is a flowchart showing an example of the third control process in the symbol enclosing determination apparatus of the present invention, corresponding to the determination process of the selection state of the option of the method of enclosing the symbols in the third embodiment of the present invention. . Note that the processing in this flowchart is executed by the CPU 101 shown in FIG. 1 based on a program stored in the ROM 102, the external storage device 104, or other recording medium. S701 to S708 indicate each step.
[0066]
Note that steps S701 and S702 shown in FIG. 10 are the same steps as S501 and S502 shown in FIG.
[0067]
After the position coordinates of the options (for example, the determination target area 801 shown in FIG. 8) are acquired in step S702, the following steps S704 to S707 are performed for the number of options in steps S703 to S708.
[0068]
First, in step S704, an area (for example, 906 in FIG. 9) of continuous rows with 0 or more black pixels sandwiched between rows with 0 black pixels is extracted and stored in a work area such as the RAM 102. . In step S705, the above-explained continuous row region having 0 or more black pixels is subjected to the determination processing shown in steps S503 to S512 in FIG. 5 or steps S604 to 614 in FIG. 7, and in step S706. It is determined whether or not the determination result of the determination process in step S705 is “selected”.
[0069]
If it is determined in step S706 that the determination result in step S705 is “not selected”, the process returns to step S704, and the number of black pixels that are sandwiched by the next black pixel number 0 row is equal to or greater than zero. The region of the row (for example, 907 in FIG. 9) is extracted, and the determination process shown in steps S503 to S512 in FIG. 5 or steps S604 to 614 in FIG. 7 is performed.
[0070]
On the other hand, if it is determined in step S706 that the determination result in step S705 is “selected”, the process exits the loop shown in steps S703 to S708, and in step S707, the option corresponding to the determined area is selected. It is determined that an index has been selected, the index is stored in a work area such as the RAM 102 or the external storage device 104, and the process ends. In the option index storage process in step S707, although not shown in the figure, a counter for counting the number of loops in steps S703 to S708 is provided, and the number of options selected by this counter is acquired. The data is stored in a work area such as the RAM 102 or the external storage device 104.
[0071]
According to this embodiment, in the option of selecting an item by enclosing the symbol in a circle, when a plurality of option symbols are arranged vertically, an area including the plurality of option symbols is designated as a determination area. As a result, it can be determined which of the plurality of options is selected, and the determination target region designation work by the user can be greatly reduced.
[0072]
In the present embodiment, the configuration in which the option first determined to be in the selected state is determined to be in the selected state has been described. However, even after it is determined that a certain option is in the selected state, step S703 is performed up to the last option. When the determination process of S708 is repeated and it is finally determined that a plurality of options are selected (when only a single selection is permitted), a warning is displayed as an error, Only the options determined to be in the selected state may be determined again.
[0073]
Thereby, it is possible to discover selection mistakes such as multiple selections and improve the determination accuracy of the selection state.
[0074]
If multiple selection is permitted, it is also possible to obtain a multiple selection result.
[0075]
Further, in FIG. 8 and FIG. 9, in the case where a plurality of options are arranged vertically, the area from the line after the end of a continuous line without any black pixels to the start of the line without any black pixels is shown. In the case where a plurality of options are arranged in a direction other than the vertical direction, the area including the plurality of options is orthogonal to the direction in which the options are arranged. The areas from the end of the continuous band-shaped area having no black pixel to the start of the next band-shaped area having no black pixel are extracted as option determination areas and determined respectively. (Steps S705 to S707) may be configured.
[0076]
For example, in the case where a plurality of options are arranged in the horizontal direction, an area including the plurality of options is divided into a vertical belt-like area (that is, “column”), and a continuous column having no black pixels is completed. An area from the column until the start of a column having no next black pixel may be extracted as an option determination region and each may be determined.
[0077]
Furthermore, when a plurality of options are arranged in the vertical and horizontal directions (for example, arranged in a matrix of 2 × 3 in length and width, etc.), an area including a plurality of option symbols in the vertical and horizontal directions is designated as a determination area. In addition, the area is divided into the number of columns of options (for example, in the case of options arranged in 2 × 3, it is divided into three areas vertically), and step S703 is performed for each of the divided vertical areas. You may comprise so that the process of S708 may be performed. Note that the number of divisions of the vertical area described above may be input by the user, or may be determined by OCR or the like.
[0078]
As a result, for any of the choices arranged vertically, the choices arranged side by side, and the choices arranged side by side, the user simply designates an area including a plurality of option symbols, and the selection state in the area is determined. Since the determination can be performed, the determination target area designation work by the user can be greatly reduced.
[0079]
[Fourth Embodiment]
In the first to third embodiments described above, the configuration for determining whether or not a number is surrounded by a circle with respect to one determination target region of one type of form has been described, but step S502 in FIG. 5 is performed. ~ S512 or steps S602 to S614 in FIG. 7 or steps S702 to 708 in FIG. 10 are sequentially executed for a plurality of determination areas, so that a plurality of determination target areas in one type of form are processed. Selection state determination processing can be performed.
[0080]
In addition, for a plurality of types of forms, in combination with existing form type discriminating means (means for judging which form has been read in comparison with a pre-stored form image, etc.) If set in advance, it is possible to easily determine whether or not a symbol is circled by simply instructing image reading and execution of determination for a plurality of forms.
[0081]
[Fifth Embodiment]
In the first to fourth embodiments described above, a configuration for determining whether or not symbols such as numbers are circled for one or a plurality of determination target areas for one form is shown. However, using the image scanner 108 or the like capable of continuous reading, a plurality of forms are set in the image scanner 108 or the like, and the processing shown in FIG. 5, FIG. 7, or FIG. With this configuration, the symbols in the determination target area (one or a plurality of predetermined determination target areas) are sequentially circled while sequentially reading a plurality of forms (one type or a plurality of types of forms). It is also possible to sequentially determine whether or not they are.
[0082]
As described above, according to each of the embodiments described above, the registration work for storing the image of the predetermined area of the form as a standard image is not performed, and the circular shape surrounding the option symbols such as numbers is conscious. It is possible to determine the selection state of the option of the method of enclosing the symbols on the form with circles.
[0083]
Further, among the options of the method of encircling the symbols, there is one in which a dotted guide is printed around the option symbols such as numbers as shown in FIG.
[0084]
In the present invention, since both the total number of lines and the number of continuous lines in which the number of line segments included in one line exceeds the prescribed number are to be determined, even when the dotted guide portion is a black pixel. , Because the number of line segments included in one line including the black pixels of the guide part exceeds the specified number is not continuous, so the continuous lines of lines where the number of line segments included in one line exceeds the specified number Dotted lines around the choice symbol (even if the total number of lines in a line exceeds the specified number exceeds the total threshold) It can be prevented that the guide in the shape is erroneously determined as the selected state.
[0085]
In the first to fifth embodiments, as shown in steps S503 to S508 in FIG. 5 or steps S605 to S610 in FIG. 7, from the top row to the bottom row in the option area, steps S504 to S507 in FIG. Alternatively, the processes in steps S604 to S609 in FIG. 7 are repeated, and in step S509 in FIG. 5 or step 612 in FIG. 7, whether the total number of rows having the three or more line segments and the continuous number are both equal to or greater than the threshold value. If both are determined to be greater than or equal to the threshold value, it is determined in step S512 in FIG. 5 or step 614 in FIG. 7 that the option is circled (that is, selected). However, the process is terminated, but the process is not repeated from the top row to the bottom row, and steps S504 to S507 in FIG. 5 or steps S604 to S609 in FIG. 7 are performed. If the number of rows with three or more line segments described above reaches the threshold for the number of continuations while repeating the process, it is determined that the option is circled (that is, selected). The processing may be terminated.
[0086]
However, in the above configuration, whether or not the option is circled (that is, selected) is determined by the fact that the number of rows having three or more line segments is equal to or greater than the threshold value of the continuous number. Since it determines, it must be an enclosure determination apparatus using the threshold value of a continuous number. That is, it cannot be realized by an enclosure determination device that determines whether or not the option is circled (that is, selected) only by the total number of thresholds.
[0087]
In the case of an enclosure determination device that uses the total number threshold and the continuous number threshold as in the first to fifth embodiments, the processing in steps S504 to S507 in FIG. 5 or steps S604 to S609 in FIG. 7 is repeated. On the way, the threshold value of the continuous number used when determining whether or not the number of rows having the above three or more line segments has reached the threshold value of the continuous number is set as “continuous number threshold value A”, and step S510 in FIG. Alternatively, the configuration may be such that the continuous number threshold used in step 612 of FIG. 7 is “continuous number threshold B”.
[0088]
For example, “threshold number threshold A” is 4 points (1/17 inch = about 17 lines at 300 DPI), and “threshold number threshold B” is 1 point (1/72 inch = about 4 lines at 300 DPI). To do.
[0089]
By adopting the above configuration, recognition accuracy can be improved.
[0090]
In each of the above embodiments, Arabic numerals (“0”, “1”) are shown as an example of a symbol indicating a circled option (an option in a format in which the option corresponding to the symbol is selected by enclosing the symbol in a circle). , “2”, “3”, “4”, “5”, “6”, “7”, “8”, “9”, etc.)
(Especially, using “6”), the symbols indicating the options are not limited to Arabic numerals. For example, “a”, “b”, “c”, “d” , “E”,..., “A”, “B”, “C”, “D”, “E”,..., Or “i”, “b”, “c”, It may be a katakana character such as ... and is not limited to these examples.
[0091]
For example, in each of the above-described embodiments, the total number of lines in which the number of line segments having a length equal to or greater than a specified value in the horizontal rows (201 to 205) illustrated in FIG. Whether or not there is a selection is determined according to whether or not the selection is made. However, the selection determination condition of the present invention is set in a predetermined direction (which may be a horizontal direction, a vertical direction, or another direction). If the number of line segments having a length equal to or greater than a specified value in a row is determined to determine whether or not there is a selection depending on whether or not the continuous number (and / or the total number) of the number of rows equal to or greater than “n” is greater than or equal to a threshold, A symbol in which the number of line segments having a length equal to or longer than a prescribed value in a row in a predetermined direction is “n−1” or “n-2” is continuous (in other words, the number of continuous segments is continuous by the threshold of the number of continuous values). Construct "n-1" or "n-2" curves that intersect a line (and / or a line with a threshold of the total number) with a width greater than a specified value What symbol if the symbol) to prime as alternative symbols, it is possible to determine the selection state.
[0092]
Note that the above symbol is a symbol (a symbol such as “6” shown in FIG. 4) including a row in which the number of line segments having a length equal to or greater than a specified value in the row in the predetermined direction is “n”. Even so, the selection state can be determined because the presence / absence of selection is determined based on whether or not the number of continuations is equal to or greater than a threshold value.
[0093]
In addition, in the “circle selection options” in which the items are selected by enclosing the symbols in circles determined in the above embodiments, the circles surrounding the symbols do not indicate a circle but are closed such as an ellipse or a polygon. Even a figure (closed figure (convex closed figure or concave closed figure)) includes a figure (open figure) partially broken in line segments.
[0094]
However, when the above-mentioned predetermined direction is the horizontal direction, the upper figure and / or the lower part thereof are broken, that is, figures such as “U”, “∩”, “II” (for example, 1201, 1202, 1203, etc. shown in FIG. 12 are included, and when the predetermined direction described above is a vertical direction, the left or / and right part of the figure is broken, that is, “C”, “⊃” “ 2 ”etc. (for example, 1204, 1205, 1206, etc. shown in FIG. 12).
[0095]
As described above, according to each embodiment, without performing registration work for storing an image of a predetermined area of a form as a standard image, and without being aware of the shape of a circle surrounding a symbol, It is possible to determine the selection state of the option of the method of enclosing the symbol in circle.
[0096]
In addition, all the structures which combined one or all of said each embodiment are also contained in this invention.
[0097]
Although one embodiment has been described above, the present invention can take an embodiment as, for example, a system, apparatus, method, program, or recording medium, and specifically includes a plurality of devices. The present invention may be applied to a system including a single device.
[0098]
The configuration of a data processing program that can be read by the symbol enclosing determination apparatus according to the present invention will be described below with reference to the memory map shown in FIG.
[0099]
FIG. 13 is a diagram illustrating a memory map of a recording medium (storage medium) such as the external storage device 104 that stores various data processing programs that can be read by the symbol box determination device according to the present invention.
[0100]
Although not specifically shown, information for managing a program group stored in the recording medium, for example, version information, creator, etc. is also stored, and information depending on the OS on the program reading side, for example, a program is identified and displayed. Icons may also be stored.
[0101]
Further, data depending on various programs is also managed in the directory. In addition, a program for installing various programs in the computer, and a program for decompressing when the program to be installed is compressed may be stored.
[0102]
The functions shown in FIGS. 5, 7, and 10 in this embodiment may be performed by a host computer by a program installed from the outside. In this case, the present invention is applied even when an information group including a program is supplied to the output device from a recording medium such as a CD-ROM, a flash memory, or an FD, or from an external recording medium via a network. Is.
[0103]
As described above, a recording medium recording software program codes for realizing the functions of the above-described embodiments is supplied to a system or apparatus, and a computer (or CPU or MPU) of the system or apparatus stores the recording medium in the recording medium. It goes without saying that the object of the present invention can also be achieved by reading and executing the programmed program code.
[0104]
In this case, the program code itself read from the recording medium realizes the novel function of the present invention, and the recording medium storing the program code constitutes the present invention.
[0105]
Therefore, as long as it has the function of the program, the form of the program such as an object code, a program executed by an interpreter, or script data supplied to the OS is not limited.
[0106]
As a recording medium for supplying the program, for example, a flexible disk, hard disk, optical disk, magneto-optical disk, MO, CD-ROM, CD-R, CD-RW, magnetic tape, nonvolatile memory card, ROM, DVD, etc. Can be used.
[0107]
In this case, the program code itself read from the recording medium realizes the functions of the above-described embodiment, and the recording medium storing the program code constitutes the present invention.
[0108]
As another program supply method, a browser of a client computer is used to connect to a homepage on the Internet, and the computer program itself of the present invention or a compressed file including an automatic installation function is stored on a recording medium such as a hard disk from the homepage. It can also be supplied by downloading. It can also be realized by dividing the program code constituting the program of the present invention into a plurality of files and downloading each file from a different homepage. That is, a WWW server, an ftp server, and the like that allow a plurality of users to download a program file for realizing the functional processing of the present invention on a computer are also included in the claims of the present invention.
[0109]
In addition, the program of the present invention is encrypted, stored on a recording medium such as a CD-ROM, distributed to users, and key information for decryption is downloaded from a homepage via the Internet to users who have cleared predetermined conditions. It is also possible to execute the encrypted program by using the key information and install the program on a computer.
[0110]
Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an OS (operating system) or the like running on the computer based on the instruction of the program code. It goes without saying that a case where the function of the above-described embodiment is realized by performing part or all of the actual processing and the processing is included.
[0111]
Furthermore, after the program code read from the recording medium is written in a memory provided in a function expansion board inserted in the computer or a function expansion unit connected to the computer, the function expansion is performed based on the instruction of the program code. It goes without saying that the case where the CPU or the like provided in the board or the function expansion unit performs part or all of the actual processing and the functions of the above-described embodiments are realized by the processing.
[0112]
Further, the present invention may be applied to a system composed of a plurality of devices or an apparatus composed of a single device. Needless to say, the present invention can be applied to a case where the present invention is achieved by supplying a program to a system or apparatus. In this case, by reading a recording medium storing a program represented by software for achieving the present invention into the system or apparatus, the system or apparatus can enjoy the effects of the present invention. .
[0113]
The present invention is not limited to the above embodiments, and various modifications (including organic combinations of the embodiments) are possible based on the spirit of the present invention, and these are excluded from the scope of the present invention. is not.
[0114]
While various examples and embodiments of the present invention have been shown and described, the spirit and scope of the present invention are not limited to the specific description within this specification.
[0115]
【The invention's effect】
As described above, according to the present invention, a determination target area including a predetermined symbol is cut out from image data, and a line segment in each band area obtained by dividing the cut out area into a band area in a predetermined direction is searched. And, when the number of line segments in the counted band-like area is more than the first specified value, the number of the continuous band-like areas is counted and the counted Since the maximum value of the number of band-like areas is compared with a threshold value based on the resolution of the image data to determine whether or not the symbol is surrounded by a predetermined figure, the image of the predetermined area of the form is stored as a standard image. Therefore, it is possible to determine the selection state of the options of the method of encircling the symbols on the form without performing the registration work for the image and without being aware of the shape of the circle surrounding the symbols. The fact that the registration work of the standard image is not necessary means that even a user who does not have an unfilled form can determine the selection state of the filled form.
[0116]
In addition, even for a form in which a dotted guide is printed around the symbol, both the total number of lines and the number of continuous lines where the number of line segments included in the one-band area exceeds the specified number Therefore, even if the guide portion on the dotted line is a black pixel, the determination is not erroneous and the determination can be made with high accuracy. Note that the determination accuracy can be further improved by removing noise before determining the selection state.
[0117]
Therefore, it is possible to easily determine whether or not a predetermined symbol in a form or the like is surrounded by a predetermined figure such as a circle without storing and managing a predetermined area such as a form as a standard image. There is an effect that the determination accuracy can be remarkably improved.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of a symbol enclosing determination apparatus showing a first embodiment of the present invention.
FIG. 2 is a schematic diagram showing an example of symbols corresponding to options determined by the symbol surrounding determination device of the present invention.
FIG. 3 is a schematic diagram showing an example of symbols corresponding to options determined by the symbol surrounding determination device of the present invention.
FIG. 4 is a schematic diagram showing a case where three lines are included in one line in a symbol corresponding to an option determined by the symbol enclosing determination apparatus of the present invention.
FIG. 5 is a flowchart showing an example of a first control process in the symbol enclosing determination apparatus of the present invention.
FIG. 6 is a schematic diagram showing an example of a determination target region designation method in the symbol surrounding determination device of the present invention.
FIG. 7 is a flowchart showing an example of a second control process in the symbol surrounding determination device of the present invention.
FIG. 8 is a schematic diagram showing an example of an option determination area in the third embodiment of the present invention.
FIG. 9 is a schematic diagram illustrating processing for extracting a region including each option symbol from a determination target region including a plurality of option symbols and determining a selection state according to the third embodiment of the present invention.
FIG. 10 is a flowchart showing an example of a third control process in the symbol enclosing determination apparatus of the present invention.
FIG. 11 is a schematic diagram showing a state in which a dotted guide is printed around an option symbol determined by the symbol surrounding determination device of the present invention.
FIG. 12 is a schematic diagram showing an example of a figure surrounding options in the symbol enclosing determination apparatus of the present invention.
FIG. 13 is a diagram illustrating a memory map of a recording medium that stores various data processing programs that can be read by the symbol box determination device according to the present invention.
[Explanation of symbols]
101 CPU
102 RAM
103 ROM
104 External storage device
105 display
106 keyboard
107 pointing device
108 Image Scanner

Claims (12)

In a symbol enclosing determination device for recognizing whether or not a predetermined symbol included in image data is surrounded by a predetermined figure,
A specifying means for specifying a determination target region including the predetermined symbol from the image data;
First counting means for searching in each band area obtained by dividing the determination target area specified by the specifying means into band areas in a predetermined direction and counting the number of line segments;
A second counting unit that counts the number of continuous band-like areas when the number of line-segments counted by the first counting means is continuous;
A determination unit that determines whether or not the symbol is surrounded by a predetermined graphic by comparing the number of strip-like regions counted by the second counting unit with a first threshold;
A symbol encircling determination device comprising: The symbol surrounding determination device according to claim 1, further comprising first calculation means for calculating the first threshold based on a resolution of the image data. And further comprising third counting means for counting the total number of rows in which the number of line segments counted by the first counting means is equal to or greater than a first specified value,
The determination means includes a comparison result between the number of band-like areas counted by the second counting means and the first threshold value, a total number of band-like areas counted by the third counting means, and a second threshold value. The symbol surrounding determination device according to claim 1, wherein it is determined whether or not the symbol is surrounded by a predetermined figure based on the comparison result. The symbol surrounding determination device according to claim 3, further comprising second calculation means for calculating the second threshold based on a resolution of the image data. Storage means for storing the maximum value of the number of band-like areas counted by the second counting means;
The symbol enclosing determination apparatus according to any one of claims 1 to 4, wherein the determination means compares the maximum value of the number of belt-shaped areas stored by the storage means with a first threshold value. The symbol surrounding determination device according to any one of claims 1 to 5, further comprising a noise removing unit that performs noise removal on the determination target region identified by the identifying unit. The predetermined symbol is a curve of the “first specified value−1” or the “first specified value−2” curve that intersects the band-like region that is continuous by the number of the first thresholds with a width equal to or greater than a predetermined value. The symbol enclosing determination device according to claim 1, wherein the symbol enclosing symbol is a symbol. The symbol surrounding determination device according to claim 1, wherein the predetermined symbol is an Arabic numeral. The symbol surrounding determination device according to claim 1, wherein the first specified value is “3” or “5”. In a symbol surrounding determination method in an information processing apparatus for recognizing whether or not a predetermined symbol included in image data is surrounded by a predetermined figure,
A first counting step in which a first counting unit searches each band-like area obtained by dividing the determination target area including the predetermined symbol in the image data into band-like areas in a predetermined direction and counts the number of line segments;
A second counting unit that counts the number of continuous band-like areas when the band-like areas whose line segments counted in the first counting step are equal to or greater than the first specified value are continuous; Counting process,
A determination step for determining whether or not the symbol is surrounded by a predetermined figure by comparing the number of band-shaped regions counted in the second counting step with a first threshold;
A symbol encircling determination method comprising: A non-transitory computer-readable storage medium storing a program for causing an information processing apparatus to execute the symbol enclosing determination method according to claim 10. Computer readable recording medium recording the program according to claim 1 1.

Images