JPH096917A - Isolation point removing method for document image - Google Patents

Abstract

PURPOSE: To provide an isolation point removing method which can discriminate and remove isolation points with efficiency. CONSTITUTION: A histogram of black pixels in a set character area is generated (b) and on the basis of this histogram, the run length in each white pixel section and the run length in each black pixel section are counted respectively, section by section. Then a threshold value 1 for the run length of the black pixel sections, a threshold value 2 for the run length of the white pixel sections, and a threshold value 3 for the number of pixel arrays from a reference end are set respectively (e). Then when the run length of a black pixel section is less than the threshold value 1 while the run length of the white pixel section adjoining to the black pixel section on the opposite side from the reference end is larger than the threshold value 2 and the total run length from the reference end to the tail of the black pixel section is less than the threshold value 3, the black pixel section is decided as an isolation point to be removed (f).

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention is applicable, for example, when an isolated point other than a regular document image is included in a character area frame set in a document image read by an image reading device.
The present invention relates to a method of identifying and removing this isolated point.

[0002]

2. Description of the Related Art An example of a conventional method for removing isolated points in a document image is described in the document: Japanese Patent Laid-Open No. 233879/1993. According to the method described in this document, the contour length of the pixel group is used to identify whether or not the pixel group in the read image data is an isolated point to be removed. Then, when the contour length of the pixel group is shorter than the set isolated pixel contour length, the pixel group is removed as an isolated point.

[0003]

However, in the method described in the above-mentioned document, in order to obtain the contour length of the pixel group, it is necessary to determine in which direction the contour is connected from the pixel of interest in the pixel group. I have to. For this reason,
It is necessary to perform a black-and-white examination of all pixels in the eight surrounding directions adjacent to the pixel of interest. Further, it is necessary to sequentially trace the contours of the isolated pixels and perform the same investigation for all the pixels having the contours connected to each other.

Further, when a pixel group that originally forms a part of a character is read as an individual pixel group apart from the main body of the character due to blurring of the character image, etc., the isolated point is determined by the contour length. , This pixel group may be removed as an isolated point.

Therefore, it has been desired to realize a method capable of efficiently identifying and removing isolated points.

[0006]

According to the method for removing isolated points of a document image according to this application, a character area frame surrounding a character image is set in the document image, and each pixel column in the character area frame is set. , A histogram in which the number of black pixels in the pixel row is used as a frequency, and the number of pixel rows in a white pixel section in which one or more pixel rows having a frequency of 0 in this histogram are continuous (hereinafter, also referred to as run length) ) And the number of pixel rows (run length) in a black pixel section in which one or more pixel rows having a frequency of 1 or more are consecutively counted for each white pixel section and each black pixel section, and With the pixel row on one side of the frame as the reference end, the threshold value 1 for the number of pixel rows in the black pixel section, the threshold value 2 for the number of pixel rows in the white pixel section, and the threshold value 3 for the number of pixel rows from the reference end. , And the number of pixel columns in the black pixel section The number of pixel columns in the white pixel section that is equal to or less than the threshold value 1 and is adjacent to the black pixel section on the other side of the black pixel section from the reference end is the threshold value 2 or more, and the number of pixel rows in the black pixel section and the reference value If the sum of the number of pixel columns from the edge to the black pixel section is less than or equal to the threshold value 3, an isolated point from which the black pixel section and the black pixel section from the reference edge to the black pixel section should be removed It is characterized in that the isolated point is removed by changing the reference end to a position where the black pixel section determined to be the isolated point is excluded from the character area frame. Incidentally, in the present invention, the characters of the document image include symbols.

[0007]

According to the method for removing isolated points of a document image according to this application, a histogram of black pixels in a set character region is created, and the run length of the white pixel section and the black pixel section are created based on this histogram. The run length is counted for each white pixel section and each black pixel section. Then, an isolated point to be removed is identified by comparing these run lengths with threshold values 1 to 3.

The threshold value 1 is generally set to utilize the fact that the isolated point has a small pixel group and the run length of the isolated point is shorter than the run length of the regular character. The run length of this threshold value 1 may be based on, for example, the minimum value of the character width. The run length of the black pixel section being shorter than the threshold value 1 is a requirement for identifying the black pixel as an isolated point.

By the way, if a short run length is uniformly removed as an isolated point, an isolated point or a hiragana character which is originally a part of the document image but has been separated from the body of the character due to faintness etc. There is a risk that an isolated point (one image) which is an image forming a character such as “ka” but distant from the other image of the character may be removed as an isolated point to be removed.

Therefore, in the present invention, in order to leave an isolated point that should not be removed, a threshold value 2 relating to the run length length of the white pixel section is set. The threshold 2 generally utilizes that the nearest isolated point of the regular document image is likely to be a part of the character body. Therefore, the run length of the threshold 2 may be based on, for example, the maximum value of the intervals between the regular characters. Then, one requirement for identifying that the run length of the white pixel section adjacent to the isolated point on the far side of the isolated point from the reference end is longer than the threshold value 2 is an isolated point to be removed. And

By the way, there are some characters such as "i" and "c" in which each image constituting a character is present apart from each other. Hereinafter, such a character is referred to as a space character. The run length of each stroke of the separated characters is usually shorter than the threshold value 1. Moreover, the run length of the white pixel section between the spaced character and the next character is typically longer than the threshold of 2. Therefore, if the isolated point is determined using only the threshold 1 and the threshold 2, such a separated character is likely to be identified as a plurality of isolated points that are to be removed being close to each other.

Therefore, according to the present invention, the threshold value 3 relating to the number of pixel columns from the reference end (total run length) is set in order to leave the separated characters. The threshold value 3 is such that the total run length of the separated characters is also a certain value or more (usually about one character, the run length of the combined black pixel sections of the separated characters and the run length of the white pixel section between the black pixel sections of the separated characters). (Above) is used. Therefore, the run length of the threshold value 3 may be set, for example, based on the minimum value of the character width. Further, the run length of the threshold value 3 needs to be longer than the run length of the threshold value 1. Then, this total run length is represented as a total run length of the run length of the black pixel section of interest and the run lengths of the black pixel section and the white pixel section included between the reference end and the black pixel section of interest. Then, the fact that the total run length is shorter than the threshold value 3 is one requirement for identifying all black pixel sections from the reference end to the black pixel section as isolated points to be removed.

Therefore, according to the isolated point removing method of the present invention, it is possible to easily identify the isolated point to be removed by comparing the three thresholds of the threshold values 1 to 3 with the run length.
Further, by setting the threshold value 2, it is possible to leave an isolated point which should not be removed and which is caused by blurring or the like. Further, by setting the threshold value 3, it is possible to reduce the risk of accidentally removing a separated character such as “C”.
Therefore, it is possible to efficiently identify and remove the isolated points to be removed, and it is particularly suitable for removing the isolated points in the peripheral portion of the character area surrounded by the character area frame.

[0014]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of a document image isolated point removing method according to the present invention will be described below with reference to the drawings. It should be noted that the drawings to be referred to are merely schematic illustrations of respective procedures to the extent that these inventions can be understood. Therefore, the present invention is not limited to the illustrated examples.

(Embodiment 1) In Embodiment 1, an example of a method for removing isolated points in a horizontally written document image will be described. FIG.
FIG. 9 shows a flowchart of a schematic procedure of the isolated point removing method in the first embodiment.

First, the procedure for setting the character area frame shown in FIG. 1A will be described. In this embodiment, a binarized document image is read using an image reader, for example. Then, using a conventionally known method, a character area frame surrounding the character image is set in the document image.

Then, the character area frame is set by using a conventionally known table analysis method. Therefore, first, the document image is divided into a plurality of tabular rectangular portions, and the coordinates of each pixel are x, y.
Expressed in an axis-orthogonal coordinate system. Note that each side of the rectangular portion is parallel to the x or y coordinate. Then, the connected component of the white pixels in each rectangular portion is obtained. Next, the black pixel existing inside the connected component of the white pixel is determined as a character area (cell). Next, x and y of the black pixel determined to be a cell
Is a rectangular character area in which the (x, y) coordinates of the maximum value set and the minimum value set are respectively obtained, and the coordinates of the minimum value set of x and y and the maximum value set are diagonal points. Frame 1
Set to 0. The area surrounded by the character area frame 10 becomes a character area 12.

In this way, the character area frame 1 is included in the document image.
A state in which 0 is set is shown in FIG. In this embodiment, the character area frame 10 that encloses the horizontally written character image 14 of "vehicle cost" is set, but an unnecessary isolated point 16 is erroneously included at the left end in the character area frame.

Next, the procedure for creating the histogram shown in FIG. 1B will be described. After the character area frame is set, for each pixel row in this character area frame, a histogram is created with the number of black pixels in the pixel row as the frequency. In this embodiment, the pixels arranged in the vertical direction perpendicular to the horizontally written row are set as one pixel column. Therefore, the number of pixels in one pixel column is the number of pixels at the row height.

FIG. 2B shows a histogram of black pixels created in the first embodiment. In addition to the histogram corresponding to each character image, a histogram corresponding to the isolated point 16 at the left end of the character image area 12 is created.

Next, the procedure for creating the run length shown in FIG. 1C and the setting of the reference end shown in FIG. 1D will be described.

In creating the run length, the number of pixel rows (run length) in the white pixel section in which one or more pixel rows whose histogram frequency is 0 is continuous, and this frequency is 1
The number of pixel rows (run length) in the black pixel section in which one or more pixel rows are continuous is counted for each white pixel section and each black pixel section.

In the character area frame setting method used in this embodiment, both ends of the character area frame are black pixel sections. And
In principle, black pixel sections and white pixel sections are alternately arranged. However, if the document image has only one character or one isolated point, 1
It may be only one black pixel section.

Further, in this embodiment, the pixel row on the left side of the character area frame 10 is used as the reference edge 18. The reference end 1
It is not necessary to determine 8 after setting the run length, but it is also possible to determine 8 after setting the character area frame. Therefore, in the flowchart of FIG. 1, the process of setting the reference end in (d) may be performed at any stage after (b) and before (f). In this embodiment, the reference end 1
Numbers are sequentially assigned to each black pixel section and each white pixel section from the side closer to 8.

Here, for convenience, the black pixel section is designated as "black".
Notated as "n" or "black n (m)". Where n
Is a natural number indicating that the black pixel section is the nth from the reference end 18 side, and m indicates the run length of the black pixel section, that is, the number of pixel columns included in the black pixel section. It is a natural number. For example, black 1 (8) indicates that the run length of the black pixel section closest to the reference end is 8 pixel columns. Similarly, white 1 is 172, blac
k 2 is 49, white 2 is 155, black 3 is 47, whit
e 3 is 154, and black 4 is 48 pixel columns.

Next, the threshold setting shown in FIG. 1E will be described. As a threshold value used as a reference for determining an isolated point, a threshold value 1 for the number of pixel rows in the black pixel section, a threshold value 2 for the number of pixel rows in the white pixel section, and a threshold value 3 for the number of pixel rows from the reference end. Are set respectively. In this embodiment, the threshold value 1 is 18 (pixels) based on the width of the character.
And set. In addition, the threshold value 2 is 1 based on the character spacing.
Set to 2 (pixels). Further, the threshold value 3 is set to 24 (pixels) which is a value larger than the threshold value 1 on the basis of the width of the character.

Next, with respect to the isolated point determination shown in FIG. 1F and the isolated point removal shown in FIG.
explain. FIG. 3 shows a flowchart of the determination and removal of isolated points in the first embodiment.

In the present invention, the reference end 18 in the character area frame is
An isolated point between the character image and the character image closest to the reference end 18 is identified. Therefore, if the character image is identified, the determination of the isolated point is completed, and if the character image is not detected, the determination / removal of the isolated point is continued in principle. Therefore, in this embodiment, in order to determine the end of the process of determining / removing an isolated point, the process is terminated when any one of the following conditions (1) to (4) is satisfied. First, when the determination is made for all the black pixels in the character area frame (for example, this corresponds to the case where the character area frame includes only isolated points), the process ends. In addition, during the black pixel section to determine whether it is an isolated point,
If the frequency of the black pixels is equal to or greater than ½ of the row, the process ends. In this case, the black pixel section is identified as a character image regardless of the run length of the black pixel section. Also, if the run length of the black pixel section to be determined is larger than the threshold value 1, the black pixel section is identified as a character image, and the process ends.

Next, the procedure of determination / removal will be described with reference to the flowchart of FIG. In the flowchart of FIG. 3, the run length of the i-th black pixel section from the reference end side and its run length are expressed as “black [i]”,
Further, the run length of the i-th white pixel section from the reference end is expressed as “white [i]”.

In this embodiment, first, the initial setting of the argument i and the like is performed in (a). In this initial setting,
"First = 1", "end = number of black [i]",
Set “i = 1”. For example, as shown in (c) of FIG. 2, when there are four black pixel sections from black 1 to black 4, the number of end = black [i] = 4.

Next, in (b), it is determined whether or not the above termination condition is met. That is, the process ends when “i = end?” And i = 4. On the other hand, when i ≠ 4 (actually i = 1 to 3), the procedure proceeds to the next step (c).

In (c), it is determined whether or not the above termination condition is met. That is, a pixel column included in the black pixel section black [i] to be determined (also simply referred to as a column)
If there is a column in which the frequency of black pixels is ½ or more of the row height, the process ends. On the other hand, if it does not exist, proceed to step (d).

In (d), it is determined whether or not the above termination condition is met. That is, it is determined whether the black pixel section to be determined is a character image or an isolated point.

When a determination is made for black 1 (8) shown in FIG. 2, the threshold value 1 = 18, and thus 8 <18.
Therefore, black 1 does not correspond to the end condition, and if the run length is equal to or less than the threshold value 1 and is an isolated point (however, it is not necessarily an isolated point to be removed), the process proceeds to the next step (e).

In (e), threshold 2 and threshold 3 are used to determine whether or not this isolated point is an isolated point to be removed.

First, it is determined whether or not the run length of the white pixel section adjacent to the black pixel section on the other side of the black pixel section from the reference end is equal to or greater than the threshold value 2.

When black 1 (8) shown in FIG. 2 is judged, it is judged whether the run length of white 1 (172) next to black 1 is equal to or greater than the threshold value 2. In this case, white 18172) threshold 2 = 12, so
172> 12.

Then, it is determined whether or not the sum of the number of pixel columns in the black pixel section and the number of pixel rows from the reference end 18 to the black pixel section is less than or equal to the threshold value 3.

When black 1 (8) shown in FIG. 2 is judged, black 1 (8) <threshold value 3 (= 24).

Therefore, the black pixel section to be judged and the black pixel section between the reference end 18 and the black pixel section are judged as isolated points to be removed. In this case, blac
Since there are no other black pixels between k 1 and the reference edge 18,
Only black 1 (8) is determined to be an isolated point to be removed, and the procedure proceeds to the next step (f).

It should be noted that white 1 <threshold value 2 or black 1
> If the threshold value is 3, it is determined that black 1 is not an isolated point that should be removed independently, and the argument i is incremented by 1 in (g) to determine the next black 2 (b).
Return to step.

In the procedure (f), the isolated point is removed by changing the reference end 18 to a position where the black pixel section determined to be the isolated point is excluded from the character area frame. Here, a new reference end 18a is set to the pixel row closest to the first reference end 18 of black 2. as a result,
From the first reference end 18 to the first reference end 1 of white 1
From 8 to the furthest pixel row, ie black 1 and white
1 is removed. The character area frame 10a set by removing the isolated points is shown in FIG.

Hereinafter, among the pixel rows in the black pixel section or the white pixel section, the pixel row closest to the reference end is referred to as "head edge", and the pixel row farthest from the reference end is referred to as "tail edge".

Next, in order to determine the black pixel rows after black 2, the first is incremented by 1 in (h), the argument i is incremented by 1 in (t), and the procedure returns to (b).

In this way, the reference end 18 of the character area frame 10 initially set and the regular character image (here, “car”) in the character area frame 10 and closest to the reference end 18 are formed. It is possible to remove the isolated points 16 existing between and to be removed. Note that, for example, in the first embodiment, when there is an isolated point on the right side of the character image “Cost”, the pixel row on the right side of the character area frame 10 is used as a reference end, and the procedure is the same as that of the first embodiment. Points can be removed. Therefore, in the case of a horizontally written character image, it is desirable to set the reference end on each of the left and right sides of the character area frame and remove the isolated points.

(Embodiment 2) In Embodiment 2, an example of a method for removing isolated points from a horizontally written document image will be described. In the second embodiment, the character area frame 20 is set as in the first embodiment. Here, as shown in FIG. 4A, “total”
Although the character area frame 20 surrounding the horizontally written character image 24 is set, the right end of the horizontal bar of the 8th stroke of the character “total” is separated from the main body of the character due to fading and the isolated point 26
It has become.

Next, as in the case of the first embodiment, as shown in FIG.
The histogram shown in (B) is created.

Then, based on this histogram, FIG.
The run length shown in (C) is created. In the second embodiment, the pixel row at the right end of the character area frame is the reference end 28. Then, from the side close to the reference end 28, numbers are sequentially assigned to each black pixel section and each white pixel section. Here, black 1 (6), white 1 (3), black 2
(7), white 2 (11), black 3 (19), white
Create run lengths of 3 (356) and black 4 (45).

Next, according to the flowchart of FIG. 3 referred to in the first embodiment, the process of determining and removing isolated points is performed.
Also in the second embodiment, the same threshold values 1 to 3 as those in the first embodiment are used.
To use.

The procedures from (start) to (a), (b) and (c) in FIG. 3 are the same as in FIG.

In (d), when black 1 (6) is determined, black 1 (6) <threshold 1 (= 18). Therefore, black 1 (6) is determined as an isolated point (however, it is not limited to an isolated point to be removed). Then, the procedure proceeds to the next step (e).

In (e), it is determined whether the isolated point is an isolated point to be removed by using the threshold 2 and the threshold 3.

First, black 1 (6) as seen from the reference end 28.
It is determined whether the run length of white 1 adjacent to the black pixel section on the other side is equal to or greater than the threshold value 2. white
Since 1 (3) <threshold value 2 (= 12), black 1
It is determined that (6) is not an isolated point to be removed.

In order to make a determination for the next black 2, the argument i is incremented by 1 in (g), and the procedure returns to (b). Since i = 2 ≠ 4 = end at this stage, the process does not end with the determination of (b) and proceeds to the next procedure of (c).

In the pixel columns included in black 2, there are columns in which the frequency of black pixels is ½ or more of the row height. Therefore,
In (c), black 2 is determined to be a character image.
And the black pixel section after black 2 is also a character image,
The process ends. Therefore, in the second embodiment, the character area frame 2
0 is unchanged and can leave an isolated point caused by a blur.

(Third Embodiment) In a third embodiment, an example of a method for removing isolated points in a horizontally written document image will be described. In the third embodiment as well, the character area frame 30 is set as in the first embodiment. Here, as shown in FIG.
Although the character area frame 30 surrounding the horizontally written character image 34 of "0,465" is set, the first isolated point 36a and the second isolated point 36b that are close to each other exist near the left end of the character area frame 30. There is.

Next, as in the case of Embodiment 1, FIG.
The histogram shown in (B) is created.

Then, based on this histogram, FIG.
The run length shown in (C) is created. In the third embodiment, the pixel row at the left end of the character area frame 30 is the (first) reference end 38. Then, from the side close to the reference end 38, numbers are sequentially assigned to each black pixel section and each white pixel section. Here, black 1 (8), white 1 (5),
black 2 (9), white 2 (125), black 3 (2
Create run lengths such as 1).

Next, according to the flowchart of FIG. 3 referred to in the first embodiment, the process of determining and removing isolated points is performed.
Also in the third embodiment, the same threshold values 1 to 3 as those in the first embodiment
To use.

The procedure from (start) to (a), (b) and (c) in FIG. 3 is the same as that in FIG.

Next, in (d), the first isolated point 16a
Judgment about black 1 (8) of black 1 (8)
<Threshold 1 (= 18). Therefore, black 1 (6)
Is determined to be an isolated point (but not necessarily an isolated point to be removed). Then, the procedure proceeds to the next step (e).

In (e), threshold 2 and threshold 3 are used to determine whether or not this isolated point is an isolated point to be removed.

First, black 1 (6) viewed from the reference end 38
It is determined whether the run length of white 1 adjacent to the black pixel section on the other side is equal to or greater than the threshold value 2. white
1 (5) <threshold value 2 (= 12), so black 1
It is determined that (6) is not an isolated point to be removed.

In order to make a determination for the next black 2, the argument i is incremented by 1 in (g), and the procedure returns to (b). Since i = 2 ≠ 9 = end at this stage, the process does not end with the determination of (b) and proceeds to the next step of (c).

In (c), the blac of the second isolated point 16b
Since the frequency of k 2 is ½ or less of the row height, the procedure proceeds to the next step (d).

In (d), when the second isolated point 16b is judged, black 2 (9) <threshold value 1 (= 18). Therefore, black 2 (9) is determined to be an isolated point (however, it is not limited to the isolated point to be removed). Then, the procedure proceeds to the next step (e).

In (e), it is determined whether or not this isolated point is an isolated point to be removed using the threshold values 2 and 3.

First, as seen from the reference end 38, black 2 (9)
It is determined whether or not the run length of white 2 adjacent to the black pixel section on the other side is equal to or greater than the threshold value 2. white
2 (125)> threshold value 2 (= 12), so black 2
(9) satisfies requirement 1, which is an isolated point to be removed.

Further, it is determined whether or not the run length from the reference point 38 to the tail end of black 2 is less than or equal to the threshold value 3. 8 + 5 + 9 = 22, which is the sum of the run lengths of black 1, white 1 and black 2, <threshold 3 (= 2
4). Therefore, therefore, the black pixel section (bla) to be determined is determined from the determination results for the threshold values 1 to 3.
ck2) and the black pixel section (bla) from the reference end 38.
The black pixel section (black 1) up to ck 2) is determined as an isolated point to be removed. Then, the procedure proceeds to the next step (f).

In step (f), the isolated point is removed by changing the reference end 38 to a position where the black pixel section determined to be the isolated point is excluded from the character area frame 30. Here, the new reference end 38a is set at the position of the head end of black 3. As a result, whit from the first reference end 38
To the tail of e 2, ie black 1, white 1, black 2
And white 2 are removed. First and second isolated points 3
A new character area frame 30a set by removing 6a and 36b is shown in FIG.

Next, in order to determine the black pixel row after black 3, the first is incremented by 1 in (h), the argument i is incremented by 1 in (g), and the procedure returns to (b). .

At this stage, i = 3. Therefore, the determination in (b) does not end the process, and the process proceeds to the next (c).

In (c), since the frequency of black 3 is less than 1/2 of the row height, the process proceeds to the next step (d).

In (d), when black 3 (21) is determined, black 3 (21)> threshold 1 (= 18). Therefore, black 3 (18) is determined to be a character image, and the process ends.

(Embodiment 4) In Embodiment 4, an example of a method for removing isolated points in a vertically written document image will be described. Also in the fourth embodiment, the character area frame 40 is set in the same manner as in the first embodiment. Here, as shown in FIG. 6A, a character area frame 40 that surrounds a vertically written character image 44 called "Introduction".
However, the isolated point 46 exists near the upper end of the character area frame 40.

Next, as in the first embodiment, the histogram of black pixels shown in FIG. 6B is created.

Then, based on this histogram, FIG.
The run length shown in (C) is created. In the fourth embodiment, the pixel row at the upper end of the character area frame 40 is the reference end 48. Then, from the side close to the reference end 48, a number is sequentially assigned to each black pixel section and each white pixel section.
Here, black 1 (9), white 1 (36), black
2 (40), white 2 (8), black 3 (42), whit
e 3 (7), black 4 (41), white 4 (8) and
Create a run length of black 5 (38).

Next, according to the flowchart of FIG. 3 referred to in the first embodiment, the process of determining and removing isolated points is performed.
Also in Example 4, the same threshold value 1 and threshold value 2 as in Example 1
And threshold 3 is used.

Since the procedure from (start) to (a), (b) and (c) in FIG. 3 is the same as that in FIG. 1, its explanation is omitted.

Next, in (d), the blac of the isolated point 46 is
When determination is made for k 1 (8), black 1 (8) <threshold value 1 (= 18). Therefore, black 1 (6) is determined as an isolated point (however, it is not limited to an isolated point to be removed). Then, the procedure proceeds to the next step (e).

In (e), it is determined whether the isolated point 46 is an isolated point to be removed by using the threshold 2 and the threshold 3.

First, as seen from the reference end 48, black 1 (9)
It is determined whether the run length of white 2 adjacent to black 1 on the other side of is equal to or greater than the threshold value 2. white 2
Since (36)> threshold value 2 (= 12), black 1
(9) satisfies one of the requirements for the threshold value 2 to be an isolated point to be removed.

Furthermore, it is determined whether or not the run length from the reference point 48 to the tail of black 1 is less than or equal to the threshold value 3. black 1 (9) <threshold value 3 (= 24), so bl
ack 1 meets one of the requirements for threshold 3 to be an isolated point to remove. Therefore, the black pixel section (blac
k 1) and the reference pixel 48 to the black pixel section (black
The black pixel section up to 1) (none in this case) is determined as an isolated point to be removed. Then, the procedure proceeds to the next step (f).

In the procedure (f), the new reference edge 48a is set at a position where the black pixel section determined to be the isolated point is excluded from the character area frame 40.
Remove 6. Here, the reference end 48a is moved to the head end of black 2. As a result, from the first reference edge 48 white
Up to the tail of 1, i.e. black 1 and white 1 are removed. The character area frame 40a set by removing the isolated points is shown in FIG.

Next, in order to determine the black pixel rows after black 2, the first is incremented by 1 in (h), the argument i is incremented by 1 in (t), and the procedure returns to (b).

At this stage, i = 2. Therefore, the determination in (b) does not end the process, and the process proceeds to the next (c).

In (c), since the frequency of black 2 is less than 1/2 of the row height, the process proceeds to the next step (d).

In (d), when black 2 (40) is determined, black 3 (40)> threshold 1 (= 18). Therefore, black 2 (40) is determined to be a character image, and the process ends.

In the above-described embodiments, the present invention has been described with respect to an example in which the present invention is configured under specific conditions, but the present invention can be modified and modified in many ways. For example, in the above-described first embodiment, the isolated points on the left and right sides of the regular document image are removed when the isolated points of the horizontally written document image are removed. It is also possible to remove isolated points. In that case, as in the case of vertical writing, columns extending in the horizontal direction may be set, a histogram may be created for each column, and isolated points may be identified as in the first embodiment.

Further, in the vertically written document image of the fourth embodiment, it is possible to remove the left and right isolated points of the regular document image.

Further, in the above-mentioned embodiment, an example in which the run lengths of the threshold values 1 to 3 are fixed to fixed values has been described, but in the present invention, each threshold value can be arbitrarily changed.

In the above-described embodiment, the table analysis method is used to set the character area frame.
The method of setting the character area frame is not limited to this, and any known method can be used.

Further, in the above-mentioned embodiment, the histogram is created for the pixel row composed of the pixels arranged in the row of the character image in the vertical direction to remove the isolated points.
For example, a histogram may be created for a pixel row composed of pixels arranged in the row direction to remove isolated points. In this case, in the case of horizontal writing, it is possible to remove the isolated points at the upper and lower sides of the line and in the character area frame. In the case of vertical writing, isolated points on the left and right of the line in the character area can be removed.

Further, in the above-described embodiment, the character area frame is set so that the sections at both ends of the character area frame are black pixel sections, but the sections at both ends may be white pixel sections.

In addition, in the above-described embodiment, when the isolated point is deleted, a new reference end is set at the position of the head end of the black pixel section which is determined to end the process. For example, a new reference point may be set on the other side of the isolated point to be removed from the reference point before removal and in the white pixel section adjacent to the isolated point.

[0096]

According to the isolated point removing method of the present invention, it is possible to easily identify the isolated point to be removed by comparing the three thresholds of the thresholds 1 to 3 with the run length. Also,
By setting the threshold value 2, it is possible to leave an isolated point that is caused by blurring or the like and should not be removed. Further, by setting the threshold value 3, it is less likely that a separated character such as “C” is erroneously removed. As described above, according to the isolated point removing method of the present invention, it is possible to efficiently identify and remove an isolated point to be removed. In particular, the isolated point in the peripheral portion of the character area surrounded by the character area frame is removed. It is suitable for the removal of

[Brief description of drawings]

FIG. 1 is a flowchart of a first embodiment.

FIG. 2 is a diagram for explaining the first embodiment.

FIG. 3 is a flowchart of isolated point determination and removal according to the first exemplary embodiment.

FIG. 4 is a diagram for explaining the second embodiment.

FIG. 5 is a diagram for explaining the third embodiment.

FIG. 6 is a diagram for explaining Example 4;

[Explanation of symbols]

 10, 20, 30, 40: (initial) character area frame 10a, 30a, 40a: (new) character area frame 12, 22, 32, 42: character area 14, 24, 34, 44: character image 16, 26 , 46: isolated point 18, 28, 38, 48: (initial) reference end 18a, 38a, 48a: (new) reference end 36a: first isolated point 36b: second isolated point

 ─────────────────────────────────────────────────── ─── Continuation of front page (72) Inventor Makoto Torikoshi 1-7-12 Toranomon, Minato-ku, Tokyo Oki Electric Industry Co., Ltd.

Claims (1)

[Claims] 1. A text area frame surrounding a text image is set in a document image, and a histogram is created for each pixel row in the text area frame with the number of black pixels in the pixel row as a frequency. The number of pixel rows (run length) in a white pixel section in which one or more pixel rows having a frequency of 0 in the histogram are continuous, and the pixels in a black pixel section in which one or more pixel rows having a frequency of 1 or more are continuous The number of columns (run length) is counted for each white pixel section and each black pixel section, and the pixel row on one side of the character area frame is used as a reference end, and the threshold value for the number of pixel rows in the black pixel section is set. 1, a threshold value 2 for the number of pixel rows in the white pixel section and a threshold value 3 for the number of pixel rows from the reference end are set, and the number of pixel rows in the black pixel section is less than or equal to the threshold value 1 and the reference end is set. Seen from the black pixel section on the other side of the black pixel section In the pixel column number of the adjacent white pixel interval the threshold 2 or more,
When the sum of the number of pixel columns in the black pixel section and the number of pixel rows from the reference end to the black pixel section is equal to or less than the threshold value 3, the black pixel section and the black pixel section from the reference end Is determined as an isolated point to be removed, and the reference point is changed to a position where the black pixel section determined to be the isolated point is excluded from the character area frame. A method for removing an isolated point in a document image, which is characterized by removing it.