JPH09269944A - Picture processor and method therefor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To execute desired ordering in plural group-designated composition paragraphs and to improve the convenience of a user by providing respective processes for dividing an inputted picture into prescribed areas and ordering the divided prescribed areas. SOLUTION: An input part 101 inputs picture data and CPU 102 controls a device and operates respective parts. A storage part 103 stores a control program and various kinds of data. An output part 104 outputs an arithmetic processing result, a picture processing result and picture data, etc. An ordering part 105 orders the paragraph and headline of a composition. An area dividing part 106 indicates the whole area processing and is constituted of a picture thinning part 201 and a labeling part 202, etc. Then, even when an article, for example, a newspaper article, etc., is constituted by plural text paragraphs, group designition is executed by a mouse, etc., so that ordering is correctly executed without executing mixing with another article and the flow of the text composition is not disturbed.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus such as an OCR (optical character recognition) apparatus, a copying machine, a facsimile apparatus and the like, and a method for extracting character areas from an input image and ordering them. It is a thing.

[0002]

2. Description of the Related Art In a conventional image processing apparatus, as a means for ordering characters in a document, in the case of vertical writing, the order is from right to left, and similarly in the vertical direction, from top to bottom. There is something to add.

[0003]

However, in the above-mentioned conventional example, for a manuscript in which a plurality of text paragraphs form a unit of one article such as a newspaper article, the grouping of the article unit is conventionally performed by using information such as a separator. Since the grouping was done automatically by the above, there is an error in the grouping judgment for manuscripts for which it is difficult to judge the grouping of articles, and it is necessary to order consecutively in the same article originally. However, there was a problem that the order of the articles and the order were mixed, and as a result, the flow of the text of the text was disturbed.

The present invention has been made to solve the above problems, and provides an image processing apparatus and method in which a plurality of text paragraphs designated by a group are ordered in a desired manner to improve user convenience. The purpose is to do.

[0005]

In order to achieve the above object, an image processing method of the present invention comprises an input step of inputting an image, and an area dividing step of dividing the image input by the input step into predetermined areas. And an ordering step of ordering the predetermined areas divided by the area dividing step,
The region dividing step is characterized by dividing into a plurality of sentence paragraphs.

In order to achieve the above object, the image processing apparatus according to the present invention comprises an input means for inputting an image, an area dividing means for dividing the image input by the input means into predetermined areas, and the area. Ordering means for ordering the predetermined areas divided by the dividing means, wherein the area dividing means divides into a plurality of sentence paragraphs.

In such a configuration, an operation is performed so that an image is input, the input image is divided into a plurality of sentence paragraphs, and the plurality of divided sentence paragraphs are ordered.

[0008]

Embodiments of the present invention will be described below in detail with reference to the drawings.

FIG. 1 is a block diagram showing the arrangement of an image processing apparatus according to this embodiment. In the figure, 101
Is an input unit for image data. Reference numeral 102 denotes an arithmetic processing unit (CPU) that controls the device and performs arithmetic operations of each unit. A storage unit 103 stores a control program and various data. An output unit 104 outputs a calculation processing result, an image processing result, image data, and the like. 105 is a paragraph of a sentence,
This is an ordering unit that orders headings, and details thereof will be described later. An area dividing unit 106 indicates the entire area dividing process.

In the above configuration, the area dividing unit 10 is first
The detailed configuration of 6 will be described. An image thinning unit 201 thins an input image. The logical sum of vertical m dots and horizontal n dots 201 is added to the input image to newly set m × n pixels to 1.
Thin out to pixels. Reference numeral 202 denotes a labeling unit that labels the thinned pixels and at the same time creates initial rectangular data, and adds labels to the black pixels of the image line by line,
Pixels that are continuous vertically, horizontally, and diagonally are given the same label, and are simultaneously shaped into a rectangle. Reference numeral 203 denotes a separator or the like detection unit for detecting a separator, a table, a figure, or the like,
The width, height, area, and number of pixels per area, that is, the rectangle corresponding to the character portion (text) using the pixel density,
Distinguish between rectangles corresponding to figures or photographs, rectangles corresponding to tables, rectangles corresponding to separators, and the like. 204 is vertical writing
A set direction detecting unit for detecting a set direction of a sentence such as horizontal writing, and estimates a vertical writing sentence or a horizontal writing sentence by comparing the heights of the widths of the rectangles corresponding to the character portions (texts). 205
Is a headline detection unit for detecting a headline, and detects the headline using the set direction and the character size. Reference numeral 206 denotes a rectangle merger, which merges rectangles by using a virtual rectangle that is an extension of the size of the original rectangle.

FIG. 2 is a flow chart showing image processing in the present embodiment, and a control program for executing this processing is stored in the storage unit 103. Step S201 First, the original image is input from the image input unit 101. Also,
When an image is input, it is determined whether or not it is multi-valued and converted into a binary image, so that even if the input image is a multi-valued image such as a color image, the region division processing is possible. In step S202 and thereafter, area division is performed by area division 106, and sentences, separators, figures, etc. are extracted from the image. This step S2
In 02, the image thinning unit 201 newly thins out m × n pixels to one pixel by taking a logical sum of vertical m dots and horizontal n dots in the original image. Where mx of the original image
If even one dot has a black pixel in the n image, the thinned image is black.

In the image thinning-out process, if the number of pixels of the input image is small enough not to impair the processing speed, the image thinning-out process can be omitted. Step S203 Next, in the labeling unit 202, a label is added to the black pixels of the above-described thinned image row by row, and consecutive pixels in the vertical, horizontal, and diagonal directions are given the same label, and at the same time, a rectangular shape is modeled. To go.

Taking FIG. 3 as an example, the first detected pixel A is labeled 1, and the coordinates (Xa,
Ya) is the start and end points of the rectangle, the number of pixels is 1, and the same label 1 as the pixel is added to the rectangular label for distinguishing the rectangle, and the above data is stored in the storage unit 103 as rectangular data as shown in FIG. Remember.

Next, a label 2 is attached to a pixel B having no continuous pixel in the left direction (there is no continuous pixel from the top because it is in the first row), and the coordinate 2 of this pixel B (Xb, Yb).
Is the starting point and the ending point of the rectangle, the number of pixels is 1, and the same label 2 as the pixel is added to the rectangular label for distinguishing the rectangle, and the above data is also rectangular data as shown in FIG.
Store in 03.

As described above, when the labeling of the first line is completed, the process moves to the second line.

The first pixel C in the second row is the pixel A of label 1.
Since it is continuous from the top, pixel label 1 is added, and the number of pixels is added to the rectangular data of rectangular label 1 by 1 to make a total of 2 pixels, the rectangular label remains 1 and the rectangular coordinate is only the end point. Is updated from (Xa, Ya) to (Xa, Yc) (the coordinates of the starting point do not change).

Since the next pixel D is continuous from the left with the pixel C, the label 1 is added, and the number of pixels is added to the rectangular data of the rectangular label 1 by 1 to make a total of 3 pixels, and the rectangular label remains unchanged 1. As it is, the rectangular coordinates are only for the end point (Xa, Y
Update from (c) to (Xd, Yc) (the Y coordinate of the end point does not change). At this time, the pixel D is diagonally continuous with the pixel B and is continuous from the pixel C, so the label of the pixel B is updated from label 2 to label 1, and the rectangular label 1
The number of pixels of the rectangular label 2 is added to the rectangular data of 4 to make a total of 4 pixels, the rectangular label remains unchanged at 1, and the rectangular coordinates include only the end points so as to include all the pixels A, B, C and D. Update from (Xd, Yc) to (Xb, Yd). Regarding the rectangular data of the rectangular label 2, the rectangular label is set to 0 and invalidated.

When the second line is completed as described above, the process moves to the third line.

Since the first pixel E on the third row is diagonally continuous with the C pixel, pixel label 1 is added, and the number of pixels is increased by 1 to the rectangular data of rectangular label 1 to give a total of 5 pixels.
The rectangular label remains unchanged at 1, and the rectangular coordinates are updated from the viewpoint (Xa, Ya) to (Xe, Ya) and the end point from (Xb, Yd) to (Xb, Ye). That is, the rectangular data of FIG. 4 on the storage unit 103 at this time is
The rectangular label is 1, the viewpoint coordinates are (Xe, Ya), the end point coordinates are (Xb, Ye), the pixel label is 1 and the number of pixels is 5.

In the same manner, labeling and rectangular tracing are performed on all thinned pixels. Step S204 Next, after the above-described labeling and tracing of rectangles, the separator or the like detecting unit 203 extracts rectangles corresponding to character portions (text), rectangles corresponding to figures or photographs, tables, rectangles corresponding to separators, and the like. , Width W, height H of the above rectangle,
The area S and the number of pixels with respect to the area, that is, the pixel density D (which can be easily obtained by calculation using these rectangular data) are used for discrimination. The details of this processing will be described below with reference to the flowchart shown in FIG.

First, as shown in FIG. 4, the stored rectangle is searched (step S501), and if the rectangle is not the end (NO in step S502), the separator and the like are distinguished. First, in the separator, the width W is equal to or smaller than the threshold Tw1 and the height H is equal to or larger than twice the threshold Tw of the width W (step S503).
YES), or if the width W is larger than the threshold value Tw1 and the height H is three times the threshold value Tw of the width W or more (YES in step S504), the storage unit 103 as a vertically long separator.
The upper rectangular label is unified as -3, and the pixel label forming the rectangle holds the current label number as it is in addition to the rectangular label (step S514).

Similarly, the above-mentioned width and height are interchanged (steps S505 and S506), and if applicable (YES), the rectangular label is changed to -3 as the vertical separator (step S514).

Next, as shown in FIG. 6, the above steps S503 to S506 result in a NO determination, and the pixel density D
Is less than or equal to the threshold Td1 (YES in step S507)
Changes the rectangular label to -3 by considering it as a deformed separator of a key shape or the like (step S514).

If step S507 is NO but the area S is larger than the threshold value Ts1 (step S507).
If the pixel density D is less than the threshold value Td2 (YES in step S509), the rectangle label regarded as a table is changed to -4 (YES in step S508). If the pixel density D is greater than or equal to the threshold value Td2, the rectangular label regarded as a figure or a photograph is changed to -5 (step S516).

On the other hand, when the area S is less than the threshold Ts1 and more than the threshold Ts2 (YES in step S510), the pixel density D is more than the threshold Td3 (YE in step S511).
The rectangle of S) or the rectangle in which both the width W and the height H are equal to or more than the threshold Tw4 and the pixel density D is equal to or more than the threshold Td5 (YES in step S513) are regarded as figures or photographs, and the rectangle label is set to -5. Change (step S516).

Further, when the area S is less than or equal to the threshold Ts1 and greater than or equal to the threshold Ts2 (YES in step S510),
The pixel density D is less than the threshold value Td4 (YE in step S512
The rectangle of (S) is regarded as a table and the rectangle label is updated to -4 (step S515).

As described above, a rectangle corresponding to a figure or photograph, a table, etc., a rectangle corresponding to a separator, etc. are detected,
The remaining rectangle is used as the body (character portion) and the rectangle label is made the same as the pixel label (step S51).
7). Note that FIG. 6 shows the relationship between the above-mentioned threshold value in the area S and the pixel density D and the division of the separator and the like.

Further, in the detection of the separator and the like, it is possible to further classify the area attribute by distinguishing the rectangular labels by the difference in the length and width of the separator, the difference in the threshold value when obtaining figures, tables and the like. Is. Further, when only an image having a specific attribute is input from the beginning, such as only a sentence, the above-described detection processing of the separator or the like can be omitted. Step S205 Next, the set direction detecting unit 204 detects the set direction of sentences such as vertical writing and horizontal writing. This processing will be described with reference to the flowchart shown in FIG.

First, in the case of a horizontally written sentence, the rectangle remaining as the body tends to be a horizontally long rectangle in which pixels thinned out in the horizontal direction are continuous, and in the case of a vertically written sentence, the rectangle remaining as the body becomes vertically long. Cheap. Therefore, the assembly direction detection unit 204
In, the average value of the width W and height H of the rectangle of the text is calculated (step S701), and when the average width W is larger than the average height h (YES in step S702), the chapter is regarded as the one with many horizontal lines and the average. The height h is set to the character size of one character (step S703). If the average height h is larger than the average width W (NO in step S702), the average width w is regarded as a sentence with many vertical writings and the average width w is set to one character size (step S710).

Next, as shown in FIG. 8, a rectangular histogram is taken in the direction opposite to the set direction (steps S704, S).
711), the place of the threshold value Tk or less is set as a paragraph break based on the shape of the peripheral distribution (steps S705 and S712).
Then, the paragraph is searched (steps S707 and S71).
4) A rectangular histogram is taken for each paragraph in the same direction as the set direction (steps S708 and S715), and from the shape of the marginal distribution, the continuous length of black pixels is set as the character size of the characters in that paragraph, and the white pixel The length of continuation is detected as the row pitch (steps S709 and S716). The above detection process is repeated until the paragraph is completed (steps S706 and S71).
3).

In the detection of the set direction, the average value,
Instead of obtaining the average height, it is possible to substitute by obtaining each maximum value. Further, if the set direction is confirmed again for each paragraph, it is possible to accurately process a document in which vertical writing and horizontal writing are mixed. Then, if only the text of a fixed set direction is input from the beginning, this detection process can be replaced by setting the set direction to a fixed value. Step S206 Next, the headlines detecting unit 205 detects headlines from the set direction and the character size. As shown in the flowchart of FIG. 9, taking the case of vertical writing as an example (step S901), a rectangle is searched (step S902), and from the body rectangle (YES in step S904), the width W of the rectangle is a character. A rectangle larger than the threshold value Tm1 times the size w is detected as a candidate for a header rectangle (step S905).
Then, when the height H of the rectangle is smaller than the threshold value Tm2 times the character size w (YES in step S906), the horizontally written characters are considered to be continuous and are regarded as headings (step S908).

Further, since the rectangles regarded as the headings from the size of the rectangles as described above may include those in which the characters of the body are combined, the distance between the body rectangle and the heading rectangle is a threshold value. Closer than T1 (step S907
If YES), the heading is corrected to the text (step S909).

Further, among the body rectangles remaining by the above-described processing, the body rectangles having no body and heading rectangles within the character size w are set as isolated rectangles (steps S910 to S913).

In the heading detection, if only an image having no heading is input from the beginning, this detection processing can be omitted. Step S207 Next, the rectangle merging unit 206 merges the rectangles corresponding to the texts that are present in a scattered manner without any relation and the rectangles of the headings.

Considering the combination of the rectangle A1 and the rectangle B shown in FIG. 10, P with respect to the X direction with respect to the rectangle A1.
Consider a virtual rectangle A1 'that is expanded by Py in the x and Y directions, search A1' for a rectangle that is in contact with or around it, and if it is in contact with a rectangle B, Rectangle A1 and rectangle B are merged to newly merge rectangle A2
Is created and stored by updating the rectangular data of the rectangle A1, and the data of the rectangle B is invalidated. However, at this time, Px,
Py is a value obtained from the character size and the line pitch, and when a rectangle formed by merging rectangles comes into contact with a figure, table, separator, etc., the merging itself is invalidated and the original rectangle remains as it is. .

In this way, the headlines are first merged, and then the body rectangles are merged. At this time, when merging texts with each other, avoid contact with not only figures, tables, or separators but also headings. If they come in contact with headings, the merger itself is invalidated and the original rectangle Leave it alone.

Further, in this merged rectangle, as shown in FIG. 11, when a rectangle such as a separator is contacted, it is further confirmed whether or not it is also in contact with a thinned pixel.
If they are not touching, then a merged image can also be used to handle tilted images.

Further, in the case of an image having a small number of pixels such that the image thinning process can be omitted, this merging process can be omitted.

As described above, after thinning the input image, the data is converted into rectangular data by using the labeling, and the character area,
By dividing into areas such as figures, photographs, tables, separators, headings, etc., the processing time can be shortened, the storage area can be downsized, and the complicated area configuration can be performed without changing existing electronic parts, circuits, etc. This has an effect of improving the division accuracy. Step S208 Next, the ordering unit 105 orders the headings and body paragraphs. Hereinafter, the ordering will be described in detail. FIG. 12 is a flowchart showing the ordering process in the embodiment.

FIG. 13 shows sentences and separators extracted by the area division. In the figure, reference numeral 1306 is a handwritten document image input from a scanner or the like. Thirteen
01 to 1305 are text areas extracted by area division. ◎ Step S1201 First, a group is designated by the mouse. For example, 1301 and 1302 shown in FIG. 13 are set as one group g1, and 1304, 1305, and 1303 are designated as a group g2 (see FIG. 14). In this case, by dragging the original image 1306 on the original image 1306 with a mouse or the like and designating a rectangular area so that each of the areas 1301 and 1302 is partially included, the area 1301,
1302 is designated as one group. Similarly, 1304, 1305, and 1303 are also designated. Step S1202 The area ID in the group, the barycentric coordinates of the area, and the diagonal coordinates are stored in the storage unit 103. Here, FIG. 15 is a diagram showing the barycentric coordinates (Jnx, Jny) and the diagonal point (Lnx, Lny)-(Rnx, Rny) for the area of the text paragraph. Here, the barycentric coordinates are obtained by the following formula.

Jnx = (Lnx + Rnx) / 2 Jny = (Lny + Rny) / 2 ⋅ Step S1203 When the group designation is completed, the process proceeds to step S1204. If there is still an area to be designated as a group, step S1
Execute 201. ◎ Step S1204 Branch depending on whether or not horizontal writing. In this example, since it is written vertically, the process proceeds to step S1208. Step S1208 The barycentric coordinates are compared within the group, and the sentence paragraphs are ordered for the vertically written sentence. As the ordering method, in the Cartesian coordinate system with the lower left corner as the origin coordinate, the Y coordinate in the barycentric coordinate having a one-to-one correspondence with each region ID stored in the storage unit in step S1202 described above is larger,
If the Y-coordinates are the same, the X-coordinates are ordered in descending order. That is, the coordinates are ordered from the upper right coordinates, and a natural number indicating the order is stored in the storage unit so as to correspond to each area ID. ◎ Step S1209 Step S12 until all the groups are ordered.
08 is executed. Here, the ordered result is shown in FIG.
It becomes as shown in. Within the group g1, consecutive orders 1 and 2 are attached, and within the group g2, consecutive orders 3, 4, and 5 are attached. Step S1210 The text paragraphs for the vertically written text are ordered in the text paragraph areas that are not designated as a group. The ordering method is the same as step S1208. ◎ Step S1205 The barycentric coordinates are compared within the group, and the sentence paragraphs are ordered for the horizontally written sentence. As the ordering method, in the Cartesian coordinate system with the lower left corner as the origin coordinate, the Y coordinate in the barycentric coordinate having a one-to-one correspondence with each region ID stored in the storage unit in step S1202 described above is larger,
If the Y coordinates are the same, the smaller X coordinates are ordered. That is, the coordinates are ordered from the upper left coordinate, and the natural number indicating the order is stored in the storage unit so as to correspond to each area ID. ◎ Step S1206 Step S12 until all of the groups are ordered.
Execute 05. (Step S1207) The text paragraphs are ordered for the horizontally written text in the text paragraph areas that are not designated as a group. The ordering method is the same as step S1205.

Thus, step S208 is completed. Step S209 Finally, the rectangular data of various areas obtained by the above processing is output from the output unit 104 to the outside together with the image data.

Further, referring to the rectangular data of various areas,
It is also possible to output only the image data of the necessary area, which allows the storage area to be further reduced and the processing time to be further shortened.

As described above, according to the first embodiment, even if an article is composed of a plurality of text paragraphs, the articles are properly ordered without being mixed with other articles and the flow of the text of the text is kept. Since there is no disturbance, the user does not have to make corrections.

[Other Embodiments] Next, other embodiments of the present invention will be described in detail.

The configuration of the character recognition device in another embodiment is the same as that of the embodiment shown in FIG.

FIG. 17 shows the step S120 shown in FIG.
7 is a flowchart showing a process in which the group designation method using the mouse 1 is improved.

First, in step S1701, the range of text paragraphs is specified and the group is specified by dragging the mouse. FIG. 18 is a diagram showing a sentence and a separator extracted from an input document by area division as an example. FIG.
FIG. 19 is a diagram showing a result of group designation of the text of FIG. 18 in step S1201. In this example, 1901 and 1902 are in the same group g1. Step S17
In 01, 1901 is designated as a group as shown in FIG. Let the group be g1.

Next, if there is another block to be added to the group g1 in step S1702, step S1703.
Proceed to. If not, the process proceeds to step S1202. In the example of FIG. 19, 1903 is also added to the group g1, so the flow advances to step S1703 to drag the mouse while pressing the SHIFT key to specify the range of 1903.

Further, FIG. 20 shows step S1 shown in FIG.
20 is a flowchart showing a process in which the mouse group designation method of 201 is further improved.

First, in step S2001, by dragging or clicking the mouse, a range of text paragraphs is designated and a group is designated. 18 and 19 are used as examples of sentences and separators extracted from the input document by area division. In the case of this manuscript example, by dragging the mouse,
1901 and 1902 are designated as a range and are set to the same group g1.

Next, if there is another block to be added to the group g1 in step S2002, step S2003.
Proceed to. If not, the process proceeds to step S1202. In the example of FIG. 19, 1903 is also added to the group g1, so the process advances to step S2003, the mouse is clicked while the SHIFT key is held down, and the range of 1903 is designated.

As described above, also in the other embodiments,
It is possible to obtain the same operation and effect as those of the above-described embodiment.

The present invention may be applied to a system composed of a plurality of devices "such as a host computer, an interface and a printer" or to an apparatus composed of a single device such as "a copying machine". . Further, it goes without saying that the present invention can be applied to the case where it is implemented by supplying a program to a system or an apparatus. In this case, the storage medium storing the program according to the present invention constitutes the present invention. Then, by reading the program into the system or device from the storage medium, the system or device operates in a predetermined manner.

[0055]

As described above, according to the present invention, by specifying a group with a mouse or the like, even if an article is composed of a plurality of text paragraphs, such as a newspaper article, it does not mix with other articles. Since the ordering is done correctly and the flow of sentences in the text is not disturbed, the user's troublesome correction can be eliminated, the usability can be greatly improved, and the processing time including correction can be shortened. Has the effect of.

[0056]

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of an image processing apparatus according to the present embodiment.

FIG. 2 is a flowchart showing image processing according to the present embodiment.

FIG. 3 is a diagram for explaining the labeling process shown in FIG.

FIG. 4 is a diagram showing a structure of rectangular data stored in a storage unit.

5 is a flowchart showing a detection process of the separator and the like shown in FIG.

FIG. 6 is a diagram showing division of rectangular (region) attributes by density and area.

FIG. 7 is a flowchart showing a detection process of a set direction shown in FIG.

FIG. 8 is a diagram for explaining a paragraph detection process.

9 is a flowchart showing a process of detecting the headings shown in FIG.

10 is a flowchart showing a process of merging the rectangles shown in FIG.

FIG. 11 is a diagram for explaining a merging process of separator rectangles.

12 is a flowchart showing the ordering process shown in FIG.

FIG. 13 is a diagram showing a sentence paragraph area extracted by the area division processing.

FIG. 14 is a diagram showing a sentence paragraph area designated by a group with a mouse.

FIG. 15 is a diagram showing barycentric coordinates and diagonal point coordinates.

FIG. 16 is a diagram showing sentence paragraph areas ordered by an ordering process.

FIG. 17 is a flowchart showing a group designation process in another embodiment.

FIG. 18 is a diagram showing a sentence paragraph area extracted by the area division processing.

FIG. 19 is a diagram showing a sentence paragraph area designated by a group with a mouse.

FIG. 20 is a flowchart showing a group designation process in another embodiment.

[Explanation of symbols]

 101 input unit 102 arithmetic processing unit (CPU) 103 storage unit 104 output unit 105 ordering unit 106 region dividing unit 201 image thinning unit 202 labeling unit 203 separator detection unit 204 group direction detection unit 205 heading type detection unit 206 rectangular merged unit

Claims (6)

[Claims] 1. Input means for inputting an image, area dividing means for dividing the image input by the input means into predetermined areas, and ordering means for ordering the predetermined areas divided by the area dividing means. An image processing apparatus, wherein the area dividing unit divides into a plurality of sentence paragraphs. 2. The image processing apparatus according to claim 1, wherein the ordering unit specifies a group of a plurality of divided text paragraphs and performs ordering within the group. 3. The image processing apparatus according to claim 2, wherein the group designation is designated by a pointing device. 4. An input step of inputting an image, an area dividing step of dividing the image input by the input step into predetermined areas, and an ordering step of ordering the predetermined areas divided by the area dividing step. The image processing method, wherein the area dividing step includes dividing into a plurality of sentence paragraphs. 5. The image processing method according to claim 4, wherein the ordering step specifies a group of a plurality of divided text paragraphs and performs ordering within the group. 6. The image processing method according to claim 5, wherein the group designation is designated by a pointing device.