JPH0830725A - Image processing apparatus and method - Google Patents

Abstract

PURPOSE:To perform the area judgement of image data at a high speed while suppressing a memory amount. CONSTITUTION:The image data inputted from an input part 1 are supplied to an area division part 105 and the picture elements (reduced picture elements) of low resolution are extracted in the area division part 105 first by ORing the respective picture elements of the area of (m)X(n) picture elements in input pictures. As a result, the memory amount for judging the kind of the images practically becomes 1/(mXn). Then, the picture elements of the low resolution are successively generated and the kinds of the images of the respective positions (areas) of the image data are judged by them.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION The present invention relates to an image processing apparatus and method,
More specifically, the present invention relates to an image processing apparatus and method for determining the type of image of each area in input image data.

[0002]

2. Description of the Related Art In a device such as an optical character recognition (OCR) device, a copying machine, or a facsimile, a region such as a character region, a figure, or a table in an input image is processed in order to perform the processing accurately. Will need to be split.

As the area dividing means, one using a method of analyzing the Fourier spectrum of the input image and dividing it into various areas, such as a spectrum analysis method, or Japanese Patent Laid-Open No. 64-158.
As disclosed in Japanese Patent No. 89, there is a method using a method in which projections in the vertical and horizontal directions are alternately repeated to divide an area from information on peripheral distribution.

As a labeling means, there is a method using a method of tracing the contour line of continuous pixels.

[0005]

However, in any of the above-mentioned methods, a large amount of time is spent on the arithmetic processing and the processing is performed on the pixels of the image, so that the storage area becomes large in scale, and a complicated area structure is formed. However, there is a problem that the division accuracy for the image is low.

Further, there is a problem that the division accuracy deteriorates even when the resolution of the input image is low, and conversely, when the resolution is high, the number of pixels increases and the processing time such as labeling and the storage area increase. There was a point.

[0007]

[Means for Solving the Problems] and

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and an object of the present invention is to provide an image processing apparatus and method capable of performing area determination of image data at high speed while suppressing the amount of memory. Is.

In order to solve this problem, for example, the image processing apparatus of the present invention has the following configuration. That is, an image processing apparatus for determining the type of each area of given image data, comprising an extracting means for extracting one pixel of low resolution from an m × n pixel area in the image data, and a pixel of low resolution. An area discriminating unit that discriminates an image type region from a continuous spread, and a discriminating unit that determines the type of the region from the region information discriminated by the region discriminating unit.

According to a preferred embodiment of the present invention, it is desirable that the m and n have larger values as the resolution of input image data is higher. As a result, the weight of low-resolution pixels can be made substantially constant regardless of the resolution of image data, and image determination can be performed in almost the same environment.

Further, when at least one significant pixel exists in the m × n pixels, the extracting means preferably extracts a low-resolution pixel for the m × n pixels as a significant pixel. Accordingly, when at least one black pixel exists in the m × n pixel group, the low-resolution pixel can be set as a black pixel, and thus it can be used for image area determination.

Further, it is preferable that the extracting means includes a calculating means for calculating a logical sum of dot states of m × n pixels. This makes it possible to obtain low-resolution pixels with an extremely simple configuration or processing.

Further, it is desirable that the area discriminating means discriminates a rectangle inscribed with respect to a continuous spread of low-resolution pixels as an area. This is because characters, photographs, tables, etc. are generally developed for each rectangular area, and it is possible to cope with this favorably and at a high speed by simple processing.

Further, the recording area discriminating means is means for obtaining a significant pixel position of each low resolution in line units in which an m × n pixel group in given image data is one pixel, and in the main scanning direction. A memory for storing the start position of consecutive significant low-resolution pixels and the number of consecutive pixels for each scanning line, and storing predetermined discrimination information when there is no significant low-resolution pixel in the line of interest. Means, a searching means for searching a significant low resolution two-dimensional continuous area according to the contents stored in the storage means, and a unique label for the continuous low resolution pixel group obtained by the search. And a means for obtaining the coordinates of the rectangular area inscribed in the pixel group based on the coordinate position of the pixel group of the unique label. This is because only the portion where no significant pixel exists is stored, and it is possible to suppress the amount of memory consumption accordingly.

Further, the judging means can judge the type of the area according to the vertical and horizontal sizes of the area judged by the area judging means and the ratio of the number of pixels of significant low resolution in the area. desirable. This makes it possible to determine each area with a personality.

[0015]

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

FIG. 1 shows an example of the configuration of the image processing apparatus in the embodiment. In the figure, 101 is an input unit for inputting image data, which is an image scanner. However, the present invention is not limited to this, and may be, for example, an interface for inputting image data from a host device (host computer) or receiving a facsimile. The point is that it only needs to input image data.

Reference numeral 102 denotes an arithmetic processing unit (hereinafter referred to as CPU) that controls the apparatus and performs arithmetic operations for processing of each unit, and 103 is a storage unit that stores the control program of the CPU 102 and various data. An output unit 104 outputs the calculation processing result, the image processing result, and the image data.

Reference numeral 105 denotes an area dividing unit showing the entire area dividing processing, which has the following configuration.

Reference numeral 106 reduces the input image to data and
An image reduced data conversion unit 107 is a labeling unit that labels reduced pixel data and simultaneously creates initial rectangular data. Reference numeral 108 denotes a basic attribute determination unit that detects a separator, a table, a figure, and the like. Reference numeral 109 denotes a set direction detection unit that detects a set direction of a sentence such as vertical writing or horizontal writing. Reference numeral 110 denotes a headline detection unit that detects headlines. 111 is a rectangular merged part.

FIG. 2 is a flow chart showing image processing in the image processing apparatus of this embodiment. A control program for executing this processing is stored in the storage unit 103.

The operation of the above configuration will be described below with reference to the flowchart.

1) Description of Step S201 First, an original image is input from the image input unit 101.

2) Description of Step S202 Next, in the image reduced data conversion unit 106, the resolution of the input image is Rdpi (dpi = dots / inch).
In the above case, the logical sum of vertical m dots and horizontal n dots in 1 dot units is taken, and the logical sum result is set as a new 1 pixel (reduced pixel). The resolution of the input image data is Rd.
If it is less than pi, the logical sum of dot units of vertical p dots and horizontal q dots is taken, and the logical sum result is newly set to 1 pixel (reduced pixel) (however, m> p, n> q). Here, the reason that the area size is changed according to the resolution is that the latter pixel is more important in meaning when compared with one pixel at high resolution and one pixel at low resolution. Therefore, when the resolution of the input image data varies,
It is desirable to divide it into multiple stages instead of the above two stages. Incidentally, the determination of the resolution of the input image may be instructed from an operation panel (not shown) provided outside, or may be an image data generation source (host computer or the like).
May add a resolution specification command to the header part and interpret this command.

When the above logical sum processing is performed, if even one dot has a black pixel in the m × n area or the p × q area of the input image, the reduced pixel becomes black (here). The term "black" is used for convenience.)

The reduced pixels obtained as described above are treated as one group of reduced pixels continuous in the main scanning direction, and the X coordinate at which the black pixel starts and the number of black pixels are stored as reduced pixel data (FIG. 5). ).

Pixel data of a group of reduced black pixels existing in the main scanning direction are linked in order from the left, and the address of the leftmost pixel data is stored in the reduced pixel row header.

Further, each reduced pixel row header is linked so that it can be accessed as a series of reduced pixel data.

That is, the header of each reduced pixel row stores the address (pointer) at which the next block of black pixels in that row is stored, and also the address of the header of the next row. ing.

The above is the processing of the image reduced data conversion unit 106.

3) Description of Step S203 Next, the processing contents of the labeling unit 107 will be described.

A label is added to the black pixels of the reduced image by referring to the reduced pixel data line by line, and
The same label is attached to diagonally continuous pixel data,
Simultaneously model the rectangle. However, at this time, since the continuity in the horizontal direction is previously changed by the reduced pixel data, it is only necessary to inspect the continuity in the vertical and diagonal directions.

Taking FIG. 3 as an example, when the reduced pixel header of the first row (row composed of reduced pixels) is referenced and the first reduced pixel data is read from the reduced pixel data start address, pixel A is included. The pixel data will be referred to.

The label 1 is attached to the pixel data including the pixel A that is detected first, and the coordinates (Xa, Y
a) 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 rectangle label for distinguishing the rectangle, and the above data is stored in the storage unit as rectangle data (FIG. 4).

Next, when the next reduced pixel data is referred to by the next reduced pixel data address, the pixel data including the pixel B is referred to, and it is clear that the pixel data is different from the pixel A in the left direction because the pixel data is different. (Since it is the first row, of course, there are no continuous pixels from the top). Label 2 is attached to the pixel data including the pixel B, the coordinates (Xb, Yb) of the pixel B are used as the start point and the end point of the rectangle, the number of pixels is 1, and the rectangular label for distinguishing the rectangle has the same label as the pixel. 2 is added and the above data is also stored in the storage unit as rectangular data (FIG. 4).

When the labeling of the first line is completed as described above, the process moves to the second line.

When the reduced pixel header of the second row is referred to and the first reduced pixel data is read from the reduced pixel data start address, the data from pixel C to pixel D is referred to. Since the pixel data including the first pixel C in the second row is continuous from the top with the pixel data including the pixel A with label 1, pixel label 1 is added, and the number of pixels is added to the rectangular data with rectangular label 1 by 1. The total number of pixels is 2 pixels, the rectangle label remains unchanged at 1, and only the end point of the rectangle coordinate is (Xa, Y
Update from (a) to (Xd, Yc) (coordinates of pixel D) (the coordinates of the start point do not change).

At the same time, the pixel data including the pixel D is diagonally continuous with the pixel data including the pixel B.
The label of the pixel data including is changed from label 2 to label 1. Then, for the rectangular data of rectangular label 1,
The number of pixels of the rectangular label 2 is added to make a total of 4 pixels, the rectangular label remains unchanged at 1, and the rectangular coordinates are pixels A, B, C,
Only the end point is updated from (Xd, Yc) to (Xb, Yd) so as to include all D. Then, the rectangular data of the rectangular label 2 is invalidated by setting the rectangular label to 0.

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

When the reduced pixel row header of the third row is referred to and the first reduced pixel data is read from the reduced pixel data start address, the data of the pixel E is referred to. Since the pixel data including the first pixel E in the third row is diagonally continuous with the pixel data including the pixel C, the pixel label 1 is added, and the number of pixels is added to the rectangular data of the rectangular label 1 to calculate the total. The number of pixels becomes 5 pixels, the rectangular label remains unchanged at 1, and the rectangular coordinates are updated from the starting point of Xa, Ya) to (Xe, Ya) and the ending point of (Xb, Yd) to (Xb, Ye).

In the same manner, labeling and rectangular tracing are performed on all the reduced pixels. As a result, the same label is attached to the reduced black pixel groups that are continuous vertically and horizontally and diagonally, and the coordinate data of the upper left corner of the rectangle that inscribes the reduced pixel groups represented by the same label, the coordinate data of the lower right corner, and The reduced number of black pixels will be obtained.

4) Description of Step S204 This process is performed by the basic attribute determination unit 108. After tracing the above labeling and rectangles, the basic attribute determination unit 108 determines whether each rectangle is a rectangle corresponding to a text, a rectangle corresponding to a figure or a photograph, a table, or a rectangle corresponding to a separator. , Width W, height H, area S of the labeled rectangle, the number of black pixels for the area,
That is, the pixel density D (these are easily obtained by calculation using rectangular data) is used for the discrimination. The term "separator" as used herein means a delimiter portion of an image, for example, a text portion and a photograph portion, or a line (for example, a line that delimits a text portion in a newspaper or the like) for demarcating text portions. Hereinafter, a description will be given according to the flowchart of FIG.
A CPU (not shown) is provided inside the basic attribute determination unit 108.
Therefore, the CPU proceeds with the processing according to the program corresponding to the flowchart of FIG.

In the separator, the width W is not more than the threshold Tw1 and the height H is not less than twice the threshold Tw of the width W (S60 in FIG. 6).
3) or the width W is larger than the threshold Tw1 and the height H
Is equal to or greater than the threshold value Tw three times the width W (S604 in FIG. 6), the rectangular label is unified as “-3” as the vertically long separator, and the pixel labels forming the rectangle are held as they are separately from the rectangular label (FIG. 6 of S614).

Also, in the case where the width and the height are interchanged, the rectangular label is changed to "-3" as the horizontally long separator in the same manner as above (S605 and S606 in FIG. 6).

Further, as shown in FIG. 7, when the pixel density D is less than or equal to the threshold value Td1 (S607 in FIG. 6), the rectangular label is changed to "-3" by considering it as a deformed separator such as a key-shaped one (FIG. 6). S614).

When the area S is larger than the threshold value Ts1 (S608 in FIG. 6) and the pixel density D is less than the threshold value Td2 (S609 in FIG. 6), it is regarded as a table and the rectangular label is changed to "-4". If the pixel density D is equal to or higher than the threshold value Td2 (S615 in FIG. 6), the rectangle label is changed to “−5” by regarding it as a figure or a photograph (S616 in FIG. 6).

That is, in general, a table is composed of line segments and has a large area compared to characters. Moreover, since the area is almost white, the rectangular density has a small value. On the other hand, figures, photographs and the like have a higher pixel density than those in the table.

When the area S is less than or equal to the threshold Ts1 and greater than or equal to the threshold Ts2 (S610 in FIG. 6), the pixel density D
Is a threshold value Td3 or more (S611 in FIG. 6), or the width W and height H are both threshold value Tw4 or more and the pixel density D is Td.
When the number is 5 or more (S613 in FIG. 6), the rectangle is regarded as a figure or a photograph, and the rectangle label is changed to "-5".

Further, when the area S is less than or equal to the threshold Ts1 and greater than or equal to the threshold Ts2 (S610 in FIG. 6), the rectangle having the pixel density D less than the threshold Td4 (S612 in FIG. 6) is regarded as a table and the rectangle label is "-4". To “” (S615 in FIG. 6).

As described above, a rectangle corresponding to a figure, a photograph, a table, etc., a rectangle corresponding to a separator, etc. are detected,
The remaining rectangle is used as the text and the rectangle label is made the same as it is (because the sign is positive, it can be easily distinguished from a table etc.) and the pixel label (S617 of FIG. 6).

5) Description of Step S205 Next, the operation processing contents of the assembly direction detecting unit 109 will be described with reference to the flowchart of FIG. A CPU and a memory that stores a program corresponding to the flowchart of FIG.

In the case of a horizontally written sentence, the rectangle remaining as the body tends to become a horizontally long rectangle in which reduced black pixels are continuous in the horizontal direction, and in the case of a vertically written sentence, the rectangle remaining as the body tends to become vertically long. .

Therefore, the average value of the width W and the height H of the rectangle of the text is calculated (S801 in FIG. 8), and if the average width w is larger than the average height h, it is regarded as a chapter with many horizontal writing and the average height h is set. 1
Set to the character size of the character (S802, S80 in FIG. 8
3). On the contrary, when the average height h is larger than the average width w, it is regarded as a sentence with many vertical writings and the average height w is set to the character size of one character (S802 and S810 in FIG. 8).

Next, a histogram of the reduced black pixels of each body rectangle is taken in the opposite direction to the set direction (S8 in FIG. 8).
04), the location of the threshold value Tk or less is set as a paragraph break based on the shape of the peripheral distribution (see S805 and S812 in FIG. 8 and FIG. 9). Also, for each step, a rectangular histogram is taken in the same direction as the set direction (808, S815 in FIG. 8), and from the shape of the marginal distribution, the continuous length of black pixels is determined by the character size (height) of the characters in the paragraph. Size) and the continuous length of white pixels is detected as a row pitch (S809, S816 in FIG. 8 and FIG. 8).

6) Description of Step S206 Next, the procedure for detecting the headings based on the set direction and the character size in the headings detection unit 110 will be described with reference to the flowchart of FIG. It should be noted that the case where the text is written vertically will be described here, and the case where the text is written horizontally will not be described, but from the following description, the processing procedure in the case of horizontal writing can be easily guessed.

First, from the main rectangle, a rectangle whose width W is larger than the character size w by a threshold value Tm1 times or more is detected as a candidate for a heading rectangle (S1005 in FIG. 10).

Furthermore, when the height H of the rectangle is smaller than Tm2 times the character size w (S1006 in FIG. 10),
Since there may be a case where the horizontally written characters are continuous, if the distance between the body rectangle and the heading rectangle is shorter than the threshold T1 (S1007 in FIG. 10), the headline is corrected to the body (S1009 in FIG. 10).

Further, among the body rectangles remaining by the above-mentioned processing, a body body and a headline type rectangle in the range of the character size w are regarded as isolated rectangles as headings (S1010 to S1013 in FIG. 10).

As described above, in the case of horizontal writing,
It can be easily conceived because it is only rotated by 90 degrees in the above processing.

7) Description of Step S207 Next, the processing contents of the rectangular merger 111 will be described.

In this processing, the rectangles corresponding to the main text that have been separated and have no relation to each other and the rectangles of the headings are merged.

As an example in FIG. 11, consider merging rectangles A1 and B. Consider a virtual rectangle A1 ′ that is expanded by Px in the X direction and Py in the Y direction with respect to the rectangle A1.
1'is searched for a rectangle surrounding or in contact with it. In the case shown in the figure, if they are in contact with each other like rectangle B, rectangles A1 and B are merged to create a new merged rectangle A2 and the rectangle data of rectangle A1 is updated and stored. The data of rectangle B is invalid. To do. However, at this time, Px and Py are values obtained from the character size and the line pitch, and when the rectangle formed by merging the rectangles contacts a figure, a table, a separator, etc., the merging itself is invalidated. The rectangle is left as it is.

8) Description of Step S208 Finally, the rectangular data of various areas obtained as described above is output from the output unit 104 together with the image data.

As described above, according to this embodiment, the number of dots per reduced pixel is changed and reduced according to the resolution of the input image, and at the same time, the run length of black pixels is linked and stored in the main scanning direction. By reducing the input image by the image reduction data conversion means that stores the start address of the data in the header area of each row, the processing time of the labeling process is shortened, the storage area is downsized, and the complicated area structure is formed. This has the effect of improving the division accuracy of.

It should be noted that although the processing on the input image is out of the scope of the present invention, it is conceivable that, for example, characters are recognized in the text and processing is performed by an error diffusion method or the like in the case of a photographic image area.

Further, the respective threshold values indicated by the processing contents in the basic attribute discrimination section 108 are determined by the resolution of the input image data and are not fixed.

Further, it is possible to perform area division processing even if the input image is a multi-valued image such as color by judging whether it is multi-valued or not when inputting the image in step S201 and converting it into a binary image. Is.

Further, in the image reduced data conversion processing of step S202, if the number of pixels of the input image is sufficiently small so as not to impair the processing speed, the reduction processing may be omitted and the input image may be directly converted into pixel data.

Further, in the basic attribute detection processing of step S204, the rectangular labels are distinguished by the vertical / horizontal difference of the separator, the difference of the threshold value when obtaining figures, tables, etc.
It is also possible to perform more detailed classification of area attributes.

Similarly, in the basic attribute detection processing of step S204, when only an image having a specific attribute is input from the beginning such as a sentence, the processing can be omitted by designating that fact in advance. Is.

Further, in the detection of the set direction in step S205, instead of obtaining the average width and the average height, the maximum value of each can be obtained for substitution.

Similarly, in the detection of the set direction in step S205, if the set direction is reconfirmed for each paragraph, it is possible to accurately perform processing even on a document in which vertical writing sentences and horizontal writing sentences are mixed.

Similarly, in the detection of the set direction in step S205, if only the text of a fixed set direction is input from the beginning, the set direction is fixed (specified from the operation panel (not shown)). I can do things.

Further, in the heading detection in step S206, if only an image without a heading is input from the beginning, the process can be omitted. Of course, in this case, it is instructed from the operation unit that there is no heading.

Further, in the merge of rectangles in step S207, as shown in FIG. 12, when a rectangle such as a separator is contacted, it is confirmed whether or not the contact is also designated with the actual reduced pixel, and the contact must be made. For example, by performing merger, it is possible to deal with tilted images.

At the final output in step S208, it is also possible to refer to the rectangular data of various areas and output only the image data of the necessary area (of course, the area of the corresponding original image). Further, the storage area can be further reduced and the processing time can be further shortened. For example, if the input image data is output to the character recognition device, only the image determined to be the text can be output to the device. It is extremely easy to calculate the position in the original image from the position of the reduced pixel. That is, if the reduced pixel corresponds to the N × M pixel area of the original image, the positions (X, Y) of the reduced pixel may be multiplied by N and M, respectively.

Therefore, for example, using the apparatus of the embodiment,
It can also be configured to supply image data to it and output only an image of a desired type.

Further, in the above-described embodiment, it has been described that each constituent unit in the area dividing unit 105 is provided with an independent CPU, and the processing is independently performed in each of the constituent units. However, the entire apparatus is operated by one CPU. Of course, it can be applied to the case of processing.

The present invention may be applied to a system composed of a plurality of devices or an apparatus composed of one device. The present invention can also be applied to the case where it is achieved by supplying a program to a system or an apparatus.

[0079]

As described above, according to the present invention, it is possible to determine the area of image data at high speed while suppressing the amount of memory.

[0080]

[Brief description of drawings]

FIG. 1 is a diagram illustrating a schematic configuration of an image processing apparatus according to an embodiment.

FIG. 2 is a flowchart showing image processing in the image processing apparatus of the embodiment.

FIG. 3 is a diagram for explaining labeling processing according to the embodiment.

FIG. 4 is a diagram showing a rectangular data structure of the embodiment.

FIG. 5 is a diagram showing a link structure of reduced pixel data on one line and a link structure of a header portion of each line in the embodiment.

FIG. 6 is a flowchart showing a process of a basic attribute determination unit of the embodiment.

FIG. 7 is a density (D) and area (S) of attributes of rectangles (regions) in the embodiment
It is a figure which shows the division in.

FIG. 8 is a flowchart showing a process of a set direction detecting unit of the embodiment.

FIG. 9 is a diagram illustrating an example of paragraph detection processing according to the embodiment.

FIG. 10 is a flowchart showing a process of a headline type detection unit of the embodiment.

FIG. 11 is a diagram illustrating an example of rectangle merging processing according to the embodiment.

FIG. 12 is a diagram illustrating an example of a separator rectangle merging process according to another embodiment.

[Explanation of symbols]

 101 input unit 102 arithmetic processing unit (CPU) 103 storage unit 104 output unit 105 region dividing unit 106 image reduction data converting unit 107 labeling unit 108 basic attribute discriminating unit 109 set direction detecting unit 110 heading detecting unit 111 rectangular merging unit

Claims (14)

[Claims] 1. An image processing apparatus for determining the type of each area of given image data, comprising: an extracting means for extracting one pixel of low resolution from an m × n pixel area in the image data; An image characterized by including an area discriminating means for discriminating an area of an image type from the continuous spread of pixels, and a discriminating means for judging the type of the area from the area information discriminated by the area discriminating means. Processing equipment. 2. The image processing apparatus according to claim 1, wherein the m and n have larger values as the resolution of input image data is higher. 3. The extracting means extracts, when there is at least one significant pixel in the m × n pixel, a low-resolution pixel corresponding to the m × n pixel as a significant pixel. The image processing device according to item 1. 4. The image processing apparatus according to claim 3, wherein the extraction unit includes a calculation unit that calculates a logical sum of dot states of m × n pixels. 5. The image processing apparatus according to claim 1, wherein the area discriminating means discriminates a rectangle inscribed in a continuous spread of low-resolution pixels as an area. 6. The area discrimination means is means for obtaining a significant pixel position of each low resolution in line units in which a pixel group of m × n in given image data is one pixel, and in the main scanning direction. A memory for storing the start position of consecutive significant low-resolution pixels and the number of consecutive pixels for each scanning line, and storing predetermined discrimination information when there is no significant low-resolution pixel in the line of interest. Means, a searching means for searching a significant low-resolution two-dimensional continuous region in accordance with the contents stored in the storage means, and a label unique to the continuous low-resolution pixel group obtained by the search And a means for obtaining the coordinates of a rectangular area inscribed in the pixel group based on the coordinate position of the pixel group of the specific label.
An image processing apparatus according to the item. 7. The determining means determines the type of the area according to the vertical and horizontal sizes of the area determined by the area determining means and the ratio of the number of pixels of significant low resolution in the area. The image processing apparatus according to claim 1, wherein: 8. An image processing method for determining the type of each area of given image data, comprising an extraction step of extracting one pixel of low resolution from an m × n pixel area in the image data, and a low resolution. An image characterized by including an area discrimination step of discriminating an area of an image type from the continuous spread of pixels, and a discrimination step of judging the type of the area from the area information discriminated in the area discrimination step. Processing method. 9. The image processing method according to claim 8, wherein the m and n have larger values as the resolution of input image data is higher. 10. The extracting step extracts, when there is at least one significant pixel in m × n pixels, a low-resolution pixel for the m × n pixel as a significant pixel. Item 8. The image processing method according to Item 8. 11. The image processing method according to claim 10, wherein the extraction step includes calculation means for calculating a logical sum of dot states of m × n pixels. 12. The image processing method according to claim 8, wherein in the area determining step, a rectangle inscribed in a continuous spread of low resolution pixels is determined as an area. 13. The area determining step includes a step of obtaining a significant pixel position of each low resolution in line units in which an m × n pixel group in given image data is one pixel, and in the main scanning direction. A memory for storing the start position of consecutive significant low-resolution pixels and the number of consecutive pixels for each scanning line, and storing predetermined discrimination information when there is no significant low-resolution pixel in the line of interest. A process, a search process for searching a significant low-resolution two-dimensional continuous region in accordance with the contents stored in the storage process, and a unique label for the continuous low-resolution pixel group obtained by the search. And obtaining the coordinates of a rectangular area inscribed in the pixel group based on the coordinate position of the pixel group of the unique label.
The image processing method according to item 2. 14. The determining step determines the type of the area according to the vertical and horizontal sizes of the area determined in the area determining step and the ratio of the number of significant low-resolution pixels in the area. The image processing method according to claim 8, further comprising: