JP2009064219A - Image processor and image processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor and an image processing method which can obtain a range for an extraction object region with more accuracy in a document image and extract the region where spacings between characters are not uniform. <P>SOLUTION: The image processor is provided with: an extraction object region designating means which makes a user designate a prescribed region to be extracted from image data by drawing a line; a measuring range determining means which determines the measuring range in which at least one of a histogram measurement or a block unit measurement is carried out based on an arbitrary reference point among coordinate data composing the designated line; a measuring means which carries out at least one of the histogram measurement or the block unit measurement for pixels within a determined measuring range; a first exclusion/inclusion means which determines the excluded region and the included region based on the measured result; a circumscribing region extraction means which extracts the circumscribing region in the region after determining which is merged with the determined included region; a second exclusion/inclusion means determining the excluded region and the included region regarding the extracted circumscribing region; and an integrated region determination means for merging the determined included region and making an integrated region. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an image processing apparatus and an image processing method for performing image processing for automatically determining and extracting a designated area in a document image.

In general, in image processing that extracts characters, photographs, diagrams, tables, and the like in a document image, it is difficult to make the extraction rate completely 100%. For example, in the document image data as shown in FIG. 3, a character line (title) that is composed of title characters (large size characters) that are larger in size than other characters (Riko Taro won the XX Award). When it is desired to extract a character line), it is difficult to specify the title character line exactly at the four corners, and conventionally, a rough area slightly smaller is often specified. As such a prior art example, for example, there is a “method of specifying and extracting an extraction target region with a point” (for example, see Patent Documents 1 and 2).
Japanese Patent No. 2948840 Japanese Patent No. 2938490

  However, in the conventional “method of designating and extracting an extraction target region with dots”, for example, when extracting a character string (region) with non-uniform character spacing as shown in FIG. It is difficult to guess the range (how far is the region to be extracted). That is, in the case of FIG. 10, it is estimated whether the range of the extraction target area is only “A”, “A” to “U”, or “A” to “Eo”. Is difficult. The reason is that this conventional method is performed by extracting a rectangle based on position information (coordinates of a specified point) in the extraction target area and increasing the extracted rectangle. This is because position information is required and cannot be applied to a character string with non-uniform character spacing as shown in FIG.

  The present invention has been made in view of the above circumstances, and by specifying with a line (free band) instead of a point, a range of a region to be extracted can be captured more accurately, and a region where character spacing is not uniform An object of the present invention is to provide an image processing apparatus and an image processing method capable of extracting the image.

  In order to achieve such an object, the first image processing apparatus of the present invention includes an extraction target region specifying unit that allows a user to specify a region to be extracted from image data using a line, and an extraction target region specification. An arbitrary coordinate data constituting a line specified in the image data by the means is used as a reference point, and a measurement range in which at least one of histogram measurement and block unit measurement is performed is determined based on the reference point. Based on the measurement range determination means, the measurement means for performing at least one of the measurement by the histogram measurement and the block unit on the pixels within the measurement range determined by the measurement range determination means, and the measurement result of the measurement means, The first exclusion inclusion means for determining the exclusion area and the inclusion area and the inclusion area determined by the first exclusion inclusion means are merged as a post-determination area, Circumscribed area extracting means for extracting a circumscribed area of the area, second excluded inclusion means for determining an excluded area and an included area for the circumscribed area extracted by the circumscribed area extracting means, and an inclusion determined by the second excluded included means And an integrated area determination unit that merges areas into an integrated area.

  In the second image processing apparatus of the present invention, in the first image processing apparatus of the present invention, when measurement is performed in block units after the histogram measurement by the measurement unit, the measurement unit is determined by the measurement range determination unit. The first excluded inclusion means determines a first inclusion region based on the result of the histogram measurement performed by the measurement means, and the measurement means For each pixel in the first inclusion area determined by one exclusion inclusion means, measurement is performed in block units, and the first exclusion inclusion means is based on the result of measurement in block units performed by the measurement means, The second inclusion region is determined, and the circumscribed region extraction unit merges the second inclusion region determined by the first exclusion inclusion unit to obtain a post-determination region, and extracts the circumscribed region of the post-determination region To

  According to a third image processing apparatus of the present invention, in the first or second image processing apparatus of the present invention, the measurement range determining means obtains the number of pixels corresponding to a predetermined character size from the top, bottom, left, and right of the reference point. The number of pixels is used as the measurement range, or the measurement range is all from the top, bottom, left, and right of the reference point to the end of the image data.

  According to a first image processing method of the present invention, an extraction target region specifying step that allows a user to specify a region to be extracted from image data by using a line and an extraction target region specifying step are specified in the image data. A measurement range determining step for determining a measurement range in which at least one of histogram measurement and block unit measurement is performed based on any coordinate data constituting the line as a reference point; The exclusion region and the inclusion region are determined based on the measurement step that performs at least one of the histogram measurement and the block unit measurement on the pixels within the measurement range determined by the determination step, and the measurement result of the measurement step. Merge the inclusion area determined in the first exclusion inclusion step and the first exclusion inclusion step into a post-determination area; A circumscribed area extracting step for extracting a circumscribed area of the fixed area, a second excluded including step for determining an excluded area and an included area for the circumscribed area extracted in the circumscribed area extracting step, and a second excluded including step And an integrated region determination step that merges the included regions into an integrated region.

  The second image processing method of the present invention is the same as the first image processing method of the present invention, in the case where measurement is performed in block units after histogram measurement in the measurement step, and within the measurement range determined in the measurement range determination step. The pixel is measured with a histogram, the first inclusion region is determined based on the result of the histogram measurement, the pixel within the first inclusion region is measured with the block unit, and the pixel unit Based on the measurement result, a second inclusion region is determined, and the circumscribed region extraction step merges the second inclusion region into a post-determination region, and extracts the circumscribed region of the post-determination region .

  According to a third image processing method of the present invention, in the first or second image processing method of the present invention, in the measurement range determining step, the number of pixels corresponding to a predetermined character size is obtained from the top, bottom, left, and right of the reference point. The number of pixels is used as the measurement range, or the measurement range is all from the top, bottom, left, and right of the reference point to the end of the image data.

  According to the present invention, it is possible to form an area in which character spacing is not uniform in image data.

  The best mode for carrying out the present invention will be described below in detail with reference to the accompanying drawings.

The configuration of the image processing apparatus of the present invention will be described with reference to the block diagram of FIG.
An image processing apparatus according to the present invention includes a CPU 101 that performs overall control, a scanner unit 102 that reads a document and acquires image data, a hard disk and a CD / DVD that store image data, information indicating the results of image processing, and the like. / An external storage unit 103 such as a memory card, an input image memory unit 104 that stores input image data, and an operation display unit (touch panel type display) that is operated by a user and displays the input image data such as a preview display ) 106, an area information storage unit 107 for storing area information indicating an area designated by an operation on the operation display unit 106, an image for performing image processing such as binarization processing, block-based measurement, histogram measurement, and rectangle extraction processing Obtain image data from the processing unit 108 and the network 110, A communication control unit 109, or to deliver information indicative of a result of image processing.

  A first embodiment of the operation (image processing method) of the image processing apparatus of the present invention configured as described above will be described with reference to the flowchart of FIG. An image processing program for causing the image processing apparatus of the present invention to execute the processing operation described below is read into the image processing apparatus from a program storage unit (not shown in FIG. 1), or from the external storage unit 103 or the network 110. This controls the operation of the image processing apparatus. The image processing apparatus of the present invention executes the following processing operations under the control of this image processing program.

  In the present invention, as shown in FIG. 14, after a title character string “Riko Taro won the XX Award” is designated as an extraction target area by a line (free band, hereinafter also referred to as a designated line). For example, from the coordinates of the reference point (the leftmost point on the line) to the right, the next character and the next character are extracted based on the measurement result of histogram frequency and pixel distribution, and the space interval (character Between the character strings and the interval is extracted as an extraction target area.

  First, by reading from an image file stored in the external storage unit 103, scanning by the scanner unit 102, downloading from another device on the network 110 via the communication control unit 109, for example, the document shown in FIG. Image data (hereinafter simply referred to as “image data”) is input and displayed on the operation display unit 106 (step S201). It is assumed that the input document image data is subjected to a binarization process for reducing the color to binary.

  While viewing the image data of FIG. 3 displayed on the operation display unit 106, the user can select an area to be extracted (an area that the user desires to extract through the operation display unit 106. In the following description, as an example, an operation for designating the title character line “Taro Riko won the XX Award” as “extraction target area” is performed (step S202).

  Here, the operation display unit 106 accepts an operation by the user (an operation for designating an extraction target area). In the present invention, a line (free band) is used instead of a point in order to simplify the operation. An operation for specifying an extraction target area is accepted. Specifically, the operation display unit 106 receives an input by making contact via an extraction target area designating unit such as a human (user) fingertip, a stylus pen, or other contact input tool. The operation display unit 106 detects and accepts an input at each position on the display surface by a known technique such as a resistance film method that detects a change in resistance by pressing from a fingertip or a pen tip or an analog capacitive coupling method. As an input form, various input methods including a mouse, a keyboard, and a push switch can be applied in addition to a contact input (touch input) in which input is performed by touching the operation display unit 106.

  FIG. 4 shows an image when the extraction target area is designated as described above. FIG. 4 shows a state in which the title character line “Taro Riko receives the XX prize” is designated by a line (free band) as an extraction target area.

  The vector data of the input line (free band) is composed of coordinate data, such as coordinate 1 (x1, y1), coordinate 2 (x2, y2)... Coordinate n (xn, yn), It consists of multiple coordinate data. These coordinate data are used as reference points for determining a surrounding range (measurement range) described later. 5 and 8, each coordinate data (reference point) is shown as a blue point.

  Next, based on each reference point described above, a “surrounding range (hereinafter referred to as a measurement range)” to be measured (histogram measurement or measurement in block units) is determined (step S203). Here, in the present invention, the reason for performing the measurement only in the measurement range is that if the measurement is performed on the entire image, the processing time is reduced.

  The size of the measurement range is determined based on one of the following two conditions, <measurement range determination condition 1> or <measurement range determination condition 2>. Which condition to select can be specified by the user (implementing the present invention in an application). In the following description, <measurement range determination condition 1> is applied, and an example thereof is shown in FIGS. 5 and 8 show a case where the measurement range is determined based on the leftmost reference point 1 on the line (free band).

<Measurement range determination condition 1>
The number of pixels corresponding to the character size of the title character (large size character constituting the title character line) is obtained from the top, bottom, left and right of the reference point, and the value is taken as the measurement range. Note that the number of pixels is obtained from the character size and resolution corresponding to the title character. It is assumed that the user can specify the character size (for example, the character size of each title character shown in FIGS. 5 and 8 is 20 mm).

<Measurement range determination condition 2>
The measurement range is all from the top, bottom, left, and right of the reference point to the edge of the image (for example, as shown in FIG. 12, in the case of the reference point 1 at the leftmost end of the line, it is shown from the reference point 1 to each end of the image. The up, down, left and right arrows indicate the measurement range).

Next, in the determined measurement range, histogram measurement or measurement in block units is performed (step S204).
In the measurement range, the measurement is aborted if any of the following two conditions, <measurement abort condition 1> or <measurement abort condition 2> is satisfied.

<Measurement termination condition 1>
When arriving at the end of a pixel (blanks must be above a certain value). However, when the interval of the blank matrix (character spacing or line spacing; see FIGS. 6 and 10) is equal to or less than a certain value, the process proceeds to the next pixel.

<Termination condition 2>
When the measurement range is exceeded.

  Hereinafter, measurement in units of blocks and histogram measurement will be described.

[Measurement in block units]
The measurement in units of blocks (pixel distribution measurement) is used to determine whether the character is a character or a character other than the character based on the strength of the edge of the pixel. Characters tend to have strong edges, while figures and photographs tend to have weak edges. Therefore, non-character / characters are determined based on the pixel distribution, and any non-characters are excluded.

  As described above, in step S203, the measurement range is determined based on each reference point on the designated line (each point shown in FIG. 5A). FIG. 5A shows only the measurement range determined by the above <Measurement range determination condition 1> based on the leftmost reference point 1 on the designated line.

  Then, the block is divided into blocks of an arbitrary size within the determined measurement range. As a dividing method, as shown in FIG. 5B, the block is divided into an arbitrary size starting from the reference point 1.

  After dividing the block at an arbitrary size, the number and distribution of black and white pixels scattered in the divided block area are examined. This is a measurement in units of blocks (pixel distribution measurement).

Here, the censoring of measurement in units of blocks will be described with reference to FIG.
It is assumed that measurement is performed in the direction indicated by the arrow in the measurement range shown in FIG.
In “pixel arrangement example 1”, white pixels (blanks) do not come (be detected), and therefore measurement is performed to the full measurement range.
“Pixel arrangement example 2” is a case in which the setting is such that the measurement is unconditionally terminated when a white pixel comes. Since two white pixels come in the middle of the measurement, the measurement is terminated. It will be.
“Pixel arrangement example 3” is a case in which the measurement is stopped in advance when the white pixel reaches a certain value (here, 3 pixels) or more. Since the white pixel comes, the measurement is aborted (the white pixel for 2 pixels does not abort).
The white pixel (blank) is “character spacing” or “line spacing”.

Then, it is determined whether the trend of the number and distribution of black and white pixels obtained as a result of the measurement corresponds to any one of [1] to [5] in FIG. 7, and the area to be excluded and the area to be included are determined. Exclusion / inclusion processing is performed (step S205). A description of the arrangement of the pixels in each block area shown in [1] to [5] in FIG. 7 will be given below.
[1] Black or white pixels are arranged in a line. Included as characters / ruled lines.
[2] The distribution of black or white pixels is random and evenly arranged. Judge as picture / photo and exclude.
[3] The edge of a black or white pixel is clear. Included as characters / ruled lines.
[4] The number of black or white pixels is small. exclude. However, it may not be excluded depending on the condition of the blank matrix interval (white pixels).
[5] There is no black or white pixel. exclude. However, it may not be excluded depending on the condition of the blank matrix interval (white pixels).

  Based on the result of the exclusion / include process in step S205, the block areas to be included are merged to determine a post-determination area (step S206).

[Histogram measurement]
The histogram measurement is used to measure the frequency of pixels per column or row, and to determine that there is a blank if the number of rows / columns without pixels is equal to or greater than a certain value.

  As described above, in step S203, the measurement range is determined based on each reference point (each point shown in FIG. 8) on the designated line. FIG. 8 shows the measurement range determined by the above <Measurement range determination condition 1> based on the leftmost reference point 1 on the designated line. The a portion is the upper measurement range, the b portion is the lower measurement range, and the c portion is the left measurement range (actually, measurement is also performed in the right direction, but the right measurement range is not shown in FIG. 8).

  Then, histogram measurement is performed within each measurement range shown in FIG. For example, when the histogram is measured for the portion a, the number of times that a black region indicating a black pixel continuously occurs or the number of times that a white region indicating a white pixel continuously occurs is counted in row units in the upward direction. Histogram measurement is performed in the same manner in directions other than the upward direction. The result of histogram measurement of the part a is an image as shown in FIG. Further, the result of histogram measurement of the portion b downward is an image as shown in FIG. Further, the result of the histogram measurement of the portion c downward is an image as shown in FIG. The counted number of times is compared with a predetermined threshold value, and the boundary position of the extraction target area designated based on the comparison result is determined.

  Then, based on the result of histogram measurement (histogram frequency), an exclusion / inclusive process for determining an excluded area and an included area is performed (step S205). In this exclusion / inclusion process, for example, as shown in FIG. 9, a blank portion (blank space) B that can be regarded as a character spacing / line spacing is determined. The value for determining the blank space B is determined under the following conditions.

<Blank determination condition 1>
The number of black pixels in the binarized image is at least one.

<Blank determination condition 2>
The number of black pixels is not one (the row / column is blank), and the blank interval is equal to or less than a certain value (st).

In order to be able to cope with various resolutions, the space interval is proportional to the resolution. Specifically, it is 1 for 100 dpi, 2 for 200 dpi,... 6 for 600 dpi, and a value obtained by multiplying the value by a count n designated by the user is a constant value (st. (See the following formula).

  Based on the result of the exclusion / include process in step S205, the included block areas are merged to determine the post-determination area (step S206).

A circumscribed area is extracted from the determined area by the rectangle extraction process disclosed in Patent Document 1 (step S207). Judgment is made from the extracted circumscribed area based on the frequency / size / area attribute of the pixel, and the extracted circumscribed area is assigned to the circumscribed area to be excluded and the circumscribed area to be included (step S208). For example, in the case where it is desired to take only a character, there is a case where a circumscribed area indicating a long and narrow side line indicating a line is excluded. Conversely, there are cases where you do not want to exclude them, so you can adjust them with parameters. The detection method of the elongated circumscribed area is calculated by the following equation.

  Calculated from the above equation (Equation 2) and detected when both sides exceed. As shown in FIG. 13, a plurality of circumscribed areas (areas surrounded by thin frame lines) are merged into one area (area surrounded by thick frame lines) to obtain an integrated area (step S209). . The integrated area is output (step S210), and the process ends.

As described above, according to the first embodiment of the present invention, the following effects can be obtained.
As a first effect, it is possible to extract a region where character spacing is not uniform.
As a second effect, the troublesome operation of the user can be saved.
As a third effect, it is possible to appropriately specify a region to be extracted.
As a fourth effect, the integrated area can be used for applications such as character recognition processing.

  Further, the present invention can cope with the following cases by extracting a region having a non-uniform character spacing. For example, as shown in FIG. 3, the title character line in the document image is often composed of one line. When the user draws a line (free band) on one title character line and designates it as an extraction target area, for example, as shown in FIG. 11, the line extends beyond the extraction target area (title character line). It is also possible to pull In such a case, in the conventional extraction method described above, the region other than the region to be extracted (the region specified by the protruding line, the title character “book” in FIG. 11) is also extracted together. However, in the present invention, in the region to be extracted designated by the line (free band), the region designated by protruding is excluded or included based on the frequency of the pixel histogram or the pixel distribution. By performing such determination, it is possible to extract only the extraction target region without extracting the region other than the extraction target region.

  In the description of the operation in the first embodiment, after the measurement range is determined, either the block unit measurement or the histogram measurement is performed. However, both measurements may be performed in order. That is, first, histogram measurement is performed, and an area to be included is determined. Next, measurement is performed in units of blocks for the area, and a non-character / character is determined based on edge strength. This operation (image processing method) will be described with reference to FIG.

  The process from the input of image data in step S301 to the determination of the measurement range in step S303 is the same as steps S201 to S203 in FIG. 2 described in the first embodiment (detailed description is omitted).

  In the determined measurement range, first, histogram measurement is performed (step S304). Then, exclusion / inclusive processing is performed based on the result of the histogram measurement, and an area (range) to be excluded and an area (range) to be included are determined (step S305).

  Next, in the “include region (range)” determined by the exclusion / include process in step S305, measurement is performed in block units (step S306). Then, exclusion / inclusive processing is performed based on the result of measurement in block units, and a region (range) to be excluded and a region (range) to be included are determined (step S307).

  The included region (range) determined in step S307 is set as a post-determination region (step S308). Processes after step S308 (S308 to S312) are the same as steps S206 to S210 in FIG. 2 (detailed description is omitted).

  As described above, by performing the two measurements in order, the extraction accuracy of the designated region can be further increased.

  As mentioned above, although Example 1 and 2 of this invention were demonstrated, it is not limited to description of the said Example 1, 2, and a various deformation | transformation is possible in the range which does not deviate from the summary.

  The control operation in the above-described image processing apparatus can be executed by hardware, software, or a combined configuration of both. In the case of executing processing by software, a program in which a processing sequence is recorded is installed in a memory in a computer (such as the CPU 1 in FIG. 1) incorporated in dedicated hardware and executed. It is possible to install and execute a program on a general-purpose computer capable of executing various processes.

  For example, the program can be recorded in advance on a hard disk or a ROM (Read Only Memory) as a recording medium. Alternatively, the program is temporarily stored on a removable recording medium such as a floppy (registered trademark) disk, a CD-ROM (Compact Disc Read Only Memory), an MO (Magneto optical) disk, a DVD (Digital Versatile Disc), a magnetic disk, or a semiconductor memory. Or can be stored (recorded) permanently. Such a removable recording medium can be provided as so-called package software.

  The program is installed on the computer from the removable recording medium as described above, or is wirelessly transferred from the download site to the computer, or is wired to the computer via a network such as a LAN (Local Area Network) or the Internet. However, the computer can receive the transferred program and install it on a recording medium such as a built-in hard disk.

  In addition to being executed in time series according to the processing operation of the image processing apparatus of the present invention described in the first and second embodiments, the processing capability of the apparatus for executing the process, or in parallel as necessary Alternatively, it can be constructed to execute individually.

  In addition, the image processing apparatus of the present invention described in the first and second embodiments can be configured to have a logical set configuration of a plurality of apparatuses or to have functions of each apparatus mixed.

  The present invention can be applied to an apparatus / device, a system, a method, a program, and the like that execute image processing for extracting a predetermined region in an image.

It is a block diagram which shows the structure of the image processing apparatus of this invention. It is a flowchart which shows operation | movement of the image processing apparatus of this invention. It is a figure which shows an example of the document image data processed with the image processing apparatus of this invention. It is a figure which shows the state by which the area | region of extraction object was designated with the line in the document image data processed with the image processing apparatus of this invention. It is a figure which shows an example of the measurement by the block unit performed with the image processing apparatus of this invention. It is a figure which shows the example of censoring of the measurement by the block unit performed with the image processing apparatus of this invention. It is a figure which shows each example of the result of the measurement by the block unit performed with the image processing apparatus of this invention. It is a figure which shows an example of the histogram measurement performed with the image processing apparatus of this invention. It is a figure which shows the example of the exclusion / inclusion process based on the result of the histogram measurement performed with the image processing apparatus of this invention. It is a figure which shows the example of the character string with a non-uniform character space | interval which can be processed with the image processing apparatus of this invention. FIG. 5 is a diagram showing a state in which an extraction target area is specified in a document image data processed by the image processing apparatus of the present invention. It is a figure which shows the example of the measurement range at the time of determining based on the measurement range determination condition 2 in determination of the measurement range performed with the image processing apparatus of this invention. It is a figure which shows the example of the integrated area calculated | required by the merging of several circumscribed area | region performed with the image processing apparatus of this invention. It is a figure for demonstrating the outline | summary of the extraction in the document image data processed with the image processing apparatus of this invention. It is a flowchart which shows another example of operation | movement of the image processing apparatus of this invention.

Explanation of symbols

101 CPU
DESCRIPTION OF SYMBOLS 102 Scanner part 103 External storage part 104 Input image memory part 106 Operation display part 107 Area | region information storage part 108 Image processing part 109 Communication control part 110 Network 111 Recording medium 112 Database

Claims (6)

An extraction target area specifying means for allowing a user to specify an area to be extracted from image data using a line;
Arbitrary coordinate data constituting the line designated in the image data by the extraction target area designating unit is used as a reference point, and at least one of histogram measurement and block unit measurement is performed based on the reference point. A measuring range determining means for determining a measuring range to be performed;
Measurement means for performing at least one of histogram measurement and measurement in block units on pixels within the measurement range determined by the measurement range determination means;
First exclusion inclusion means for determining an exclusion area and an inclusion area based on a result measured by the measurement means;
A circumscribed area extracting means for merging the inclusion areas determined by the first exclusion inclusion means into a post-determination area and extracting a circumscribed area of the post-determination area;
A second exclusion inclusion means for determining an exclusion area and an inclusion area for the circumscribed area extracted by the circumscribed area extraction means;
An integrated region determination unit that merges the inclusion regions determined by the second exclusion inclusion unit into an integrated region;
An image processing apparatus comprising: When the measurement unit performs measurement by the block unit after the histogram measurement,
The measurement unit performs histogram measurement on the pixels within the measurement range determined by the measurement range determination unit,
The first exclusion inclusion means determines a first inclusion area based on a result of histogram measurement performed by the measurement means,
The measurement means performs measurement in units of blocks on the pixels in the first inclusion area determined by the first exclusion inclusion means,
The first exclusion inclusion means determines a second inclusion area based on the result of measurement in block units performed by the measurement means,
2. The circumscribed area extraction unit merges the second inclusion area determined by the first exclusion inclusion unit as a post-determination area, and extracts a circumscribed area of the post-determination area. Image processing apparatus. The measurement range determining means includes
The number of pixels corresponding to a predetermined character size is obtained from the top, bottom, left, and right of the reference point, and the obtained number of pixels is taken as the measurement range, or all from the top, bottom, left, and right of the reference point to the edge of the image data are the measurement range. The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus. An extraction target area specifying step for allowing a user to specify an area to be extracted from image data using a line;
Arbitrary coordinate data constituting the line specified in the image data in the extraction target area specifying step is used as a reference point, and at least one of histogram measurement and block unit measurement is performed based on the reference point. A measuring range determining step for determining the measuring range to be performed;
A measurement step of performing at least one of histogram measurement and block-based measurement on pixels within the measurement range determined by the measurement range determination step;
A first exclusion inclusion step for determining an exclusion region and an inclusion region based on the result measured in the measurement step;
A circumscribed region extraction step of merging the inclusion regions determined in the first exclusion inclusion step into a post-determination region and extracting a circumscribed region of the post-determination region;
A second exclusion inclusion step for determining an exclusion area and an inclusion area for the circumscribed area extracted in the circumscribed area extraction step;
An integrated area determination step that merges the inclusion areas determined in the second exclusion inclusion step into an integrated area;
An image processing method comprising: In the measurement step, after the histogram measurement, when the measurement by the block unit is performed,
Histogram measurement is performed on pixels within the measurement range determined in the measurement range determination step,
Determining a first inclusion region based on the result of the histogram measurement;
Performing a block-by-block measurement on the pixels in the first inclusion region;
Determining a second inclusion region based on the result of the measurement in block units;
5. The image processing method according to claim 4, wherein, in the circumscribed area extracting step, the second inclusion area is merged to be a post-determination area, and a circumscribed area of the post-determination area is extracted. In the measurement range determination step,
The number of pixels corresponding to a predetermined character size is obtained from the top, bottom, left, and right of the reference point, and the obtained number of pixels is taken as the measurement range, or all of the image data from the top, bottom, left, and right of the reference point to the end of the image data is the measurement range. 6. The image processing method according to claim 4, wherein the image processing method is performed.

Images