JP2011170481A - Image processing apparatus and image processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing apparatus which controls the number of control points in a vectorized result to be equal to the target number of control points in vectorizing an image. <P>SOLUTION: A vectorizing means of the image processing apparatus vectorizes the image using a threshold value. A measuring means of the number of control points counts the number of control points in the vectorized result by the vectorizing means. If the number of control points measured by the measuring means of the number of control points does not coincide with the target number of control points, a threshold calculation means calculates a threshold based on the number of control points counted by the measuring means of the number of control points, and the vectorizing means vectorizes the image using the threshold calculated by the threshold calculation means. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to an image processing apparatus and an image processing program.

There is a vectorization technique for images.
As a technology related to this, for example, Patent Document 1 discloses a method for obtaining an image processing method capable of faithfully reproducing the shape of a character or a figure using a small amount of data. A distance function between a given contour point and a contour vector is obtained while adjusting the positions of a predetermined number of end points of the contour vector in the candidate region at a time so as to obtain a contour vector having a minimum norm. It is disclosed.

  In addition, for example, Patent Document 2 discloses that a polygon shape is approximated to a region shape with a smaller code amount, and further, the adjustment of the code amount is facilitated. The threshold value of the permissible error is determined, attention is paid to one side of the approximate polygon, and an intersection formed by extending two sides adjacent to the side is removed, and the intersection is replaced with a new approximate polygon. Measure the approximation error when the vertex is set, select the side with the minimum approximation error, and if the approximation error is less than the threshold, remove the side and use the intersection as a new vertex of the approximate polygon, leaving no side to be removed It is disclosed that the above processing is continued. That is, it is a technique for expressing a curve with as few line segments as possible while maintaining image quality (approximation accuracy). Here, the image quality (approximation accuracy) is maintained by dividing the line segment until the distance between the target curve and the line segment is equal to or less than a predetermined threshold value, and the predetermined threshold value is set. Since the division is finished when the time becomes the following, the number of line segments can be made as small as possible.

  In addition, for example, Patent Document 3 has a problem that it is difficult to accurately describe the shape of an image area with a small amount of data without trial and error, and a plurality of attention points are taken on the boundary line of the area. Draw an approximate curve while taking into account the position of the reference point in the vicinity, and when the error of the approximate curve for a certain point of interest is large, replace the approximate curve with a nearby approximate curve, and if the error is still large, correct the position of the reference point Then, it is disclosed that the curvature and normal direction at each point of interest are accurately obtained from the approximate curve, and feature points such as inflection points and inflection points are detected.

  In addition, for example, Patent Document 4 aims to provide a data processing device that reduces the amount of data when high-quality outline data is generated, and the acute-angle point extraction unit is a line obtained by a straight line approximation unit. An acute point where the angle of the adjacent line segment is equal to or less than a predetermined angle is extracted from the segment group, the segment group between the acute angle points is defined as a segment group C, and the via point calculation unit has a cubic Bezier curve that approximates the segment group C. The control point calculation unit calculates a via point that is assumed to pass, and the control point calculation unit obtains a binary primary simultaneous system obtained by assuming that a cubic Bezier curve that approximates the line segment group C passes through the via point calculated by the via point calculation unit. The equation is solved to calculate two control points of the cubic Bezier curve, and the determination unit determines whether or not an error between the obtained cubic Bezier curve and the line segment group C is equal to or greater than a predetermined value. When is greater than or equal to a predetermined value, the dividing unit divides line segment group C, and the divided line segment group is Re as a line segment group C, and it is disclosed that seek again cubic Bezier curve.

JP 05-035871 A Japanese Patent Laid-Open No. 06-060174 Japanese Patent Laid-Open No. 10-091796 JP 2009-199340 A

  An object of the present invention is to provide an image processing apparatus and an image processing program that can control the number of control points of the vectorization result to a target number of control points when the image is vectorized. It is said.

The gist of the present invention for achieving the object lies in the inventions of the following items.
The invention according to claim 1 is measured by the vectorization means for vectorizing the image using a threshold, the control point number measurement means for measuring the number of control points of the vectorization result by the vectorization means, and the control point measurement means. A threshold calculating means for calculating a threshold based on the number of control points measured by the control point number measuring means when the number of control points and the target number of control points do not match, The vectorization means is an image processing apparatus characterized in that the image is vectorized using the threshold value calculated by the threshold value calculation means.

  The invention of claim 2 further comprises storage means for storing the threshold value and the number of control points in association with each other, and the threshold value calculation means is a correspondence between the threshold value stored in the storage means and the number of control points. The image processing apparatus according to claim 1, wherein a threshold value corresponding to a target number of control points is calculated using.

  According to a third aspect of the present invention, the threshold value calculation means determines whether or not the relationship between the threshold value and the number of control points is monotonically decreasing. When the relationship between the threshold value and the control point number is not monotonically decreasing, a predetermined threshold value is used. The image processing apparatus according to claim 1, wherein a threshold value is calculated.

  According to a fourth aspect of the present invention, the threshold value calculation means determines whether or not the relationship between the threshold value and the number of control points is monotonously decreased. The image processing apparatus according to claim 1, wherein a threshold value is calculated.

  According to a fifth aspect of the present invention, the vectorization means divides the vector until an error between the vector and a line segment in the image satisfies a predetermined condition, and the predetermined condition is determined by the vectorization means. An error storage means for storing an error in the immediately preceding division when satisfied, and a representative error calculation means for calculating a representative value of the error stored in the error storage means; 5. The image processing apparatus according to claim 1, wherein the means calculates a next threshold value using the representative value calculated by the representative error calculation means. 6.

  According to the sixth aspect of the present invention, there is provided a computer comprising: vectorizing means for vectorizing an image using a threshold value; control point number measuring means for measuring the number of control points resulting from vectorization by the vectorizing means; and the control point number measurement. When the number of control points measured by the means and the target number of control points do not match, function as threshold calculation means for calculating a threshold based on the number of control points measured by the control point number measurement means An image processing program for causing the vectorization means to vectorize the image using the threshold value calculated by the threshold value calculation means.

  According to the image processing apparatus of the first aspect, when the image is vectorized, the number of control points of the vectorization result can be controlled.

  According to the image processing apparatus of the second aspect, it is possible to reduce the processing load as compared with the case where the present configuration is not provided.

  According to the third and fourth image processing apparatuses, even when the relationship between the threshold value and the number of control points is not monotonously decreasing, the number of control points of the vectorization result can be controlled.

  According to the image processing apparatus of the fifth aspect, it is possible to calculate the threshold value corresponding to the target image.

  According to the image processing program of the sixth aspect, when the image is vectorized, the number of control points of the vectorization result can be controlled.

It is a conceptual module block diagram about the structural example of 1st Embodiment. It is a flowchart which shows the process example by 1st Embodiment. It is explanatory drawing which shows the data structural example of a threshold-value / control score table. It is a graph which shows the example of a relationship between a threshold value and the number of control points. It is a conceptual module block diagram about the structural example of 2nd Embodiment. It is a flowchart which shows the process example by 2nd Embodiment. It is explanatory drawing which shows the data structural example of a threshold value and image quality target value table. It is a graph which shows the example of a relationship between a threshold value and the number of control points. It is a graph which shows the example of a relationship between a threshold value and the number of control points. It is a graph which shows the example of a relationship between a threshold value and the number of control points. It is a graph which shows the example of a relationship between a threshold value and the number of control points. It is explanatory drawing which shows the example of determination of a control point. It is a notional module block diagram about the structural example of 4th Embodiment. It is a flowchart which shows the process example by 4th Embodiment. It is a graph which shows the example of a relationship between a threshold value and the number of control points. It is a block diagram which shows the hardware structural example of the computer which implement | achieves this Embodiment.

Hereinafter, examples of various preferred embodiments for realizing the present invention will be described with reference to the drawings.
<First Embodiment>
FIG. 1 is a conceptual module configuration diagram of a configuration example according to the first embodiment.
The module generally refers to components such as software (computer program) and hardware that can be logically separated. Therefore, the module in the present embodiment indicates not only a module in a computer program but also a module in a hardware configuration. Therefore, the present embodiment also serves as an explanation of a computer program, a system, and a method. However, for the sake of explanation, the words “store”, “store”, and equivalents thereof are used. However, when the embodiment is a computer program, these words are stored in a storage device or stored in memory. It is the control to be stored in the device. Modules may correspond to functions one-to-one, but in mounting, one module may be configured by one program, or a plurality of modules may be configured by one program, and conversely, one module May be composed of a plurality of programs. The plurality of modules may be executed by one computer, or one module may be executed by a plurality of computers in a distributed or parallel environment. Note that one module may include other modules. Hereinafter, “connection” is used not only for physical connection but also for logical connection (data exchange, instruction, reference relationship between data, etc.).
In addition, the system or device is configured by connecting a plurality of computers, hardware, devices, and the like by communication means such as a network (including one-to-one correspondence communication connection), etc. The case where it implement | achieves by etc. is also included. “Apparatus” and “system” are used as synonymous terms. Of course, the “system” does not include a social “mechanism” (social system) that is an artificial arrangement. “Predetermined” means that the process is determined before the target process, and not only before the process according to this embodiment starts but also after the process according to this embodiment starts. In addition, if it is before the target processing, it is used in accordance with the situation / state at that time or with the intention to be decided according to the situation / state up to that point.

  The image processing apparatus according to the first embodiment is an apparatus for vectorizing an image, and as shown in FIG. 1, a vectorization module 110, a control point measurement module 120, a threshold value calculation module 130, a threshold value and a control point number. A storage module 140, a comparison module 150, and a vectorization result storage module 160 are provided.

  The vectorization module 110 is connected to the control point measurement module 120, the threshold calculation module 130, and the vectorization result storage module 160. The vectorization module 110 receives an image, receives a threshold value from the threshold value calculation module 130, vectorizes the target image using the threshold value, and stores the vectorization processing result in the control score measurement module 120, the vectorization result storage. Pass to module 160.

  Accepting an image means, for example, reading an image with a scanner, a camera, etc., receiving an image from an external device via a communication line by fax, etc., a hard disk (in addition to what is built in a computer, via a network) And the like, and the like read out the images stored in the device etc.). Although the received image is a binary image, a multi-value image (including a color image) may be received and binarization processing may be performed. One image may be received or a plurality of images may be received.

  Further, the threshold value accepted here is a value used for vectorization of an image, and by changing the threshold value, the number of control points of the vectorization result is also changed. For example, vectorization is performed so that the distance (difference, error) when the received image is compared with the vectorization line segment at the control point is equal to or less than a threshold value.

The vectorization process uses the existing technique described in the background art, and examples of the vectorization process include a straight line, a Bezier curve, and a spline curve.
For example, in the technique described in Patent Document 4, a line segment group in an image is approximated by a Bezier curve expression.
As the line segment group, the target image is a binary image, pixels in the image are captured as squares, and the surrounding shape of black pixels in the target binary image is captured as a line segment group. Alternatively, the surrounding shape of the square may be approximated by a straight line (including an oblique line) to form a line segment group.
In the technique described in Patent Document 4, when a binary image is expressed by a mathematical expression, the distance between the original line segment group in the target image and the curve of the approximation result after vectorization is calculated, and the distance is Control is performed so as to be equal to or less than a predetermined threshold.
Information for drawing these straight lines, Bezier curves, spline curves, and the like is vectorized control points. The number of vectorized control points is, for example, “control point as start point”, “end point” described in Patent Document 4. As the control point ”and“ the control point of the Bezier curve ”. Alternatively, since the end point of a certain curve and the start point of the next curve may be shared, the number of “control points as start points” and “control points of Bezier curves” may be used. The file capacity as a result of vectorization processing is determined by the number of vectorization control points.

The control point measurement module 120 is connected to the vectorization module 110, the threshold calculation module 130, and the comparison module 150. The control point number measurement module 120 measures the number of control points of the vectorization result by the vectorization module 110 and passes the control point number to the threshold value calculation module 130 and the comparison module 150.
The comparison module 150 is connected to the control point measurement module 120, the threshold calculation module 130, and the vectorization result storage module 160. The comparison module 150 compares the number of control points measured by the control point number measurement module 120 with the target number of control points. If the two values do not match, the threshold calculation module 130 is instructed to calculate the next threshold used by the vectorization module 110. If both values match, an instruction is given to output the vectorization result stored in the vectorization result storage module 160. Here, as the target number of control points, the number of control points for preventing the file size output by the vectorization result storage module 160 from exceeding a predetermined size, or an application using the output From the above restrictions, it is the number of vectorization control points that can exist in the file format, etc. The target control point number may be a single numerical value, or a numerical value with a range (a range in which only an upper limit is determined) Or a range in which an upper limit and a lower limit are defined. Therefore, the case where the two values match each other means that the two values match or the number of control points measured by the control point number measuring module 120 is within the target control point number range. This is a condition for ending the processing according to the form. The case where the two values do not match means the case where the two values do not match or the case where there is no number of control points measured by the control point number measuring module 120 within the range of the target control points, such as the vectorization module 110. The process according to is repeated.

The threshold calculation module 130 is connected to the vectorization module 110, the control point count module 120, the threshold / control point storage module 140, and the comparison module 150. The threshold value calculation module 130 is measured by the control point measurement module 120 in accordance with an instruction from the comparison module 150 (when the number of control points measured by the control point measurement module 120 does not match the target number of control points). A threshold value is calculated based on the number of control points. Further, the threshold value corresponding to the target number of control points may be calculated using the correspondence between the threshold value and the number of control points stored in the threshold value / control point number storage module 140. Further, a threshold value corresponding to the target number of control points may be calculated based on the number of control points measured in the past by the control point number measuring module 120 and the target number of control points. In the case of the first or second vectorization process by the vectorization module 110, a predetermined value may be calculated as a threshold value. Then, the calculated threshold value is passed to the vectorization module 110. Further, the calculated threshold value is associated with the number of control points measured by the control point number measurement module 120 and stored in the threshold value / control point number storage module 140.
The threshold / control score storage module 140 is connected to the threshold calculation module 130. The threshold / control score storage module 140 stores the threshold received from the threshold calculation module 130 in correspondence with the number of control points. Further, a correspondence between a predetermined threshold value and the number of control points may be stored.

The vectorization result storage module 160 is connected to the vectorization module 110 and the comparison module 150. The vectorization result storage module 160 stores the vectorization result by the vectorization module 110. Then, in accordance with an instruction from the comparison module 150 (when the number of control points measured by the control point measurement module 120 matches the target number of control points), the stored vectorization result is output. To output the vectorization result is, for example, printing with a printing device such as a printer that draws the vectorization result, displaying it on a display device such as a display, transmitting an image with an image transmission device such as a fax, This includes writing an image to a storage device such as a database, storing it in a storage medium such as a memory card, and passing it to another information processing device.
In addition, the vectorization result storage module 160 may convert the image into a drawing command such as a straight line or a curve using the result of vectorizing the image at the time of output and create a file. For example, by doing this, vector data such as a drawing command of a file for PDF ((registered trademark) Portable Document Format), PS (PostScript), a word processor application (document creation program), draw graphics, etc. Files such as the file formats described, clip art, etc. may be formed. In the case of forming such a file, the present embodiment controls the file size so as not to exceed a predetermined size, or vectorization control existing in the file format due to restrictions on the application. You may use it for controlling a score below a predetermined value.

FIG. 2 is a flowchart illustrating a processing example according to the first exemplary embodiment.
In step S202, the vectorization module 110 receives an image.
In step S204, the threshold calculation module 130 and the comparison module 150 accept the target control score.
In step S206, the threshold calculation module 130 calculates an initial threshold. That is, a predetermined initial threshold value is output to the vectorization module 110. The predetermined initial threshold value is stored in the threshold value / control score storage module 140 and is read out. It is also assumed that the second (second round) threshold value is also determined in advance and stored in the threshold value / control score storage module 140.
In step S208, the vectorization module 110 performs vectorization on the image received in step S202 using the threshold value output in step S206.
In step S210, the control point measurement module 120 measures the number of control points as a vectorization result.
In step S212, the vectorization result storage module 160 stores the vectorization result.

In step S214, the comparison module 150 compares the number of control points with the target number of control points. If they match (for example, if the number of control points is equal to or less than the target number of control points), the process proceeds to step S224; otherwise (for example, if the number of control points is greater than the target number of control points), the process proceeds to step S216.
In step S <b> 216, the threshold / control score storage module 140 stores the control scores transferred from the threshold calculation module 130.
In step S218, the threshold value calculation module 130 calculates a new threshold value. In the case of the second (second round) threshold, one stored in the threshold / control score storage module 140 may be used as it is. After the third (third round), a new threshold value is calculated based on the threshold value and the control point number stored in the threshold value / control point number storage module 140.
In step S220, the threshold / control score storage module 140 stores the threshold calculated in step S218.
In step S222, the vectorization module 110 performs the vectorization process again using a new threshold value. Then, the process returns to step S210. The processes from step S210 to step S222 are repeated until they are matched in step S214.
In step S224, the vectorization result storage module 160 outputs the vectorization result according to the instruction of the comparison module 150.

  The threshold calculation module 130 calculates the threshold mainly based on the number of control points measured by the control point number measurement module 120, a pair of threshold and control points, and the target number of control points. A pair of threshold and control points can be represented by a threshold / control points table 300 as illustrated in FIG. This is stored in the threshold / control point storage module 140. The threshold / control score table 300 includes a threshold column 310 and a control score column 320. The threshold value column 310 stores a threshold value. The control points column 320 stores the number of control points corresponding to the threshold value.

The relationship between the threshold value, the number of control points, and the target number of control points can be represented by a graph as illustrated in FIG.
For example, if the relationship between the threshold value (horizontal axis) and the number of control points (vertical axis) can be expressed as shown in FIG. 4, the target threshold value can be received and the threshold value calculated.
Let N be the number of control points and T be the threshold. The number N of control points is regarded as a function of the threshold value T. For example, N = f (T). Furthermore, let P be the target number of control points.
At this time,
f (T) = P
It becomes a problem for obtaining T satisfying the above. This can be obtained by a general numerical calculation method (Newton method or the like).

Below is a simple example. There are various other numerical calculation methods.
For example, the initial threshold value is T0.
If the number of control points when vectorized at the initial threshold value T0 does not satisfy the target control point number P, the next threshold value T1 is determined in advance and the next vectorization process is performed.
The number of control points when vectorized with the initial threshold value T0 is N0, and the number of control points when vectorized with the threshold value T1 is N1.
Using these two pairs ((T0, N0), (T1, N1)), an estimated value T2 of T satisfying the target number of control points P is calculated in the (T, N) two-dimensional space as (T0, N0). And the T coordinate of the intersection of the straight line passing through (T1, N1) and the straight line N = P.
If the target number of control points is not satisfied even at the threshold T2, the vector is calculated using the control point number N0 or the control point number N1 that is closer to the target control point number P, the threshold value corresponding to the control point number, and the threshold value T2. The next threshold value T3 is calculated using the number of control points N2.
This process is repeated.

In the above-described processing, f () is approximated by a straight line, but other methods such as approximation by a quadratic curve may be used.
In the above-described processing, the vectorized result is stored in the vectorized result storage module 160 and the finally stored result is output. However, it is not necessarily stored. The vectorization process may be performed again using the finally determined threshold value, and the result may be output.

  In the determination process (step S214) of the comparison module 150, as the end condition, when the target control points are within the range, when the measured control points are equal to or less than the target control points, the measured control points are within the target control point range. In addition to the above, two types are exemplified, but there may be cases where the difference between the measured number of control points and the target number of control points is within a predetermined range.

The threshold may be a value corresponding to the number of vectorization processes. For example, normally, the first threshold value (initial threshold value) is desirably a small value in order to guarantee image quality. Therefore, if the number of control points when vectorized with the first threshold is equal to or less than the target number of control points, the processing may be terminated (output from the vectorization result storage module 160). In this case, in order to perform control so as to match the target number of control points, the second and subsequent threshold values need to be larger than the first threshold value. If the threshold value increases, the image quality deteriorates. In order to prevent the image quality from being degraded as much as possible, the number of control points should be as close as possible to the target number of control points. Therefore, the second (second round) and subsequent termination conditions are “the difference between the measured number of control points and the target number of control points is within a predetermined range”.
That is, the first end condition is “the measured number of control points is equal to or less than the target number of control points”. The end condition after the second (second round) is “the difference between the measured number of control points and the target number of control points is within a predetermined range”.

<Second Embodiment>
FIG. 5 is a conceptual module configuration diagram of a configuration example according to the second embodiment. The second embodiment receives an image quality target value and calculates a threshold value for vectorization. A vectorization module 510, a threshold value calculation module 520, a threshold value storage module 530, and a vectorization result storage module 540 are provided. Have.
The vectorization module 510 is connected to the threshold calculation module 520 and the vectorization result storage module 540. The vectorization module 510 is equivalent to the vectorization module 110 in the first embodiment, receives an image, receives a threshold from the threshold calculation module 520, and vectorizes the target image using the threshold. The result of the vectorization process is passed to the vectorization result storage module 540.
The threshold calculation module 520 is connected to the vectorization module 510 and the threshold storage module 530. The threshold calculation module 520 receives the image quality target value, and calculates the threshold using information stored in the threshold storage module 530. Then, the calculated threshold value is passed to the vectorization module 510. The received image quality target value is, for example, an instruction from the user using a touch panel or the like provided in the present embodiment.

The threshold value storage module 530 is connected to the threshold value calculation module 520. The threshold storage module 530 stores a pair of image quality target value and threshold. For example, a threshold / image quality target value table 700 shown in FIG. 7 is stored. The threshold / image quality target value table 700 has a threshold value column 710 and an image quality target value column 720. The threshold value column 710 stores a threshold value. The image quality target value column 720 stores the image quality target value. Any image quality target value can be used as long as it can be converted into a qualitative number. For example, (image quality 1, image quality 2, image quality 3), (high image quality, medium image quality, low image quality), and the like. Then, conversion is performed as follows: high image quality → 1, medium image quality → 2, low image quality → 3. Converting to a qualitative number means this.
The vectorization result storage module 540 is connected to the vectorization module 510. The vectorization result storage module 540 is equivalent to the vectorization result storage module 160 in the first embodiment, stores the vectorization result by the vectorization module 510, and outputs it. Further, at the time of output, file conversion equivalent to that of the vectorization result storage module 160 may be performed.

FIG. 6 is a flowchart illustrating a processing example according to the second exemplary embodiment.
In step S602, the vectorization module 510 receives an image.
In step S604, the threshold value calculation module 520 receives an image quality target value.
In step S606, the threshold value calculation module 520 uses the threshold value storage module 530 to calculate a threshold value corresponding to the image quality target value.
In step S608, the vectorization module 510 performs vectorization of the image received in step S602 using the threshold value calculated in step S606.
In step S610, the vectorization result storage module 540 stores the vectorization result.
In step S612, the vectorization result storage module 540 outputs the vectorization result.

<Third Embodiment (1)>
In the first embodiment, it is assumed that the relationship between the threshold value and the number of control points is a monotone function. If it is a monotonous function, the target point can be reliably reached by using a numerical calculation method such as Newton's method.
However, the relationship between the threshold value and the number of control points is not always monotonous. This will be described with reference to the examples of FIGS. In this graph, the horizontal axis represents the threshold value, and the vertical axis represents the number of control points, showing the relationship between them. The target control point number (the target value in FIGS. 8 and 9) and the threshold value TP that matches the target control point number It is shown.
First, it is assumed that the point A is obtained with the first threshold TA. It is assumed that the point A is larger than the target control point number. At this time, it is assumed that a new threshold value is calculated and the next point B is obtained.
When the next threshold value is calculated using the points A and B, the calculated threshold value is smaller than TA and cannot reach the true value TP.

Therefore, in the third embodiment, the configuration is the same as the module configuration of the first embodiment, but the processing in the threshold calculation module 130 is as follows.
Here, it is assumed that there are two pairs of threshold values and control points. That is, (threshold value T1, number of control points N1), (threshold value T2, number of control points N2).
At this time, two pairs of the past threshold value and the control point number are used to determine whether or not the relationship between the threshold value and the control point number is monotonously decreasing. When the relationship between the threshold value and the number of control points is monotonously decreasing, that is, T1 ≧ T2 and N2 ≧ N1
Or
T2 ≧ T1 and N1 ≧ N2
Only in this case, the operation of the first embodiment is performed. In the previous formula, the equal sign may not be entered. The determination of whether or not the monotonic decrease may be made using three or more pairs of threshold values and control points used in the past.
If this relationship does not hold,
(1) A third threshold value T3 larger than the threshold values T1 and T2 is output to the vectorization module 110 as the next threshold value.
(2) It is assumed that the third threshold value T3 is determined in advance and stored in the threshold value / control score storage module 140.
9, the threshold calculation module 130 calculates a threshold T3 that is larger than the threshold TA at the point A and larger than the threshold at the point B. Then, the vectorization module 110 performs vectorization using the threshold value T3. As a result, the number of control points is smaller than the number of control points at point A. In other words, when the threshold value T3 is used, the relationship with the point A can be monotonously decreased, so that a thick straight line can be drawn as shown in FIG. Can do.

<Third Embodiment (2)>
In the third embodiment (1), the third threshold value T3 is output to the vectorization module 110 as the next threshold value, and the third threshold value is predetermined and stored in the threshold value / control score storage module 140. It was supposed to be.
However, since the monotonous phenomenon may not be realized even when the third threshold is used, the following embodiment is adopted in the third embodiment (2). This will be described with reference to the example of FIG.
First, the number N1 of control points when vectorized with the threshold T1 is acquired (point A in the example of FIG. 10). If this control point number N1 satisfies the end condition, the process ends.
Hereinafter, it is assumed that the number N1 of control points is larger than the number of target control points (target value in FIG. 10). This is because if it is smaller than the target number of control points, it is finished.
When the control point number N1 is not a value that satisfies the termination condition, the control point number N2 is acquired using a predetermined threshold value T2 (point B in the example of FIG. 10). The threshold value T2 may be determined in advance, or may be acquired by the method described in the fourth embodiment described below. If this control point number N2 is a value that satisfies the end condition, the process ends.

Next, the threshold value calculation module 130 determines whether or not the relationship between the threshold value T1 and the threshold value T2, the control point number N1, and the control point number N2 is monotonously decreasing. The determination method may be the same as the method described in the third embodiment (1).
In the case of monotonic decrease, the threshold value calculation module 130 calculates the next threshold value using a method equivalent to the above-described embodiment (for example, the first embodiment).
If not monotonously decreasing, the threshold calculation module 130 calculates a new threshold T3 (T3 = K × T2) by multiplying the past threshold T2 by K (where K> 1). The control point number N3 is acquired using this threshold value T3. Then, the threshold value calculation module 130 determines whether or not the relationship between the threshold values T1 and T3, the control point number N1, and the control point number N3 is monotonously decreasing. Hereinafter, i is increased until the relationship between the threshold value T1, the threshold value Ti, the control point number N1, and the control point number Ni monotonically decreases.
However,
Ti = K × T (i−1)
It is. Note that the threshold T (i−1) is a threshold used immediately before the threshold Ti.
By doing so, a monotonous decrease relationship is guaranteed.

<Third embodiment (2-1)>
In the third embodiment (2), the relationship between the threshold value Ti and the next threshold value T (i-1) is a constant K times, but K is not necessarily a constant. That is, K may be a function K (i) of i. For example, the initial value may be doubled, the next may be three times, and the next may be eight times. That is, K (2) = 2, K (3) = 3, K (4) = 8, and the like may be used. Of course, this figure is an example.
If the value is changed at a stretch with a large value, the accuracy of the threshold estimation is lowered. Therefore, the smallest value is first multiplied. However, if the value is changed with a very small value, the desired threshold value may not be reached easily.
Therefore, the threshold calculation module 130 may calculate the threshold in a direction in which the threshold is increased according to the number of vectorization processes. For example, specifically, the change is made slowly by applying a small multiple at first, and the rate of change is increased by applying a gradually larger multiple.

<Third embodiment (2-2)>
In the third embodiment (2) and (2-1), when the second threshold value T2 is used and the termination condition is not satisfied, the threshold value Ti (i> 2) is calculated using the threshold value T2. Indicated.
However, a predetermined threshold value is set as a calculated threshold value. The threshold value Ti (i> 2) may be determined in advance. For example, a plurality of predetermined threshold values Ti (i> 2) may be stored as a table, and may be sequentially output from the table until it decreases monotonously. This table is stored in the threshold / control point storage module 140.

<Third embodiment (2-3)>
In the third embodiment, the third embodiment (2), etc., only the example of Ti> T (i-1) is shown.
However, when iteratively obtained by the Newton method or the like, there may be a case of Ti <T (i-1).
That is, as in the example of FIG. 11, the upper limit (target value upper limit in FIG. 11) and the lower limit (target value lower limit in FIG. 11) are set, and the control point number N (i− When 1) is below the lower limit of the target number of control points, Ti <T (i-1).
Even in such a case, the relationship between the threshold value and the number of control points is set so as to monotonously decrease.
That is, when the threshold value Ti does not monotonously decrease when the threshold value Ti is used, the threshold value calculation module 130 may determine a sufficiently small threshold value in advance and use the value as the threshold value T (i + 1). Alternatively, a new threshold value T (i + 1) (T (i + 1) = K × Ti) may be calculated. However, in this case, K <1. K may be a constant or a function of i (a value corresponding to the number of times of vectorization processing).

<Fourth embodiment>
In the first embodiment, it is necessary to store two or more predetermined initial threshold values. Since the second and subsequent threshold values are predetermined threshold values, they are completely unrelated to the target image and are not guaranteed to be appropriate threshold values. In the fourth embodiment, the second and subsequent threshold values are calculated from the characteristics of the target image.

In the technique described in Patent Document 4, control points are determined by the following method. This will be described with reference to the example of FIG.
The solid line shown in the example of FIG. 12 is a straight line before curve approximation. The vectorization process is to approximate this straight line like a dotted curve.
First, in the example of FIG. 12A, a curve that approximates a straight line segment group (A to B) is drawn. If the distance between the line segment group and the curve is greater than or equal to the threshold, the line segment group is divided into two. The division result is an example of FIG. As in the example of FIG. 12B, the straight line segment group is divided into two (A to C) and (C to B). Vectorization processing is performed on the divided one to obtain two curves. Dividing in this way doubles the number of control points. If the threshold value is not satisfied even if it is divided into two, the curve is further divided. The curve is divided until the threshold is finally satisfied.
Here, when the threshold is finally satisfied, the distance (error) between the curve and the straight line at the time of division immediately before the division is stored. For example, in the case of the example in FIG. 12, when the threshold value is satisfied in the division of (A to C), the distance between the curve and the straight line at the time of division of (A to B) is stored.
The distance at the time of the previous division can be considered to correspond to the distance when the number of control points is halved.

Therefore, in the fourth embodiment, after the vectorization process, when the division can be finally performed so as to satisfy the threshold value, the distance at the time of division immediately before the division is stored.
FIG. 13 is a conceptual module configuration diagram of a configuration example according to the fourth embodiment. As shown in the example of FIG. 13, the fourth embodiment includes a vectorization module 1310, a control point measurement module 1320, a threshold calculation module 1330, a threshold / control point storage module 1340, a comparison module 1350, a distance storage module 1360, A representative distance calculation module 1370 and a vectorization result storage module 1380 are provided. Compared to the first embodiment, a distance storage module 1360 and a representative distance calculation module 1370 are added, and the other modules are equivalent to the corresponding modules of the first embodiment. Is omitted.

The vectorization module 1310 is connected to the control point measurement module 1320, the threshold calculation module 1330, the distance storage module 1360, and the vectorization result storage module 1380, and performs processing equivalent to that of the vectorization module 110 in the first embodiment. After being performed, the vector is divided until the distance, which is an error between the vectorization result and the line segment in the target image, satisfies a predetermined condition. That is, after the vectorization process, it is determined whether the distance between the vector and the target line segment group is equal to or less than a threshold, the vector is divided until the threshold is satisfied, and the vectorization process is repeated. Do. And when it can divide | segment so that a threshold value may be finally satisfy | filled, the distance at the time of the division | segmentation immediately before the division | segmentation is memorize | stored in the distance storage module 1360.
The distance storage module 1360 is connected to the vectorization module 1310 and the representative distance calculation module 1370. When the vectorization module 1310 can finally divide so as to satisfy the threshold, the distance storage module 1360 Remember the distance.

この関係を図１５に例示する。ここでは、点（Ｔ０，Ｎ０）から点（Ｄ，Ｎ０／２）への直線を引き、この直線が目標制御点数と交差する点を次の閾値Ｔ１として採用する。つまり、閾値算出モジュール１３３０は、ベクトル化モジュール１３１０、制御点数計測モジュール１３２０、閾値・制御点数記憶モジュール１３４０、比較モジュール１３５０、代表距離算出モジュール１３７０と接続されており、初期閾値Ｔ０、その初期閾値Ｔ０を用いたベクトル化処理を行った場合の制御点数Ｎ０、代表距離算出モジュール１３７０によって算出された代表距離Ｄを用いて、閾値を算出して、その算出した閾値をベクトル化モジュール１３１０に渡す。
なお、点（Ｔ０，Ｎ０）から点（Ｄ，Ｎ０／２）へは直線の他に、多次曲線等であってもよい。ここでは、閾値Ｔ０から閾値Ｔ１への算出方法を述べたが、閾値Ｔ２以降についても以下同様に算出する。 The representative distance calculation module 1370 is connected to the threshold value calculation module 1330 and the distance storage module 1360, and uses these distances stored in the distance storage module 1360 to calculate the representative value (representative distance) of the target image. To do. As the representative distance, for example, any one of average values, median values, mode values, maximum values, minimum values, and the like that can be used as representative values as statistics is adopted.
Here, when the representative distance determined in this way is used as a threshold value, the number of control points can be halved. That is, the threshold value when vectorization is now performed is T0, the number of control points is N0, and the representative distance is D. The relationship between the threshold T and the number N of control points is N = f (T). Assume that the threshold T0, the number of control points N0, and the representative distance D have a relationship as shown in Expression (1).

This relationship is illustrated in FIG. Here, a straight line from the point (T0, N0) to the point (D, N0 / 2) is drawn, and a point where this straight line intersects the target control point number is adopted as the next threshold value T1. That is, the threshold value calculation module 1330 is connected to the vectorization module 1310, the control point number measurement module 1320, the threshold value / control point number storage module 1340, the comparison module 1350, and the representative distance calculation module 1370, and the initial threshold value T0 and the initial threshold value T0. The threshold value is calculated using the number of control points N0 when the vectorization process using the symbol is performed and the representative distance D calculated by the representative distance calculation module 1370, and the calculated threshold value is passed to the vectorization module 1310.
The point (T0, N0) to the point (D, N0 / 2) may be a multi-order curve or the like in addition to a straight line. Here, the calculation method from the threshold value T0 to the threshold value T1 has been described.

FIG. 14 is a flowchart illustrating a processing example according to the fourth exemplary embodiment.
In step S1402, the vectorization module 1310 receives an image.
In step S1404, the threshold calculation module 1330 and the comparison module 1350 accept the target control score.
In step S1406, the threshold calculation module 1330 calculates an initial threshold. That is, a predetermined initial threshold value is output to the vectorization module 1310. The predetermined initial threshold value is stored in the threshold value / control score storage module 1340 and is read out.
In step S1408, the vectorization module 1310 performs vectorization on the image received in step S1402, using the threshold value calculated in step S1406. The vectorization processing here is the above-described division processing until the threshold is satisfied (for example, until the distance between the target line segment and the vectorization result is equal to or less than the threshold).
In step S1410, the control point measurement module 1320 measures the number of control points of the vectorization result.
In step S1412, the vectorization result storage module 1380 stores the vectorization result.

In step S1414, the comparison module 1350 compares the number of control points with the target number of control points. If they match (for example, if the number of control points is equal to or less than the target number of control points), the process proceeds to step S1428; otherwise (for example, if the number of control points is greater than the target number of control points), the process proceeds to step S1416.
In step S 1416, the threshold / control score storage module 1340 stores the control scores transferred from the threshold calculation module 1330.
In step S1418, the distance storage module 1360 stores the distance. The distance here is a distance in a state just before the threshold value is satisfied when the vectorization module 1310 performs the vectorization process in step S1408 (that is, immediately before the final division process is performed in step S1408). It is. When there are a plurality of vectors, the number of distances is stored.
In step S1420, the representative distance calculation module 1370 calculates the representative distance in the image using the distance stored in the distance storage module 1360.

In step S1422, the threshold value calculation module 1330 calculates a new threshold value. That is, using the representative distance calculated in step S1420, the threshold value / control score storage module 1340, and the threshold value / control score pair, the next threshold value estimated to match the target control score value is calculated.
In step S1424, the threshold / control score storage module 1340 stores the threshold calculated in step S1422.
In step S1426, the vectorization module 1310 performs the vectorization process again using the new threshold value. Then, the process returns to step S1410. The processes from step S1410 to step S1426 are repeated until they are matched in step S1414.
In step S1428, the vectorization result storage module 1380 outputs the vectorization result according to the instruction of the comparison module 1350.

  A hardware configuration example of the image processing apparatus according to the present embodiment will be described with reference to FIG. The configuration shown in FIG. 16 is configured by a personal computer (PC), for example, and shows a hardware configuration example including a data reading unit 1617 such as a scanner and a data output unit 1618 such as a printer.

  A CPU (Central Processing Unit) 1601 includes various modules described in the above-described embodiments, that is, the vectorization module 110, the control point measurement module 120, the threshold calculation module 130, the comparison module 150, the representative distance calculation module 1370, and the like. It is a control part which performs the process according to the computer program which described the execution sequence of each module.

  A ROM (Read Only Memory) 1602 stores programs, calculation parameters, and the like used by the CPU 1601. A RAM (Random Access Memory) 1603 stores programs used in the execution of the CPU 1601, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus 1604 including a CPU bus.

  The host bus 1604 is connected to an external bus 1606 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 1605.

  A keyboard 1608 and a pointing device 1609 such as a mouse are input devices operated by an operator. The display 1610 includes a liquid crystal display device or a CRT (Cathode Ray Tube), and displays various types of information as text or image information.

  An HDD (Hard Disk Drive) 1611 includes a hard disk, drives the hard disk, and records or reproduces a program executed by the CPU 1601 and information. The hard disk stores a target image, a vectorization result, a threshold / control score table 300, a threshold / image quality target value table 700, and the like. Further, various computer programs such as various other data processing programs are stored.

  The drive 1612 reads data or a program recorded on a removable recording medium 1613 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and the data or program is read out from the interface 1607 and the external bus 1606. , A bridge 1605, and a RAM 1603 connected via the host bus 1604. The removable recording medium 1613 can also be used as a data recording area similar to the hard disk.

  The connection port 1614 is a port for connecting an external connection device 1615 and has a connection unit such as USB, IEEE1394. The connection port 1614 is connected to the CPU 1601 and the like via the interface 1607, the external bus 1606, the bridge 1605, the host bus 1604, and the like. A communication unit 1616 is connected to a network and executes data communication processing with the outside. The data reading unit 1617 is a scanner, for example, and executes document reading processing. The data output unit 1618 is a printer, for example, and executes document data output processing.

  Note that the hardware configuration of the image processing apparatus shown in FIG. 16 shows one configuration example, and the present embodiment is not limited to the configuration shown in FIG. 16, and the modules described in this embodiment are executed. Any configuration is possible. For example, some modules may be configured with dedicated hardware (for example, Application Specific Integrated Circuit (ASIC), etc.), and some modules are in an external system and connected via a communication line In addition, a plurality of systems shown in FIG. 16 may be connected to each other via communication lines so as to cooperate with each other. Further, it may be incorporated in a copying machine, a fax machine, a scanner, a printer, a multifunction machine (an image processing apparatus having any two or more functions of a scanner, a printer, a copying machine, a fax machine, etc.).

In the above description of the various embodiments, the description has been made using mathematical expressions, but the mathematical expressions include those equivalent to the mathematical expressions. The equivalent includes not only the mathematical formula itself, but also transformation of the mathematical formula to the extent that the final result is not affected, or solving the mathematical formula by an algorithmic solution.
Further, in the description of the above-described embodiment, “more than”, “less than”, “greater than”, and “less than (less than)” in a comparison with a predetermined value contradicts the combination. As long as the above does not occur, “larger”, “smaller (less than)”, “more than”, and “less than” may be used.
Note that the various embodiments described above may be combined (for example, a module in one embodiment may be applied to another embodiment, replaced, etc.), and the background art may be used as the processing content of each module. You may employ | adopt the technique demonstrated by. For example, the target control point is received in the first embodiment and the third embodiment, but the image quality target value may be received as in the second embodiment. In this case, a table storing the correspondence between the image quality and the number of control points is prepared in advance, and the number of control points corresponding to the received image quality target value is extracted using the table, and thereafter The processing according to the first embodiment and the third embodiment described above may be performed.
In the above-described fourth embodiment, the second and subsequent threshold values can be calculated. However, the threshold value using the representative distance is limited to the second (second cycle) only. It is good also as a calculation process.

The program described above may be provided by being stored in a recording medium, or the program may be provided by communication means. In that case, for example, the above-described program may be regarded as an invention of a “computer-readable recording medium recording the program”.
The “computer-readable recording medium on which a program is recorded” refers to a computer-readable recording medium on which a program is recorded, which is used for program installation, execution, program distribution, and the like.
The recording medium is, for example, a digital versatile disc (DVD), which is a standard established by the DVD Forum, such as “DVD-R, DVD-RW, DVD-RAM,” and DVD + RW. Standard “DVD + R, DVD + RW, etc.”, compact disc (CD), read-only memory (CD-ROM), CD recordable (CD-R), CD rewritable (CD-RW), Blu-ray disc ( Blu-ray Disc (registered trademark), magneto-optical disk (MO), flexible disk (FD), magnetic tape, hard disk, read-only memory (ROM), electrically erasable and rewritable read-only memory (EEPROM), flash Includes memory, random access memory (RAM), etc. .
The program or a part of the program may be recorded on the recording medium for storage or distribution. Also, by communication, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a wired network used for the Internet, an intranet, an extranet, etc., or wireless communication It may be transmitted using a transmission medium such as a network or a combination of these, or may be carried on a carrier wave.
Furthermore, the program may be a part of another program, or may be recorded on a recording medium together with a separate program. Moreover, it may be divided and recorded on a plurality of recording media. Further, it may be recorded in any manner as long as it can be restored, such as compression or encryption.

110, 510, 1310 ... Vectorization module 120, 1320 ... Control point measurement module 130, 520, 1330 ... Threshold calculation module 140, 1340 ... Threshold / control point storage module 150, 1350 ... Comparison module 160, 540, 1380 ... Vectorization Result storage module 530 ... Threshold storage module 1360 ... Distance storage module 1370 ... Representative distance calculation module

Claims (6)

Vectorizing means for vectorizing an image using a threshold;
Control point number measuring means for measuring the number of control points resulting from vectorization by the vectorization means;
Threshold value for calculating a threshold value based on the number of control points measured by the control point number measuring means when the number of control points measured by the control point number measuring means does not match the target number of control points A calculation means,
The image processing apparatus characterized in that the vectorization means vectorizes the image using the threshold value calculated by the threshold value calculation means. Storage means for storing the threshold value and the number of control points in association with each other;
The threshold value calculating unit calculates a threshold value corresponding to a target number of control points using a correspondence between the threshold value stored in the storage unit and the number of control points. The image processing apparatus described. The threshold calculation means determines whether or not the relationship between the threshold and the number of control points is monotonously decreasing, and calculates the threshold using a predetermined threshold when the relationship between the threshold and the number of control points is not monotonously decreased. The image processing apparatus according to claim 1 or 2. The threshold value calculation means determines whether or not the relationship between the threshold value and the number of control points is monotonically decreasing. If the relationship between the threshold value and the control point number is not monotonously decreased, the threshold value calculating unit calculates the next threshold value using the past threshold value. The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus. The vectorization means divides the vector until an error between the vector and a line segment in the image satisfies a predetermined condition,
Error storage means for storing an error in the previous division when the predetermined condition is satisfied by the vectorization means;
Representative error calculating means for calculating a representative value of errors stored in the error storage means,
The image processing apparatus according to any one of claims 1 to 4, wherein the threshold value calculation unit calculates a next threshold value using the representative value calculated by the representative error calculation unit. Computer
Vectorizing means for vectorizing an image using a threshold;
Control point number measuring means for measuring the number of control points resulting from vectorization by the vectorization means;
Threshold value for calculating a threshold value based on the number of control points measured by the control point number measuring means when the number of control points measured by the control point number measuring means does not match the target number of control points An image processing program for functioning as a calculation means,
The image processing program characterized in that the vectorization means vectorizes the image using the threshold value calculated by the threshold value calculation means.

Images