JP2018060343A - Image processing apparatus, image processing method and image processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing apparatus capable of extracting a straight line included in an image with a small quantity of calculation.SOLUTION: An edge extraction unit 1 extracts an edge in the horizontal (or vertical) direction included in an image signal. A Hough space storage unit 2 stores in the Hough space an angle indicative of the complete horizontal (or vertical) direction and a data represented by a vote value for which the first pixel number of pixels constituting the edge for a first pair of the angle indicative of the complete horizontal (or vertical) direction and a distance from the origin to a straight line is voted. An inclined straight line fitting unit 3 calculates an actual inclination angle of the edge, the second pixel number of the edge included in an inclined straight line, and the distance from the origin to the inclined straight line. A Hough space correcting unit 4 adds the second pixel number to a voting value for a second pair of an actual inclination angle and a distance to the straight line inclined from the origin and subtracts the second pair of voting values from the first number of pixels to correct the Hough space. A straight line extracting unit 5 extracts the data of the voting value exceeding a predetermined threshold value in the corrected Hough space as a straight line.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an image processing apparatus, an image processing method, and an image processing program for extracting a straight line included in an image.

  For example, a concrete wall such as a wall inside a tunnel may crack due to deterioration over time. As described in Non-Patent Document 1, it has been proposed to detect the presence or absence of cracks by photographing a concrete wall surface with a camera. Cracks can be detected by extracting the edges of the captured image.

  However, when an edge of an image obtained by photographing a wall surface inside a tunnel is extracted, a substantially linear edge may be extracted in addition to an edge indicating a non-linear crack. The straight edge is generated due to factors such as the construction method of the wall surface and the structure of the wall surface. If a straight line can be extracted from an image in which non-linear cracks and straight lines are mixed, the straight lines can be removed.

  As described in Patent Documents 1 and 2 and Non-Patent Document 1, Hough transform is often used to extract a straight line included in an image.

JP 2006-252400 A JP 2014-146326 A

Obata, Yamazaki, Tsubouchi, “Automated Inspection of Cracks on Indoor Walls Using a Moving Camera,” Proceedings of the 13th Image Sensing Symposium, IN3-02, (CD-ROM), 2007. (http: //www.jsk. (tu-tokyo.ac.jp/~yamazaki/rp/SSII2007_yamazaki.pdf)

  The straight line is often horizontal or vertical, but may be slightly inclined from horizontal or vertical. Straight lines may occur intermittently. In an image obtained by photographing a wall surface inside a tunnel, a plurality of straight lines having a low contrast and not necessarily in a horizontal direction or a vertical direction may occur in the entire frame.

  In order to extract a plurality of straight lines existing in the entire frame using the Hough transform, a huge amount of calculation is required. There is a need for an image processing apparatus, an image processing method, and an image processing program that can extract a straight line with a small amount of calculation while using the Hough transform.

  It is an object of the present invention to provide an image processing apparatus, an image processing method, and an image processing program that can extract a straight line included in an image with a small amount of calculation using Hough transform.

  The present invention provides an edge extraction unit that extracts at least one of a horizontal direction and a vertical direction included in an input image signal, and the edge extracted by the edge extraction is a complete horizontal or vertical direction. The first pixel of the angle indicating the complete horizontal direction or the vertical direction and the distance from the origin of the frame of the image signal to the straight line is assumed by performing a Hough transform on each pixel constituting the edge. And a Hough space storage unit for storing data represented by a vote value obtained by voting the first number of pixels constituting the edge in a Hough space, and an actual inclination angle of the edge is calculated. The edge is fitted to an inclined straight line, and the second pixel number of the edge included in the inclined straight line and the distance from the origin to the inclined straight line are calculated. The second pixel number is added to a second set of voting values of the fitting unit, the actual tilt angle and the distance from the origin to the tilted straight line, and the voting value of the first set A Hough space correction unit that corrects the Hough space by subtracting the second number of pixels, and a straight line extraction unit that extracts data of voting values exceeding a predetermined threshold in the Hough space corrected by the Hough space correction unit as a straight line An image processing apparatus is provided.

  The present invention extracts at least one of a horizontal direction and a vertical direction included in an image signal, regards the extracted edge as a complete horizontal or vertical straight line, The edge is formed for a first set of an angle indicating a complete horizontal direction or a vertical direction and a distance from the origin of the frame of the image signal to the straight line by performing a Hough transform on each of the constituting pixels. The data represented by the vote value obtained by voting the first number of pixels to be stored is stored in the Hough space, the actual inclination angle of the edge is calculated and the edge is fitted to the inclined straight line, the inclination A second pixel number of the edge included in a straight line and a distance from the origin to the inclined straight line are calculated, and an actual inclination angle and a distance from the origin to the inclined straight line are calculated. The second number of pixels is added to the voting value of the set, and the second number of pixels is subtracted from the voting value of the first set to correct the Hough space, and a predetermined value in the corrected Hough space is determined. Provided is an image processing method characterized by extracting data of voting values exceeding a threshold value as a straight line.

  According to the present invention, a computer extracts at least one of a horizontal direction and a vertical direction included in an image signal, and the extracted edge is regarded as a complete horizontal or vertical straight line. Then, Hough transform is performed on each pixel constituting the edge, and a first set of an angle indicating a complete horizontal direction or a vertical direction and a distance from the origin of the frame of the image signal to the straight line Storing the data represented by the vote value obtained by voting the first number of pixels constituting the edge in a Hough space, and calculating the actual inclination angle of the edge to a straight line inclined the edge. And calculating a second pixel number of the edge included in the inclined straight line, a distance from the origin to the inclined straight line, and the actual inclination The second number of pixels is added to a second set of vote values of an angle and the distance from the origin to the inclined straight line, and the second number of pixels is subtracted from the first set of vote values. Thus, there is provided an image processing program characterized by executing a step of correcting a Hough space and a step of extracting data of voting values exceeding a predetermined threshold in the corrected Hough space as a straight line.

  According to the image processing apparatus, the image processing method, and the image processing program of the present invention, a straight line included in an image can be extracted with a small amount of calculation while using the Hough transform.

It is a block diagram which shows the image processing apparatus of one Embodiment. It is a figure which shows an example of the image which image | photographed the wall surface of the concrete containing a non-linear crack line and a some straight line. It is a figure for demonstrating Hough conversion. It is a figure for demonstrating the inclination straight line fitting operation | movement of a horizontal straight line. It is a figure for demonstrating the inclination straight line fitting operation | movement of a vertical straight line. It is a flowchart which shows the procedure performed with the process by the image processing method of one Embodiment, and the image processing program of one Embodiment. It is a block diagram which shows a 1st modification. It is a block diagram which shows the 2nd modification.

  Hereinafter, an image processing apparatus, an image processing method, and an image processing program according to an embodiment will be described with reference to the accompanying drawings. In this embodiment, an image obtained by photographing a concrete wall such as a wall inside a tunnel is an example of an image including a straight edge. An image including a straight edge is not limited to an image obtained by photographing a concrete wall surface.

<Image processing device>
First, the configuration and operation of an image processing apparatus according to an embodiment will be described with reference to FIG. In FIG. 1, the edge extraction unit 1 is sequentially input with pixels constituting a frame 10 of an image signal obtained by photographing a concrete wall as shown in FIG. The image signal input to the edge extraction unit 1 is, for example, a still image signal, and may be a grayscale image signal.

  The frame 10 of the image signal includes a non-linear crack line 11 which is a crack generated on a wall surface, a plurality of straight lines 12a to 12c extending in a substantially horizontal direction, and a plurality of straight lines 13a to 13i extending in a substantially vertical direction. . The straight lines 12a to 12c extending in the substantially horizontal direction are collectively referred to as the horizontal straight line 12, and the straight lines 13a to 13i extending in the substantially vertical direction are collectively referred to as the vertical straight line 13.

  The horizontal straight line 12 is slightly inclined from the horizontal, and the vertical straight line 13 is slightly inclined from the vertical. The horizontal straight line 12 may include a completely horizontal straight line, or the vertical straight line 13 may include a completely vertical straight line.

  In FIG. 2, the upper left corner of the frame 10 is the origin coordinate (0, 0), and the pixel coordinate is (i, j). The width (number of horizontal pixels) of the frame 10 is w, and the height (number of vertical pixels) is h. In the present embodiment, the horizontal direction is 0 °, and the vertical direction rotated clockwise is 90 °.

  For example, the edge extraction unit 1 extracts an edge of an image by applying a differential filter to 9 pixels of 3 horizontal pixels and 3 vertical pixels centered on the target pixel. For example, a Sobel filter is used as the differential filter. The edge extraction unit 1 classifies the pixel of interest into three types: an edge in the horizontal direction (hereinafter, horizontal edge), the pixel of interest is an edge in the vertical direction (hereinafter, vertical edge), and the pixel of interest is not an edge. Divide.

  The Hough space storage unit 2 performs Hough transform on each pixel extracted as being a horizontal edge or a vertical edge, and stores the Hough transformed data in the Hough space.

  Here, general Hough transform will be described. As shown in FIG. 3, when the coordinates before the Hough transform are (x, y), a straight line L passing through the coordinates (x, y) is represented by ρ = x · cos θ + y · sin θ. θ is an angle relative to the horizontal line, and ρ is the distance from the origin (0,0) to the straight line L. There are an infinite number of pairs of the angle θ and the distance ρ of the straight line passing through the coordinates (x, y). In general Hough transform, a candidate for a set of angle θ and distance ρ is voted, and one set of angle θ and distance ρ is selected by majority vote. Such a Hough transform requires a huge amount of calculation.

  Therefore, in the present embodiment, the angle of the horizontal straight line 12 and the vertical straight line 13 shown in FIG. 2 is regarded as a complete horizontal direction or a straight line in the vertical direction, and each of the pixels constituting the horizontal straight line 12 and the vertical straight line 13 is determined. It is assumed that the Hough transform is performed by limiting to 0 ° and 90 °, respectively.

  As can be seen from FIG. 3, the straight line L is a vertical straight line when the angle θ is 0 °, and the straight line L is a horizontal straight line when the angle θ is 90 °. Therefore, the Hough space storage unit 2 performs the Hough transform by subtracting the angles 0 ° and 90 ° defined in FIG. 2 from the angle 90 ° and converting them to an angle θ used in general Hough transform. However, in order to simplify the description, the angle in the Hough space will be described with the angle defined in FIG. 2 unless it is noted that the angle θ is shown in FIG.

  In this embodiment, since the angle of the horizontal straight line 12 is limited to 0 °, a straight line including a horizontal edge at an arbitrary coordinate (i, j) has an angle of 0 ° from the origin as shown by a broken line in FIG. Can be represented by j. The Hough space storage unit 2 votes 1 for the Hough space H [0, j]. Further, in the present embodiment, the angle of the vertical straight line 13 is limited to 90 °, and therefore a straight line including a vertical edge at an arbitrary coordinate (i, j) has an angle of 90 °, as indicated by a broken line in FIG. The distance from the origin can be represented by i. The Hough space storage unit 2 votes 1 for the Hough space H [90, i].

  The Hough space storage unit 2 votes 1 in the Hough space H [0, j] or H [90, i] in each pixel extracted as a horizontal edge or a vertical edge in the frame 10. As a result of voting in the frame 10, the Hough space H [0, j] at the vertical position j where the horizontal straight line 12 is located and the Hough space H [90, i] at the horizontal position i where the vertical straight line 13 is located as shown in FIG. Is a large value.

  The Hough space storage unit 2 includes a first number of pixels constituting an edge with respect to a first set of an angle indicating a complete horizontal direction or a vertical direction and a distance from the origin of the frame 10 to a straight line. Data represented by the vote value obtained by voting is stored. In the case of the image shown in FIG. 2, there are a plurality of first sets.

  The inclined straight line fitting unit 3 performs fitting so that the extracted straight line matches the actual horizontal straight line 12 or vertical straight line 13. The inclined straight line fitting unit 3 is a strict horizontal straight line depending on whether the pixels of the horizontal edge are arranged in the horizontal direction, or the pixels of the horizontal edge go up or down in order toward the right side of the frame 10. It is determined whether or not there is. The inclined straight line fitting unit 3 determines whether the vertical edge pixels are arranged in the vertical direction, or whether the vertical edge pixels are sequentially shifted to the right side or the left side as they go to the lower side of the frame 10. It is determined whether or not it is a strict vertical straight line.

  The operation of the inclined straight line fitting unit 3 will be specifically described with reference to FIGS. 4 and 5. As shown in FIG. 4, the inclined straight line fitting unit 3 counts the number of horizontal edges on the straight line connecting the coordinates (0, j) and the coordinates (w, j + n). Here, n is ± w × 0.1, for example. The angle range shown in FIG. 4 is about ± 6 ° with respect to the horizontal direction from arctan (0.1) = 5.7 °. An arbitrary angle within this angle range is defined as a positive or negative angle p.

  The maximum count value of the horizontal edge is edhmax, the angle p when the maximum count value edhmax is obtained is the angle pmax, and the distance between the straight line of the angle pmax and the coordinate (0, 0) is rh. The maximum count value of the horizontal edge is represented by the number of pixels.

  As shown in FIG. 5, the inclined straight line fitting unit 3 counts the number of vertical edges on the straight line connecting the coordinates (i, 0) and the coordinates (i + m, h). Here, m is ± h × 0.1, for example. The angle range shown in FIG. 5 is also about ± 6 ° with respect to the vertical direction. An arbitrary angle within this angle range is defined as a positive or negative angle q.

  The maximum count value of the vertical edge is edvmax, the angle q when the maximum count value edvmax is obtained is the angle qmax, and the distance between the straight line of the angle qmax and the coordinate (0, 0) is rv. The maximum count value of the vertical edge is represented by the number of pixels.

  In this way, the inclined straight line fitting unit 3 calculates the actual inclination angle (pmax or qmax) of the horizontal edge and the vertical edge, and fits the horizontal edge and the vertical edge to an inclined straight line. The inclined straight line fitting unit 3 calculates a second pixel number (edhmax or edvmax) of a horizontal edge or a vertical edge included in the inclined straight line and a distance (rh or rv) from the origin to the inclined straight line.

  The Hough space correction unit 4 has a horizontal straight line 12 that is determined by the inclined straight line fitting unit 3 to have an angle pmax that is not 0 ° (the actual angle is not 0 °) and an angle qmax that is not 90 °. The Hough space in the vertical straight line 13 determined to be inclined (not the actual angle is 90 °) is corrected.

  The Hough space correction unit 4 adds the count value edhmax to the vote value of the Hough space H [pmax, rh], and adds the count value edvmax to the vote value of the Hough space H [90 + qmax, rv]. Further, the Hough space correction unit 4 subtracts the count value edhmax from the vote value of the Hough space H [0, j], and subtracts the count value edvmax from the vote value of the Hough space H [90, i].

  In this way, the Hough space correction unit 4 adds the second number of pixels to the second set of voting values of the actual inclination angle and the distance from the origin to the inclined line, and the first set of voting values The Hough space is corrected by subtracting the second number of pixels. This corrects the Hough space.

  The straight line extraction unit 5 extracts data whose voting value in the Hough space exceeds a predetermined threshold value thr as a straight line. As described above, according to the image processing apparatus of the present embodiment, a straight line included in an image can be extracted with a small amount of calculation while using the Hough transform.

  The image correction unit 6 receives an image signal and information indicating the horizontal straight line 12 and the vertical straight line 13 extracted by the straight line extraction unit 5. Information indicating the horizontal straight line 12 and the vertical straight line 13 can be represented by the coordinates of the pixels constituting the horizontal straight line 12 and the vertical straight line 13 respectively.

  Based on the information indicating the horizontal straight line 12 and the vertical straight line 13, the image correction unit 6 deletes the horizontal straight line 12 and the vertical straight line 13 from the image shown in FIG. 2 or makes the horizontal straight line 12 and the vertical straight line 13 inconspicuous. Or the like, the image is corrected so that the crack line 11 is visually conspicuous. If the corrected image signal is supplied to a display (not shown) to display the corrected image, the inspector can easily recognize the crack line 11.

  The image processing apparatus illustrated in FIG. 1 may be configured by hardware, may be configured by software, or may be configured by combining hardware and software.

  The image processing apparatus shown in FIG. 1 may be composed of a central processing unit (CPU) and a memory of a microcomputer, or an integrated circuit. The image processing apparatus shown in FIG. 1 may be functionally realized by a computer program (image processing program) stored in the memory being executed by the CPU.

<Image processing method and image processing program>
Next, a procedure executed by the image processing program according to the embodiment will be described with reference to FIG. FIG. 6 also shows processing by the image processing method of one embodiment.

  In FIG. 6, when the image processing program is executed and processing is started, the CPU captures an image signal in step S11. In step S12, the CPU extracts a horizontal edge and a vertical edge. Steps S <b> 11 and S <b> 12 correspond to processing executed by the edge extraction unit 1.

  In step S21, the CPU votes 1 in the Hough space H [0, j] for each pixel of the horizontal straight line 12. Step S21 corresponds to the processing executed in the Hough space storage unit 2.

  In step S22, the CPU counts the number of horizontal edges on a straight line passing through the coordinates (0, j) with an inclination of an angle (0 + p) °. In step S23, the CPU sets the angle p when the maximum count value edhmax is obtained as the angle pmax, and calculates the distance rh between the straight line having the angle pmax and the origin. Steps S <b> 22 and S <b> 23 correspond to processing executed by the inclined straight line fitting unit 3.

  In step S24, the CPU adds the count value edhmax to the vote value of the Hough space H [pmax, rh], and subtracts the count value edhmax from the vote value of the Hough space H [0, j] in step S25. . Steps S <b> 24 and S <b> 25 correspond to processing executed by the Hough space correction unit 4.

  In parallel with the above steps S21 to S25, the CPU executes steps S31 to S35. In step S31, the CPU votes 1 in the Hough space [H90, i] for each pixel of the vertical straight line 13. Step S31 corresponds to the processing executed in the Hough space storage unit 2.

  In step S32, the CPU counts the number of vertical edges on a straight line passing through the coordinates (i, 0) with an inclination of angle (90 + q) °. In step S33, the CPU calculates the distance rv between the straight line having the angle qmax and the origin by setting the angle q when the maximum count value edvmax is obtained as the angle qmax. Steps S <b> 32 and S <b> 33 correspond to processing executed by the inclined straight line fitting unit 3.

  In step S34, the CPU adds the count value edvmax to the vote value of the Hough space H [90 + qmax, rv], and subtracts the count value edvmax from the vote value of the Hough space H [90, i] in step S35. . Steps S34 and S35 correspond to processing executed by the Hough space correction unit 4.

  In step S41, the CPU selects data satisfying the Hough space H [θ, ρ]> thr as a straight line to be extracted, and the process ends. Thereby, the horizontal straight line 12 and the vertical straight line 13 of FIG. 2 are extracted. Step S <b> 41 corresponds to a process executed by the straight line extraction unit 5. The angle θ and the distance ρ in step S41 are the straight line angle defined in FIG. 3 and the distance from the origin to the straight line.

  According to the image processing method and the image processing program of the present embodiment, the same effects as those obtained by the image processing apparatus of the present embodiment described above can be obtained. The image processing program may be stored in a non-transitory storage medium, or distributed via a communication line such as the Internet.

<First Modification>
In order to facilitate the correction of the image signal in the image correction unit 6, the configuration may be as shown in FIG. In FIG. 7, the illustration from the Hough space storage unit 2 to the Hough space correction unit 4 is omitted. In FIG. 7, the binary conversion unit 7 binarizes the image signal and supplies it to the image correction unit 6.

  If it does in this way, the part of the crack line 11, the horizontal straight line 12, and the vertical straight line 13 in FIG. 2 will be represented by white, and another part will be represented by black. The image correcting unit 6 easily replaces the horizontal straight line 12 and the vertical straight line 13 from white to black on the basis of the information indicating the horizontal straight line 12 and the vertical straight line 13 to easily change the horizontal straight line 12 and the vertical straight line 13. Can be erased.

  With the configuration shown in FIG. 7, when the corrected image signal is supplied to a display (not shown) and the corrected image is displayed, only the crack line 11 is displayed in white, so that the inspector easily recognizes the crack line 11. be able to.

<Second Modification>
In the embodiment described above, the horizontal straight line 12 is a straight line slightly inclined from the horizontal, and the vertical straight line 13 is a straight line slightly inclined from the vertical. When the straight line extending in the horizontal direction is greatly inclined from the horizontal and the straight line extending in the vertical direction is greatly inclined from the vertical, n of the coordinates (w, j + n) and m of the coordinates (i + m, h) in the inclined straight line fitting unit 3 are increased. It must be a value, and the amount of calculation in the inclined straight line fitting unit 3 increases.

  In such a case, as shown in FIG. 8, it is preferable to provide an affine transformation unit 8 before the edge extraction unit 1. The affine transformation unit 8 rotates the image signal so that a straight line greatly inclined from the horizontal approaches the horizontal (or completely horizontal), and a straight line inclined greatly from the vertical approaches the vertical (or completely vertical). Let The operations after the edge extraction unit 1 are the same as those in FIG. In FIG. 8, the illustration of the image correction unit 6 is omitted.

<Third Modification>
It is good also as a structure which combined the 1st modification shown in FIG. 7 and the 2nd modification shown in FIG.

  The present invention is not limited to the embodiment described above, and various modifications can be made without departing from the scope of the present invention. In the present embodiment, it is assumed that the image signal includes both the horizontal straight line 12 and the vertical straight line 13, but only one of the horizontal straight line 12 and the vertical straight line 13 may be included. In this case, a process of extracting only one of the horizontal straight line 12 and the vertical straight line 13 may be executed. Although the image signal input to the image processing apparatus is a still image signal, it may be a moving image signal.

  When the purpose is only to extract a straight line included in the image, the image correction unit 6 can be omitted. Of course, an image processing apparatus, an image processing method, and an image processing program for extracting a straight line included in an image may be used for purposes other than the purpose of correcting the image.

DESCRIPTION OF SYMBOLS 1 Edge extraction part 2 Hough space storage part 3 Inclined straight line fitting part 4 Hough space correction part 5 Straight line extraction part 6 Image correction part 7 Binary conversion part 8 Affine transformation part

Claims (4)

An edge extraction unit that extracts at least one edge of the horizontal direction and the vertical direction included in the input image signal;
The edge extracted by the edge extraction unit is considered to be a straight line in a complete horizontal direction or a vertical direction, Hough transforms each pixel constituting the edge, and an angle indicating a complete horizontal direction or a vertical direction The data represented by the vote value obtained by voting the first number of pixels constituting the edge with respect to the first set of the distance from the origin of the frame of the image signal to the straight line is stored in the Hough space. A Hough space storage to store;
The actual inclination angle of the edge is calculated and the edge is fitted to an inclined straight line, and the second number of pixels of the edge included in the inclined straight line and the distance from the origin to the inclined straight line are calculated. An inclined straight line fitting part to be calculated;
The second pixel number is added to a second set of voting values of the actual tilt angle and the distance from the origin to the tilted straight line, and the second pixel is calculated from the first set of voting values. A Hough space correction unit that corrects the Hough space by subtracting the number;
A straight line extraction unit that extracts data of voting values exceeding a predetermined threshold in the Hough space corrected by the Hough space correction unit;
An image processing apparatus comprising: The image signal is an image signal indicating an image including a non-linear line and a straight line in a horizontal direction or a vertical direction,
The image correction unit for correcting the image signal based on the straight line extracted by the straight line extraction unit so that the non-straight line included in the image is easily recognized visually. An image processing apparatus according to 1. Extracting at least one edge of the horizontal direction and the vertical direction included in the image signal;
The extracted edge is regarded as a straight line in the complete horizontal direction or the vertical direction, and each pixel constituting the edge is subjected to a Hough transform to obtain an angle indicating the complete horizontal direction or the vertical direction, and the image signal. Storing the data represented by the vote value obtained by voting the first number of pixels constituting the edge in the Hough space for the first set of the distance from the origin of the frame to the straight line,
The actual inclination angle of the edge is calculated and the edge is fitted to an inclined straight line, and the second number of pixels of the edge included in the inclined straight line and the distance from the origin to the inclined straight line are calculated. Calculate
The second pixel number is added to a second set of voting values of the actual tilt angle and the distance from the origin to the tilted straight line, and the second pixel is calculated from the first set of voting values. Subtract the number to fix the Hough space,
An image processing method characterized by extracting data of voting values exceeding a predetermined threshold in a modified Hough space as a straight line. On the computer,
Extracting at least one edge of the horizontal direction and the vertical direction included in the image signal;
The extracted edge is regarded as a straight line in the complete horizontal direction or the vertical direction, and each pixel constituting the edge is subjected to a Hough transform to obtain an angle indicating the complete horizontal direction or the vertical direction, and the image signal. Storing in the Hough space data represented by a vote value obtained by voting the first number of pixels constituting the edge with respect to the first set of the distance from the origin of the frame to the straight line; ,
The actual inclination angle of the edge is calculated and the edge is fitted to an inclined straight line, and the second number of pixels of the edge included in the inclined straight line and the distance from the origin to the inclined straight line are calculated. A calculating step;
The second pixel number is added to a second set of voting values of the actual tilt angle and the distance from the origin to the tilted straight line, and the second pixel is calculated from the first set of voting values. Subtracting the number to correct the Hough space;
Extracting data of voting values exceeding a predetermined threshold in the modified Hough space as a straight line;
An image processing program for executing

Images