JP5802459B2 - Image processing apparatus, method, and program for calculating shape of spiral spring - Google Patents

Description

  The present application relates to a technique for making a spiral spring into a core (thinning). The spiral spring here means a spring formed in a spiral shape from the inner hook to the outer hook when viewed in plan.

  In the quality inspection process of industrial products such as spiral springs, the difference between the shape of the product and the shape defined in the design drawing is examined, and it is inspected whether or not the product is molded according to the design drawing. A product whose deviation from the shape specified in the design drawing is an allowable error is determined as a non-defective product, and a product whose deviation from the shape specified in the design drawing exceeds the allowable error is discarded as a defective product. In the quality inspection process of the spiral spring, the spiral spring is photographed, the core wire of the spiral spring is extracted from an image photographed using a computer, and the difference between the extracted core wire and the shape defined in the design drawing is inspected. In order to perform quality inspection appropriately, it is necessary to accurately extract the core wire of the spiral spring from the captured image. For this reason, a technique for core-forming the shape of an object using image processing has been developed (for example, Patent Document 1).

Japanese Patent Laid-Open No. 11-25279

  The technique of Patent Document 1 is a technique for making a line figure (characters or the like) performed in two-dimensional engraving into a core, and is not a technique for making the shape of a machine element that is an industrial product into a core. In particular, in a spiral spring that is a kind of mechanical element, it is necessary to accurately identify the positions of the inner hook region and the outer hook region from the photographed image and to make a core. On the other hand, the technique of Patent Document 1 does not consider the shape characteristics of the inner hook region and the outer hook region because the object to be cored is not a spiral spring. As a result, in the technique of Patent Document 1, the positions of the inner hook region and the outer hook region may not be accurately identified and cored. The present application provides a technique that can correctly identify the positions of the inner hook region and the outer hook region from the photographed image of the spiral spring and can appropriately perform the subsequent core wire.

The present application discloses an image processing apparatus for making the shape of a spiral spring formed into a spiral shape from an inner hook to an outer hook into a core. The image processing apparatus includes an image input unit that inputs a captured image of a spiral spring, a contour line extracting unit that extracts a contour line of the spiral spring from the input captured image, and a polar coordinate conversion of the extracted contour line. The coordinate transformation means and the polar coordinate transformed contour line “circular coordinate value sequence of the contour line (θ ₁ , θ ₂ ,..., Θ _n ) when moving in one direction on the contour line. And a hook area specifying means for specifying the inner hook area and the outer hook area using the acquired “corner coordinate value string of the contour line”.

In this image processing apparatus, a contour line is extracted from a captured image of a spiral spring, and polar coordinate conversion is performed on the contour line. Then, the “contour line angular coordinate value sequence (θ ₁ , θ ₂ ,..., Θ _n )” is acquired when the circuit travels in one direction on the contour line. When one round is made while moving in one direction on the contour line, the turning direction changes at the positions of the inner hook and the outer hook (that is, counterclockwise from clockwise or counterclockwise from clockwise). Therefore, the positions of the inner hook region and the outer hook region can be accurately specified using the “contour line angular coordinate value sequence (θ ₁ , θ ₂ ,..., Θ _n )”. Therefore, it becomes possible to perform subsequent core wire appropriately.

  In the above image processing apparatus, for example, the hook area specifying unit may include a predetermined area including “pixels” in which the “corner coordinate value sequence of the contour line” has a maximum value or a minimum value as an inner hook area or an outer hook area. May be specified. When the maximum value or the minimum value of the “contour line angular coordinate value sequence” is used, the inner hook region and the outer hook region can be accurately and easily specified.

  The image processing apparatus includes: an inner hook tip point calculating unit that specifies two inner hook end points from the contour line in the specified inner hook region, and calculates the position of the inner hook tip point from the position of the inner hook end point; An outer hook tip point calculating means for specifying two outer hook end points from the contour line in the specified outer hook region and calculating the position of the outer hook tip point from the positions of the outer hook end points; The thinning means for thinning the spiral spring inside and the end of the spiral spring thinned by the thinning means are calculated by the inner hook tip point calculated by the inner hook tip point calculation means and the outer hook tip point calculation means. It is preferable to further comprise a thinned image correcting means for correcting using the outer hook tip point.

  According to such a configuration, the position of the inner hook tip point is calculated from the specified inner hook region, the position of the outer hook tip point is calculated from the specified outer hook region, and these calculated inner hook tip points are calculated. The thinned image is corrected using the positions of the points and the outer hook tip points. For this reason, both ends of the spiral spring can be accurately thinned.

Moreover, this application discloses the image processing method for making the shape of a spiral spring into a core line. In this image processing method, an image input process for inputting a captured image of a spiral spring to a computer, a contour extraction process for extracting a contour line of the spiral spring from the input captured image, and an extracted contour line A coordinate conversion process for converting the polar coordinates, and a contour coordinate that has been converted to polar coordinates, when the circle is moved in one direction while moving in one direction, “an angular coordinate value sequence (θ ₁ , θ ₂ ,. θ _n ) ”is acquired, and the hook area specifying process for specifying the inner hook area and the outer hook area is executed using the acquired“ corner coordinate value string of the contour line ”.
Also by this method, it is possible to correctly specify the positions of the inner hook region and the outer hook region from the captured image of the spiral spring, and it is possible to appropriately perform the subsequent core wire.

The present application further discloses a program for coreizing the shape of the spiral spring. This program includes an image input process for inputting a captured image of a spiral spring to a computer, a contour extraction process for extracting a contour line of the spiral spring from the input captured image, and a polar coordinate conversion of the extracted contour line The coordinate transformation process to be performed, and the “coordinate value sequence of the contour line (θ ₁ , θ ₂ ,..., Θ _n ) when the circular coordinate transformed contour line makes a round while moving in one direction on the contour line. ) ”And the hook area specifying process for specifying the inner hook area and the outer hook area are executed using the acquired“ corner coordinate value string of the contour line ”.
With this program, it is possible to correctly specify the positions of the inner hook region and the outer hook region from the captured image of the spiral spring by using a computer, and it is possible to appropriately perform subsequent core wiring.

The figure which shows the structure of an image processing apparatus. The flowchart which shows the flow of thinning (core wire) by an image processing apparatus. The flowchart which shows the flow of the process which pinpoints a hook area | region. The figure which shows the picked-up image of a spiral spring. The figure which shows the outline extracted from the picked-up image of a spiral spring. The graph of the angular coordinate value sequence obtained by carrying out polar coordinate conversion of the outline. FIG. 6B is a graph of angular coordinate value sequences obtained by connecting discontinuous points in the graph of FIG. 6A. The figure which expands and shows the specified inner hook area | region. The figure which expands and shows the specified outer hook area | region. The figure for demonstrating the process which trims the specified outer hook area | region. The figure which expands and shows the trimmed outer hook area | region. The figure for demonstrating the process which specifies an outer hook end point. The figure which shows the thinning image which thinned the picked-up image (binarized image). The figure which shows the shrinkage | contraction image which shrunk the picked-up image (binarized image). The figure which shows the thinning image obtained from a thinning image and a shrinkage | contraction image. The figure for demonstrating the process which deletes the "beard" from the thinning image of FIG. 14, and the correction | amendment process of a "hook tip" (the 1). FIG. 15 is a diagram (No. 2) for explaining a process of deleting “beard” from the thinned image of FIG. 14 and a process of correcting “hook tip”. The figure which shows the thinning image after deleting "beard". The figure which shows the thinning image after the correction process of a "hook tip". The figure which shows an example of the spiral spring from which the shape of an outer hook area | region differs. The figure which shows the other example of the spiral spring from which the shape of an outer hook area | region differs.

(Example) As shown in FIG. 1, the image processing apparatus 10 of a present Example is an apparatus which image | photographs the spiral spring 30 and outputs the thinning image (core-lined image) of the spiral spring 30 from the image | photographed image. . The image processing apparatus 10 includes a stage 12, an illuminator 14 disposed on the stage 12, a CCD camera 16 fixed to the stage 12, and a computer 22 connected to the CCD camera 16 via a communication line 18. And a display 20 connected to the computer 22.

  The illuminator 14 is a surface light source, and a spiral spring 30 is placed on the light emitting surface thereof. The CCD camera 16 is disposed on the illuminator 14 and photographs the spiral spring 30 placed on the illuminator 14. That is, the spiral spring 30 is illuminated from below by the illuminator 14, and the transmitted light (shadow of the spiral spring 30) of the illuminator 14 is photographed by the CCD camera 16. The illuminator 14 is not limited to transmitted illumination as in the present embodiment, and may illuminate the spiral spring 30 from above. In this case, it is preferable to use a plurality of illuminators or ring-type illuminators so that the spiral spring 30 is illuminated uniformly from the entire circumferential direction.

  Image data captured by the CCD camera 16 is input to the computer 22 via the communication line 18. The computer 22 stores a program for executing various image processing described later. The computer 22 processes the image data of the captured image taken by the CCD camera 16 and creates a thinned image of the spiral spring 30. The computer 22 displays the thinned image of the created spiral spring 30 on the display 20.

  FIG. 2 is a flowchart showing a flow of thinning the spiral spring 30 by the image processing apparatus 10. FIG. 3 is a flowchart showing the flow of the hook area specifying process in step S18 and the hook tip point calculating process in step S20 shown in the flowchart of FIG. The image processing apparatus 10 creates a thinned image of the spiral spring 30 through the processes and processes shown in FIGS. Hereinafter, the flow of processing by the image processing apparatus 10 will be described with reference to the flowcharts shown in FIGS. 2 and 3.

  First, in step S10 of FIG. 2, the spiral spring 30 is photographed by the CCD camera 16. The captured image captured by the CCD camera 16 is input to the computer 22. The input captured image can be, for example, a 256-gradation image in which the density value of the blackest pixel is “255” and the density value of the whitest pixel is “0”. FIG. 4 illustrates a captured image of the spiral spring 30. As shown in FIG. 4, the spiral spring 30 extends spirally from the inner hook 32 to the outer hook 34. The photographed image is a density value image having a density value for each pixel (x, y).

  Next, in step S12 of FIG. 2, the captured image captured in step S10 is binarized. That is, for each pixel (x, y) of the input captured image, when the density value is equal to or greater than a preset set value, “1” is set, and the density value is less than the preset set value. In this case, “0” is set. As a result, the pixel group corresponding to the spiral spring 30 has the density value “1”, and the other pixel groups have the density value “0”. In addition, since the image image | photographed with the CCD camera 16 contains noise, the binarized image also contains noise. For this reason, some pixels that do not correspond to the spiral spring 30 have a density value “1”. The processing from step S12 to S30 described later is executed by the computer 22.

Next, in step S14 of FIG. 2, the center of gravity (c _x , c _y ) of the spiral spring 30 is calculated using the binarized image obtained in step S12. Specifically, the center of gravity (c _x , c _y ) is calculated from the coordinate values (x, y) of the pixel group whose density value is “1” (that is, the pixel group corresponding to the spiral spring 30). To do. In the example shown in FIG. 4, the center of gravity (c _x , c _y ) is located approximately at the center of the spiral spring 30.

  Next, in step S16 in FIG. 2, a contour line is extracted from the binarized image obtained in step S12. The process of extracting the contour line from the binarized image is a known method (for example, Junichi Hasegawa, Yamato Usui, Akira Nakayama, Shige Yokoi, “Basic Techniques of Image Processing <Technical Introduction>”, Technical Review, p. .70-73) can be used. FIG. 5 shows an example of the contour line extracted from the binarized image of the spiral spring 30.

In this embodiment, the contour line extracted in step S16 is represented by the pixel number i (i = 0 to n) and the coordinate value (x _i , y _i ) of the pixel corresponding to the pixel number i. The The pixel number i is a number assigned to the pixels on the contour line, and is assigned according to the following rules. That is, with one pixel set on the contour as the origin, a pixel number i = 0 is assigned to that pixel. The origin can be set at any point on the contour line. Next, pixel number 1 is assigned to the pixel adjacent to the origin. Here, there are two types of pixels serving as the origin: a pixel adjacent in the clockwise direction on the contour line and a pixel adjacent in the counterclockwise direction. In this embodiment, among the pixels adjacent to the origin, pixel number 1 is assigned to the pixel adjacent in the direction of moving counterclockwise. Next, the pixel number 2 is assigned to the pixel adjacent to the pixel with the pixel number 1, and the pixel number is assigned in the same procedure. Thereby, a pixel number is assigned to all the pixels constituting the contour line. As is clear from the above description, when the pixel number i is sequentially moved from the pixel number i to the pixel number n, the contour line is circulated in one direction. In this specification, coordinate value sequences (x ₀ , y ₀ ), (x ₂ , y ₂ ),... (X _n , y _n ) from pixel numbers 0 to n are represented as contour line series (x _i , y _i ) (i = 0 to n).

Next, in step S17 of FIG. 2, the contour line series (x _i , y _i ) (i = 0 to n) obtained in step S16 is converted into a contour line series (r _i , θ _i ) (i = 0). To n). That is, as shown in FIG. 5, the contour series (x _i , y _i ) in the xy coordinate system is set with the center of gravity (c _x , c _y ) calculated in step S14 as the origin and the radius r _i and the declination angle. It represents by (theta) _i . As shown in FIG. 5, the moving radius r _i is the distance between the origin (c _x , c _y ) and the contour line series (x _i , y _i ). The deflection angle θ _i is an angle formed by a straight line connecting the origin (c _x , c _y ) and the contour line series (x _i , y _i ) and the x axis. Therefore, in step S17 , the contour line series (c _x , c _y ) (i = 0 to n) in the xy coordinate system is changed to the contour line series (r _i , θ _i ) (i = 0 to n) in the polar coordinate system. Converted. Here, when the angular coordinate value sequence θ _i (i = 0 to n) obtained from the contour line series (r _i , θ _i ) of the polar coordinate system is graphed, the graph shown in FIG. 6A is obtained. In the graph shown in FIG. 6A, the vertical axis is the declination angle θ _i , and the horizontal axis is the pixel number (contour line element number) i. As is apparent from FIG. 6a, the angular coordinate value sequence θ _i has a numerical value in the range of −180 ° to + 180 °, and is discontinuous at −180 ° and + 180 °.

Next, in steps S18 and S20 in FIG. 2, the hook region is specified and the hook tip point is calculated from the contour line series (r _i , θ _i ) (i = 0 to n) converted in polar coordinates in step S17. Perform the process. These processes will be described along the flowchart shown in FIG.

First, in step S34, S36 in FIG. 3, the contour line of the polar coordinate system created in step S17 in FIG. 2 _{(r i,} θ _i) from (i = 0 to n), extracting the inner hook area and an outer hook region To do. In this embodiment, the contour line _{(r i,} θ _i) of the (i = 0 to n), by utilizing the characteristics of the angular coordinate value sequence θ _{i (i} = _0~n), an inner hook area A The outer hook area B is specified.

In the graph shown in FIG. 6A, the angular coordinate value sequence θ _i (i = 0 to n) is in a range of −180 ° to + 180 °, and the angular coordinate value sequence θ _i has discontinuous points. The processing after step S34 may be performed using an angular coordinate value sequence (FIG. 6b) in which discontinuous points of the graph shown in FIG. 6a are connected, or an angular coordinate value sequence (FIG. 6a) in which the discontinuous points are left. ) May be used.

As is clear from the above description, the contour line series (r _i , θ _i ) (i = 0 to n) starts moving counterclockwise on the contour line from the origin, and goes around the contour line to make a pixel. A number is assigned. For this reason, when the spiral spring is set clockwise when viewed from the inside, a pixel number is assigned while moving counterclockwise from the origin to the inner hook end point (or outer hook end point), and the inner hook end point (or outer hook end point). The pixel number is assigned while moving clockwise from the hook end point to the outer hook end point (or inner hook end point), and the pixel number is moved counterclockwise from the outer hook end point (or inner hook end point) to the origin. Is granted. Therefore, in the graph (FIG. 6b) in which discontinuous points are connected, the angular coordinate value sequence θ _i (i = 0 to n) monotonously decreases (or monotonously increases) from the origin to the inner hook end point (or outer hook end point). From the inner hook end point (or outer hook end point) to the outer hook end point (or inner hook end point), the angular coordinate value sequence θ _i (i = 0 to n) monotonously increases (or monotonously decreases), and the outer hook end point (or The angle coordinate value sequence θ _i (i = 0 to n) monotonously decreases (or monotonously increases) from the inner hook end point) to the origin. Therefore, as shown in FIG. 6b, the function of the angular coordinate value sequence θ _i (i = 0 to n) takes a minimum value near the inner hook end point and takes a maximum value near the outer hook end point.

Therefore, in step S34, the area A including the portion where the angular coordinate value sequence θ _i (i = 0 to n) is the minimum value is specified as the inner hook area. For example, as shown in Figure 6a, as the inner hook regions A, from the pixel number a1 of angular coordinate values theta _a1 adjacent the minimum value is 180 ° angular coordinate values theta _a2 is up to the pixel number a2 as the 180 ° The region is specified so that the minimum value is included in the region (a1 to a2). FIG. 7 shows a contour line series of the identified inner hook region A. As apparent from FIG. 7, the inner hook end point is included in the identified inner hook region A.

In step S36, the region B including the portion where the angular coordinate value sequence θ _i (i = 0 to n) is the maximum value is specified as the outer hook region. For example, as shown in FIG. 6a, as the outer hook region B, the pixel number _{b2 in} which the angular coordinate value θ _b2 is −180 ° from the pixel number b1 in which the angular coordinate value θ _b1 is −180 ° is adjacent to the local maximum value. The region up to is specified, and the maximum value is included in this region (b1 to b2). FIG. 8 shows a contour line series of the identified outer hook region B. As apparent from FIG. 8, the outer hook end point is included in the identified outer hook region B.

As is clear from the comparison between FIG. 7 and FIG. 8, the outer hook region B is wider than the inner hook region A. That is, when the specified outer hook region B (r _k , θ _k ) (k = b1 to b2) is wide, it is preferable to trim the outer hook region B as shown in FIG. In the example shown in FIG. 9, the angle range from the maximum value i _max to the angle α (for example, 40 °) is newly cut out as a new outer hook region B ′ (r _k , θ _k ) (k = b1 ′ to b2 ′). ing. FIG. 10 shows the outer hook region B ′ after trimming. As is clear from FIG. 10, the outer hook area B ′ after trimming is corrected to an appropriate size as compared with the outer hook area B before trimming. Thereby, the calculation amount of the hook tip point calculation process performed in the next step S40 can be reduced. In the above example, since the outer hook region B is wide, the outer hook region B is trimmed. However, when the inner hook region A is wider than the outer hook region B, the inner hook region A may be trimmed. Further, both the inner hook area A and the outer hook area B may be trimmed.

  In the graph shown in FIG. 6b, the local hook takes a local minimum value in the inner hook region A and the local maximum in the outer hook region B. However, if the winding direction of the spiral spring is reversed, the local maximum in the inner hook region is natural. And take a local minimum in the outer hook area.

Next, in step S38, two inner hook end points are specified from the inner hook area A (x _k , y _k ) (k = a1 to a2) specified in step S34, and the inner hook tip is determined from the two inner hook end points. The coordinate value (x _ac , y _ac ) of the point is calculated. In step S40, two outer hook end points are specified from the outer hook regions B ′ (x _k , y _k ) (k = b1 ′ to b2 ′) specified in step S36, and the two outer hook end points are detected. The coordinate value (x _bc , y _bc ) of the hook tip point is calculated. The processing in step S38 and step S40 is different depending on whether the target area is the inner hook area A or the outer hook area B, but the processing procedure is the same. Therefore, here, an example of the process of step S40, that is, the process of specifying the outer hook end point and _obtaining the coordinate value (x _bc , y _bc ) of the outer hook tip point from the specified outer hook end point will be described.

As shown in FIG. 11, there are two outer hook end points in the outer hook region B ′ (x _k , y _k ) (k = b1 ′ to b2 ′), and a contour line is formed at these two outer hook end points. It is almost orthogonal. That is, since the spiral spring 30 is manufactured by forming a spring wire (plate material) into a spiral shape, there are two outer hook end points in the outer hook region B, and contour lines are formed at these two outer hook end points. Are substantially orthogonal. Therefore, first, the points at which the contour lines are substantially orthogonal are extracted from the contour line series B ′ (x _k , y _k ) (k = b1 ′ to b2 ′) specified in step S36. This processing is performed, for example, with respect to each of the contour line series B ′ (x _k , y _k ) (k = b1 ′ to b2 ′) constituting the outer hook region B ′ as shown in FIG. (K) and m (k) are set, and extraction can be performed based on whether these vectors p (k) and m (k) are orthogonal. p (k) and m (k) can be expressed by the following formula (1), for example.

As is apparent from the above equation (1), m (k) is the contour line sequence (x _k−N ) from the point (x _k , y _k ) on the contour line to each point on the contour line N pixels before. , Y _k−N ), (x _{k− (N−1)} , y _{k− (N−1)} ),..., (X _k , y _k ) are averaged. Further, p (k) is a contour line sequence (x _k , y _k ), (x _{k + 1} , y _{k + 1} ) from the point (x _k , y _k ) on the contour line to each point on the contour line N pixels behind. ,..., (X _{k + N} , y _{k + N} ) are averaged. In this embodiment, a range of 0 to N pixels is used to calculate the vectors m (k) and p (k). Here, the set value N is preferably set according to the thickness of the strand of the spiral spring 30 in the image taken in step S10. For example, in the photographed image, when the thickness of the wire of the spiral spring 30 is about X pixels, the set value N can be set to X / 2. Thus, it is preferable to set the number of pixels for calculating m (k) and p (k) depending on how many pixels the plate thickness of the spiral spring 30 corresponds to in the captured image. .

As described above, when the vector m (k) and the vector p (k) are calculated, it is next determined whether or not the vector p (k) and the vector m (k) are orthogonal. In order to determine whether the vector p (k) and the vector m (k) are orthogonal to each other, for example, cos θ _k calculated from the vector p (k) and the vector m (k) can be used (described below) (Refer Formula (2)). Here, θ _k is an angle formed by the vector p (k) and the vector m (k).

At the end point of the hook, the vector m (k) and the vector p (k) are substantially orthogonal. When the vector m (k) and the vector p (k) are substantially orthogonal, θ _k ≈90 ° and cos θ _k ≈0. Accordingly, by searching for two ks _where cos θ _k ≈0, it is possible to identify points (two points) corresponding to the hook end points from the contour line series.

  In this embodiment, two vectors m (k) and p (k) are calculated from the contour line, and the hook end point is calculated using cos θ. However, instead of cos θ, the hook end point is used using sin θ or tan θ. May be specified. Also, instead of using the vectors m (k) and p (k), a linear expression (approximate linear expression) representing the outer shape of the spiral spring is calculated, and the orthogonal condition of the straight lines (the product of the inclinations of the two straight lines is −1) May be used to identify the hook endpoint. Further, the hook end point may be specified using template matching or the like.

The outer hook end points specified as described above are denoted as P _a (x _pa , y _pa ) , P _b (x _pb , y _pb ). When the outer hook end points P _a and P _b are specified, the midpoint between the two outer hook end points P _a (x _pa , y _pa ) and P _b (x _pb , y _pb ) is calculated. The coordinate value (x _bc , y _bc ) of the outer hook tip point is used. As already described, the coordinate value (x _ac , y _ac ) of the inner hook tip point is obtained by a procedure similar to the procedure for _obtaining the outer hook tip point coordinate value (x _bc , y _bc ) described above. Can do.

  When the coordinate values of the inner hook tip point and the outer hook tip point are calculated as described above, the process proceeds to step S22 in FIG. 2 to thin the spiral spring 30 in the photographed image photographed in step S10. Create a thin line image with. As a method of thinning the spiral spring 30 in the photographed image, a conventionally known method (for example, the above-mentioned “Basic Techniques of Image Processing <Introduction to Technology>” (Junichi Hasegawa, Yamato Usui, Akira Nakayama, Shige Yokoi) The method of disclosure etc.) can be used. FIG. 12 shows an example of a thinned image created in step S22. When a lot of noise is included in the captured image captured in step S10, as shown in FIG. 12, the thinned image obtained in step S22 also includes a lot of noise (so-called “loop”). It is.

  Next, in step S24 of FIG. 2, first, the binarized image obtained in step S12 is contracted to create a contracted image (FIG. 13). Next, an AND condition (that is, a point that is a spiral spring in both images) between the created contracted image (FIG. 13) and the thinned image (FIG. 12) obtained in step S22 is taken, and a new thinned image ( 14 and 15) are created. As is apparent from FIGS. 14 and 17, in the new thinned image, the “loop” -like noise is cut and only the “beard” -like noise remains. In addition, as a method of obtaining a contracted image from a binarized image, a conventionally known method (for example, “Basic Techniques of Image Processing <Introduction to Technology>” (by Junichi Hasegawa, Yamato Usui, Akira Nakayama, Shigeki Yokoi / The method disclosed in the technical critics) can be used.

  Next, in step S26 of FIG. 2, the “whisker” noise included in the thinned image created in step S24 is deleted. As shown in FIG. 15, the thinned image created in step S <b> 24 includes many “beard” -like noises in addition to the vicinity of the inner hook tip point and the outer hook tip point. Therefore, the “beard” noise closest to the inner hook tip point and the “beard” noise nearest to the outer hook tip point are deleted by the process described later. Noise is deleted (see FIG. 16). As a result, only one “beard” noise remains in the vicinity of the inner hook tip and / or in the vicinity of the outer hook tip.

In the thinned image created in step S24, the vicinity of the outer hook and the inner hook tip point has a Y-shaped branch shape (see FIG. 15). By performing the process of step S26 on the thinned image, one of the Y-shaped branches near the inner hook tip point and the outer hook tip point is deleted. For example, as shown in FIG. 16, among the outer hook tip points branched in a Y shape, the one closer to the coordinate value (x _bc , y _bc ) of the outer hook tip point calculated in step S40 is left and the farther one Is deleted. In the example shown in FIG. 16, the upper branch is left in the figure, and the lower branch is deleted. In addition, it can process similarly to the above also about an inner hook front-end | tip point. By performing the process of step S26, the thinned image shown in FIG. 17 is obtained.

When all the “beard” -like noises are deleted from the thinned image as described above, the process proceeds to step S28 in FIG. 2, and n pixels set in advance from the inner hook tip point of the thinned image are obtained. The point that becomes the tip after the deletion and the inner hook tip point (x _ac , y _ac ) calculated in step S38 are connected. Also, n pixels set in advance are deleted from the outer hook tip of the thinned image, and the point that becomes the tip after the deletion is connected to the outer hook tip (x _bc , y _bc ) calculated in step S40. To do. Thereby, the process of step S28 is completed. By the processing in step S28, a thin line image (FIG. 18) from which all whiskers are removed is obtained.

  Next, in step S30 in FIG. 2, the thinned image obtained in step S28 is smoothed to create a final thinned image (core image (see FIG. 18)). As a method for smoothing the thinned image, a conventionally known method (for example, a spline interpolation, a least square method, a smoothing method using a digital filter, or the like) can be used.

As described above, in the image processing apparatus 10 according to the present embodiment, the contour line series (x _i , y _i ) (i = 0 to n) of the spiral spring 30 is extracted from the captured image, and the extracted contour line is extracted. The series is subjected to polar coordinate conversion to obtain an outline series (r _i , θ _i ) (i = 0 to n). And the inner hook area | region A and the outer hook area | region B are specified from the characteristic of angle coordinate value row | line | column (theta) _i (i = 0-n). For this reason, the inner hook area A and the outer hook area B can be specified accurately. Further, since the inner hook area A and the outer hook area B can be accurately specified, the inner hook end point and the outer hook end point can also be accurately specified.

In addition, the process of specifying the inner hook area A and the outer hook area B and the process of specifying the inner hook end point and the outer hook end point are a series of contour lines (x _i , y _i ) (i = 0 to n). For this reason, the amount of data to be processed can be reduced, and the processing can be completed in a short time.

  Further, the “loop” and “beard”, which are noise components, are deleted from the thinned image using the accurately calculated inner hook tip point, outer hook tip point, and the like. For this reason, the noise component is appropriately deleted from the thinned image, and an accurate thinned image (core-lined image) can be obtained.

  Specific examples of the present invention have been described in detail above, but these are merely examples and do not limit the scope of the claims. The technology described in the claims includes various modifications and changes of the specific examples illustrated above.

For example, in the above-described embodiment, the center of gravity (c _x , c _y ) of the spiral spring 30 is used as the origin when performing polar coordinate conversion, but the present invention is not limited to such an embodiment. For example, the origin for the polar coordinate conversion may be set not on the inside of the spiral spring 30 but on the outside of the spiral spring 30. Further, the technique of the present application can not only make the spiral spring having the hook shape shown in FIG. 4 a core wire but also core the spiral springs having various hook shapes. For example, a spiral spring having a cut-off type outer hook shape as shown in FIGS. 19 and 20 can be formed into a core.

  In addition, the technical elements described in the present specification or the drawings exhibit technical usefulness alone or in various combinations, and are not limited to the combinations described in the claims at the time of filing. In addition, the technology exemplified in this specification or the drawings achieves a plurality of objects at the same time, and has technical utility by achieving one of the objects.

10: Image processing device 12: Stage 14: Illuminator 16: CCD camera 18: Communication line 20: Display 22: Computer 30: Spiral spring 32: Spiral spring inner hook 34: Spiral spring outer hook

Claims (5)

It is an image processing device for making the shape of a spiral spring formed in a spiral shape from an inner hook to an outer hook into a core wire,
An image input means for inputting a photographed image of the spiral spring;
An outline extraction means for extracting the outline of the spiral spring from the input photographed image;
Coordinate conversion means for converting the extracted contour line into polar coordinates;
The angle at which the “contour line angular coordinate value sequence (θ ₁ , θ ₂ ,..., Θ _n )” is obtained when the contour line transformed in polar coordinates makes a round while moving in one direction on the contour line. Coordinate value sequence acquisition means;
Using the acquired “contour line angular coordinate value sequence”, hook area specifying means for specifying the inner hook area and the outer hook area;
An inner hook tip point calculating means for specifying two inner hook end points from the contour line in the specified inner hook region and calculating the position of the inner hook tip point from the position of the inner hook end points;
Outer hook tip point calculating means for specifying two outer hook end points from the contour line in the specified outer hook region and calculating the position of the outer hook tip point from the positions of the outer hook end points;
Thinning means for thinning the spiral spring in the input captured image;
The end portion of the spiral spring thinned by the thinning means is thinned using the inner hook tip point calculated by the inner hook tip point calculating means and the outer hook tip point calculated by the outer hook tip point calculating means. Thinning image correction means for correcting by removing the noise component of the spiral spring,
An image processing apparatus. The thinned image correcting means includes a “whisker-like” noise in the vicinity of the inner hook tip point calculated by the inner hook tip point calculating means, and a nearest neighbor of the outer hook tip point calculated by the outer hook tip point calculating means. The image processing apparatus according to claim 1, wherein the “beard” -like noise included in the spiral spring thinned by the thinning means is deleted, leaving the “beard” -like noise . The thinned image correcting means includes
  For the Y-shaped branch of the inner hook portion of the spiral spring from which the “beard” -shaped noise other than the nearest “beard-shaped noise” has been deleted, the tip of the inner hook calculated from the Y-shaped branch Delete the branch with the tip point farther away from the point,
  For the Y-shaped branch of the outer hook portion of the spiral spring from which the “beard” -like noise other than the nearest “beard” -like noise has been deleted, the tip of the outer hook calculated from the Y-shaped branch Delete the branch with the tip point farther away from the point,
  For each of the inner hook portion and the outer hook portion from which one of the Y-shaped branches has been deleted, a predetermined number of pixels are deleted from the tip of the hook portion, and the calculation is performed corresponding to the point that becomes the tip after the deletion. The image processing apparatus according to claim 2, wherein a thinned image of the spiral spring is acquired by connecting the hook tip point. This is an image processing method for making the shape of a spiral spring spirally formed from an inner hook to an outer hook into a core, and the computer performs the following processing:
Image input processing for inputting a captured image of the spiral spring;
An outline extraction process for extracting the outline of the spiral spring from the input photographed image;
A coordinate conversion process for converting the extracted contour line into a polar coordinate;
The angle at which the “contour line angular coordinate value sequence (θ ₁ , θ ₂ ,..., Θ _n )” is obtained when the contour line transformed in polar coordinates makes a round while moving in one direction on the contour line. Coordinate value sequence acquisition processing,
Using the acquired “contour line angular coordinate value sequence”, the hook area specifying process for specifying the inner hook area and the outer hook area;
An inner hook tip point calculating means for specifying two inner hook end points from the contour line in the specified inner hook region and calculating the position of the inner hook tip point from the position of the inner hook end points;
Outer hook tip point calculating means for specifying two outer hook end points from the contour line in the specified outer hook region and calculating the position of the outer hook tip point from the positions of the outer hook end points;
Thinning means for thinning the spiral spring in the input captured image;
The end portion of the spiral spring thinned by the thinning means is thinned using the inner hook tip point calculated by the inner hook tip point calculating means and the outer hook tip point calculated by the outer hook tip point calculating means. Thinning image correction means for correcting by removing the noise component of the spiral spring,
An image processing method for executing It is a program for making the shape of a spiral spring formed in a spiral shape from an inner hook to an outer hook into a core, and the computer performs the following processing:
Image input processing for inputting a captured image of the spiral spring;
An outline extraction process for extracting the outline of the spiral spring from the input photographed image;
A coordinate conversion process for converting the extracted contour line into a polar coordinate;
The angle at which the “contour line angular coordinate value sequence (θ ₁ , θ ₂ ,..., Θ _n )” is obtained when the contour line transformed in polar coordinates makes a round while moving in one direction on the contour line. Coordinate value sequence acquisition processing,
Using the acquired “contour line angular coordinate value sequence”, the hook area specifying process for specifying the inner hook area and the outer hook area;
Inner hook tip point calculation processing for specifying two inner hook end points from the contour line in the specified inner hook region and calculating the position of the inner hook tip point from the position of the inner hook end points;
An outer hook tip point calculation process that specifies two outer hook end points from the contour line in the specified outer hook region, and calculates the position of the outer hook tip point from the position of the outer hook end point;
A thinning process for thinning the spiral spring in the input captured image;
The end of the spiral spring thinned by the thinning process is thinned using the inner hook tip point calculated by the inner hook tip point calculation process and the outer hook tip point calculated by the outer hook tip point calculation process. Thinning image correction processing to correct by deleting the noise component of the spiral spring,
A program that executes

Images