JP3622439B2 - Image processing apparatus for print inspection, machine-readable recording medium on which rotation angle detection program for print inspection is recorded, and image processing method for print inspection - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention can be a machine-readable recording medium storing a print inspection image processing apparatus and a printing inspection rotational angle detecting program for detecting the rotation angle of the processing object processed object from the processing target image captured and print inspection The present invention relates to an image processing method.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, there has been known an image processing apparatus that captures an image of a processing target with an imaging device, compares the obtained processing target image with a reference image registered in advance, and inspects defects or the like on the appearance of the processing target.
[0003]
In order to compare the two images, it is necessary to perform rotation correction, positional deviation correction, or the like on the processing target image so that the processing target image matches the reference image within the imaging field of view, and then compare the two images.
[0004]
In a conventional image processing apparatus, in order to detect a rotation shift of a processing target image, a reference image is rotated at a predetermined angle to generate a model image at each rotation angle, and the processing target image and a model image at each rotation angle are generated. When the degree of coincidence with a model image at a certain rotation angle is high, it is recognized that there is a processing object in that angular direction. Then, rotation correction is performed based on the angle to match the reference image.
[0005]
[Problems to be solved by the invention]
In the above-described prior art, since it is necessary to compare the processing target image and the model image for each rotation angle, a processing time is required and a memory device having a large storage capacity capable of storing a large number of model images is required. There was inconvenience such as doing.
[0006]
The present invention has been made to solve such a conventional problem, and is an image processing apparatus for printing inspection capable of obtaining a rotation angle of a processing target image at high speed without matching with a large number of model images. Another object of the present invention is to provide a machine-readable recording medium in which a rotation angle detection program for printing inspection is recorded and an image processing method for printing inspection .
[0007]
[Means for Solving the Problems]
The image processing apparatus for print inspection according to claim 1 of the present invention is a reference point deriving unit for obtaining a reference point of an image, and an input for setting a circle having a radius r centered on the reference point with respect to the reference image A display control unit that projects a reference image and a circle having a radius r centered on the reference point set by the input unit on the monitor, and a point on the circumference of the radius r centered on the reference point of the reference image A feature point detecting means for detecting a plurality of feature points having a predetermined feature from among them and obtaining an angle centered on the reference point of each feature point; and a circumference of radius r centering on the reference point of the processing target image Angle deviation detecting means for obtaining an angle deviation with respect to the angle of the feature point of a plurality of points corresponding to the feature point from the above points.
[0008]
According to a second aspect of the present invention, there is provided the image processing apparatus for print inspection according to the first aspect, wherein the feature point is a point whose density value is larger or smaller than a predetermined threshold value, and a processing target corresponding to a plurality of feature points. A plurality of points on the image are points at angles at which the accumulated density value of each point becomes the maximum value or the minimum value.
[0009]
According to a third aspect of the present invention, there is provided the image processing apparatus for print inspection according to the first aspect, wherein the feature point is an absolute value of a difference value between a density value at a certain angle point and a density value at a neighboring angle point. Is a point greater than the threshold.
[0010]
According to a fourth aspect of the present invention, there is provided the image processing apparatus for print inspection according to the first aspect, wherein a plurality of circles having a predetermined radius r are set concentrically, and feature points are selected from points on each circumference. Is detected.
[0011]
According to a fifth aspect of the present invention, there is provided the image processing apparatus for print inspection according to the first aspect of the present invention, further comprising a deviation correction unit that detects an angular deviation as a deviation amount in the rotation direction of the processing target image and performs rotation correction. It is.
[0012]
According to a sixth aspect of the present invention, there is provided a machine-readable recording medium on which a rotation angle detection program for print inspection is recorded, a procedure for deriving a reference point of a reference image, and a radius around the reference point with respect to the reference image. A procedure for setting an r circle and displaying it on a monitor, and detecting a plurality of feature points having a predetermined feature from points on the circumference of a radius r centering on the reference point of the reference image, and centering the reference point A plurality of points corresponding to the feature points among points on the circumference of the radius r centering on the reference point of the processing target image And a program for obtaining an angle deviation with respect to the angle of the feature point.
[0013]
According to a seventh aspect of the present invention, there is provided an image processing method for print inspection, a procedure for deriving a reference point of a reference image, a procedure for inputting a circle having a radius r centered on the reference point, and an input to the reference image. Further, a procedure for projecting a circle with a radius r centered on the reference point on the monitor, a procedure for setting the circle so as to pass through a plurality of shade change portions in the reference image, and a reference point of the reference image A procedure for detecting a plurality of feature points having a predetermined feature from points on the circumference of radius r and obtaining an angle centered on the reference point; a procedure for deriving a reference point of the processing target image; And a procedure for detecting a plurality of points corresponding to the feature points from points on the circumference of the radius r centered on the reference point of the image and obtaining an angle deviation with respect to the angle of the feature points.
[0014]
According to these inventions, the difference value between the density value of the point whose density value is larger or smaller than the predetermined threshold value or the neighboring point among the points on the circumference centering the reference point of the reference image. A plurality of feature points that satisfy a condition such as a large point are detected, a plurality of points satisfying the angular relationship of the plurality of feature points are detected from the circumference of the processing target image, and the feature points of the detected plurality of points are detected. The rotation angle of the processing object can be detected from the angle deviation. Then, the detected angular deviation can be detected as a deviation amount in the rotation direction of the processing target image, and rotation correction can be performed to match the reference image.
[0015]
DETAILED DESCRIPTION OF THE INVENTION
FIG. 1 is a block diagram showing an embodiment of an image processing apparatus for print inspection according to the present invention, which is used for a visual inspection for inspecting a print such as a date attached to a can. In the figure, an image obtained by imaging a processing object such as a can with an imaging unit 1 such as a video camera is output as a video signal, converted into digital image data by an A / D conversion unit 2, and stored in an image memory 3. Remembered.
[0016]
The image data output from the A / D conversion unit 2 or the image data stored in the image memory 3 is converted into an analog video signal by the D / A conversion unit 4 and displayed on the screen of the monitor 6 by the display control unit 5. Is displayed.
[0017]
A central processing unit (CPU) 7 controls the entire apparatus. The central processing unit (CPU) 7 includes a ROM 71 that stores fixed data such as program data, and a RAM 72 that temporarily stores data such as processing results. Derivation of reference point of processing target image, detection of rotation angle of processing target image, rotation correction based on detected angle, detection of displacement amount from reference position, position correction based on detected displacement amount, reference image Perform comparison processing.
[0018]
When these processes are represented in a block diagram, a reference point deriving unit 73 for obtaining a reference point of the reference image and the processing target image, a density value deriving unit 74 for obtaining a density value at a predetermined position of the reference image and the processing target image, and a reference image The feature point detecting means 75 for detecting the feature point of the reference image and calculating the angle with respect to the reference point by detecting the point corresponding to the feature point from the processing target image. A deviation correction unit 77 that corrects a positional deviation amount and a rotational deviation amount of the processing target image with respect to the reference image; a recognition for comparing the processing target image after correcting the deviation amount and the reference image to determine whether the processing target object is good or bad It becomes the processing means 78.
[0019]
In addition, the CPU 7 includes an input unit 8 including a keyboard and a mouse, a reference image memory 9 that stores a reference image for determining the quality of the processing target, and a second image memory 10 that stores the corrected processing target image. Etc. are connected.
[0020]
Although program data for controlling the CPU 7 is stored in the ROM 71, it may be recorded in an external recording medium such as a floppy disk and loaded into the RAM 72 by a reading device (not shown).
[0021]
Next, registration of a reference image and reference data performed prior to an inspection will be described with reference to the flowchart shown in FIG. Based on the registered reference data, a shift amount of the processing target image is detected, and after correcting the shift, the quality of the processing target image is determined based on the reference image.
[0022]
First, a reference object is imaged by the imaging unit 1, and the obtained captured image is stored in the image memory 3 as a reference image K. Further, the reference image K is registered in the reference image memory 9 via the CPU 7 (step S11).
[0023]
Next, the coordinates (xo, yo) of the reference point Ko of the reference image K are obtained and stored in the temporary storage memory 72 in the CPU 7 (step S12). As the reference point Ko, the center point or the barycentric point of the reference image K is selected. Alternatively, when there is a circular pattern whose shape does not change even when rotated, the center point of the circle may be used as the reference point.
[0024]
Next, while viewing the reference image K projected on the monitor 6, a circle having a radius r centered on the reference point Ko is set on the monitor 6 from the input unit 8. This circle is set so as to pass through a plurality of shaded portions in the reference image K. Further, a light / dark threshold t and a step angle α for expressing light / dark in the reference image K at a binary level are set and stored in the RAM 72 (step S13).
[0025]
When pre-processing is completed in this manner, reference data registration processing is performed next. In this process, the density value on the circumference of the radius r centered on the reference point Ko is compared with the threshold value t for each step angle α, and a point having a density value smaller than the threshold value t is detected as a feature point, and the angle And the number of feature points.
[0026]
In the following description, as shown in FIG. 3, assuming an XY coordinate system having an origin at the upper left of the screen, the horizontal direction as the X axis, and the vertical direction as the Y axis, and the Y axis around the reference point Ko. A description will be given on the assumption that parallel axes are rotated clockwise for each angle α. First, the rotation angle θ is set to 0 degree and the number of feature points n is set to 0 (step S14).
[0027]
Next, the density value g of the point on the circumference represented by the rotation angle θ is obtained (step S15). Since the coordinates of the point on the circumference of the radius r are expressed as (xo + r · sin θ, yo + r · cos θ), in this case “θ = 0”, the coordinates of the point on the circumference are (xo, yo + r )
[0028]
Next, it is determined whether the density value g is smaller than the threshold value t (step S16). In this example, the black level is low and the white level is high. If the density value g is smaller than the threshold value t, 1 is added to the number n, and the value of the angle θ at that time is set as the storage angle θn ( Step S17). Then, the storage angle θn is stored in the RAM 72 (step S18). If the density value g is greater than or equal to the threshold value t (step S16), the processing of steps S17 to S18 is jumped.
[0029]
Next, the step angle α is added to the rotation angle θ (step S19), and the processing of steps S15 to S19 is repeated until the rotation angle θ reaches 360 degrees (step S20). When the rotation angle θ reaches 360 degrees, the value n of the number of feature points is stored in the RAM 72 (step S21).
[0030]
Thus, the density value on the circumference having the radius r is compared with the threshold value t for each step angle α, the angle θn of the feature points on the circumference having the density value (black level) smaller than the threshold value t, and the number n of feature points. Are stored in the RAM 72, and the reference data registration process is terminated.
[0031]
In FIG. 4, the circumference of the radius r is set on the character “ABCD”, the density value on the circumference is compared with the threshold value t for each step angle α, and the density value (black level) is smaller than the threshold value t. It is the figure which attached the "*" mark to the feature point on the circumference. In this example, six feature points are detected.
[0032]
Next, the process for obtaining the rotation angle of the processing object will be described with reference to the flowchart shown in FIG. First, the processing object is imaged by the imaging unit 1, and the obtained captured image is stored in the image memory 3 as the processing object image M (step S31).
[0033]
Next, the coordinates (x1, y1) of the reference point Mo of the processing target image M are obtained and stored in the RAM 72 in the CPU 7 (step S32). This reference point Mo is determined in the same manner as the reference point Ko of the reference image K. If the reference point Ko is the center point of the reference image K, the reference point Mo is also the center point, and if the reference point Ko is the center of gravity point, the reference point Mo. Is also the center of gravity.
[0034]
Next, the rotation angle θ is set to 0 degree, the minimum value Gmin of the accumulated density values G of n feature points to be detected is set to the maximum value, and the minimum value θmin of the rotation angle θ is set to 0 degree ( Step S33). Also, the parameter i is set to 1 and the density value G is set to 0 (step S34).
[0035]
Then, the accumulated density value G is accumulated with the density value of the coordinates (x1 + r · sin (θi + θ), y1 + r · cos (θi + θ)) (step S35). This coordinate represents a coordinate on the circumference of an angle (θi + θ) obtained by adding the i-th stored angle θi among the n stored angles θ1 to θn to the angle θ. In this case, since “i = 1”, the coordinates of the angle (θ1 + θ) are represented.
[0036]
The accumulation in step S35 is repeated n times until the parameter i reaches n (steps S36 to S37). When the n accumulation processes are completed, it is determined whether or not the accumulated density value G at that time is smaller than the minimum value Gmin (step S38). If it is smaller, the minimum value Gmin is rewritten to the accumulated density value G, and the angle θ at that time is set as the minimum value θmin (step S39). If it is larger, the process of step S39 jumps.
[0037]
Next, the step angle α is added to the rotation angle θ (step S40), and the processes of steps S34 to S40 are repeated until the rotation angle θ reaches 360 degrees (step S41). When the rotation angle θ reaches 360 degrees, the rotation angle θ of the minimum value θmin is recognized as the rotation angle of the processing target, and the processing target image M is subjected to rotation correction based on the rotation angle θ. Further, the positional deviation correction of (x1-xo) in the X-axis direction and (y1-yo) in the Y-axis direction is performed to match with the reference image K (step S42). After that, the processing target image M is compared with the reference image K, and inspection processing for inspecting defects on the appearance of the processing target is executed (step S43), and the processing is terminated.
[0038]
In this way, the storage angles θ1 to θn of the n feature points detected at the time of registration of the reference image K are added to the rotation angle θ, and the accumulated density value G of the n points θ1 + θ to θn + θ obtained thereby is obtained. It is assumed that the rotation angle θ when the value G is minimum coincides with n feature points detected at the time of registration, and the rotation angle θ at that time is detected as the rotation angle of the processing target image M. FIG. 6 shows this state, and shows a state in which the processing target image M is rotated 90 degrees with respect to the reference image K shown in FIG.
[0039]
In the above-described embodiment, only one circle having a radius r is drawn and the density value is a function f (θ) having only an angle θ. However, as shown in FIG. May be a function f (r, θ) of radius r and angle θ. By doing so, erroneous measurement due to the influence of noise or the like can be prevented.
[0040]
If the reference point cannot be determined in the image, the rotation angle may be detected by performing the above-described processing at each moving position while moving the reference point, as shown in FIG.
[0041]
FIG. 9 is an explanatory diagram showing a specific example for obtaining the reference points Ko and Mo. (A) When the reference image K is circular, the four corners of the circumference are registered as model images K1 to K4, the processing target image M is searched in the model images K1 to K4, and the detected model image K1, A point where a line segment connecting the center positions of both images corresponding to K3 and a line segment connecting the center positions of both images corresponding to the model images K2 and K4 intersects is set as a reference point Mo of the processing target image M. is there.
[0042]
(B) When the reference image K is circular, the circumference is registered as a model image K5, the processing target image M is searched for in the model image K5, and the center position of the image corresponding to the detected model image K5 Is the reference point Mo of the processing target image M.
[0043]
(C) draws a region K6 indicated by a rectangular dotted line around the reference image K, and sets the center of gravity of the region K6 as reference points Ko and Mo.
[0044]
In (d), when there is a circular pattern that does not change in shape when rotated in the reference image K, the circular pattern is registered as a model image K7, and the circular center point of the model image K7 is set as reference points Ko, Mo. To do.
[0045]
In the above-described embodiment, the condition (step S16) is that the density value g of the point on the circumference is smaller than the threshold value t in order to obtain the feature point. However, the density value g is not limited to this. You may make it a condition that it is larger. In this case, the angle θ at which the cumulative density value G is maximized in the processing shown in FIG.
[0046]
In the above-described embodiment, the density value g is the density value of the point on the circumference of the rotation angle θ (step S15). However, the present invention is not limited to this, and the absolute value of the difference value from the density value of the neighboring angle is used. It may be the density value g.
[0047]
The flowchart shown in FIG. 10 is obtained by changing the density value g from the density value of the neighboring angle in the processing procedure shown in FIG. 2, and expressing the density value of the angle θ as f (θ), “g = | F (θ) −f (θ + α · a) | ”(step S15a). A is a natural number (1, 2,...).
[0048]
Further, it is determined whether or not the difference density value g is larger than the threshold value u (step S16a). If it is larger, the angle at that time is stored. By doing this, it is possible to detect a point where the density value changes significantly as a feature point.
[0049]
The flowchart shown in FIG. 11 obtains the rotation angle of the processing target image M based on the feature points detected by the procedure of the flowchart shown in FIG. 10, and is a modification of the flowchart shown in FIG.
[0050]
In this processing, when the cumulative density value G is maximum, it matches the feature point, so the maximum value Gmax of the cumulative density value G is set to the minimum value, and the maximum value θmax of the rotation angle θ is set to 0 degree (step) S33a).
[0051]
Further, the difference value | f (θi + θ) −f (θi + θ + α · a) | is accumulated in the accumulated density value G (step S35a). The accumulation in step S35a is repeated n times until the parameter i reaches n (steps S36 to S37).
[0052]
Next, when n accumulation processes are completed, it is determined whether the accumulated density value G is larger than the maximum value Gmax (step S38a). If it is larger, the maximum value Gmax is rewritten to the accumulated density value G, and the angle θ at that time is set as the maximum value θmax (step S39a). When the rotation angle θ reaches 360 degrees, the rotation angle θ of the maximum value θmax is recognized as the rotation angle of the processing object, and the rotation correction based on the rotation angle θ is performed on the processing object image M (step S42a).
[0053]
The flowchart shown in FIG. 12 shows another method for deriving the density value g, and the two density values g1 and g2 are obtained as follows (step S151).
[0054]
g1 = f (θ−α · a) −f (θ)
g2 = f (θ + α · a) −f (θ)
Next, if the density values g1 and g2 are both negative numbers (steps S152 to S153), the density value g is set to 0 (step S154). If the density values g1 and g2 are both positive numbers (steps S152 to S153) and the density value g1 is smaller than the density value g2 (step S155), the density value g is set to g1 (step S156). If the density value is equal to or greater than g1, the density value g is set to g2 (step S157).
[0055]
If the density value g is obtained in this way, only a black thin line (a line thinner than the width α · a) is regarded as a feature point, and large black dirt is not regarded as noise. Only feature points can be detected stably.
[0056]
The flowchart shown in FIG. 13 shows still another method for deriving the density value g, and the two density values g1 and g2 are obtained as follows (step S151a). The processing in steps S152 to S157 is the same as the processing in the flowchart shown in FIG.
[0057]
g1 = f (θ) −f (θ−α · a)
g2 = f (θ) −f (θ + α · a)
If the density value g is obtained in this way, only white thin lines (thin lines smaller than the width α · a) are regarded as feature points, and white reflected light is not regarded as noise. It is strong against such noise, and only feature points can be detected stably.
[0058]
In addition, in order to obtain | require the rotation angle of the process target image M based on the feature point detected by the procedure shown in FIG. 12 or FIG. 13, it performs according to the procedure shown in FIG.
[0059]
【The invention's effect】
According to the present invention, a plurality of feature points are detected from points on the circumference centered on the reference point of the reference image, and the angular relationship between the plurality of feature points is used as a reference from the circumference of the processing target image. Since multiple corresponding points are detected and the angle of the object to be processed is detected from the angles of these points, it is not necessary to compare with the model image for each rotation angle as in the past, and the processing time is fast. And memory devices for storing model images can be reduced.
[Brief description of the drawings]
FIG. 1 is a block diagram showing an embodiment of an image processing apparatus for print inspection according to the present invention.
FIG. 2 is a flowchart illustrating a reference image and reference data registration process.
FIG. 3 is an explanatory diagram showing a method of detecting feature points on a reference image.
FIG. 4 is an explanatory diagram illustrating a specific example of a method for detecting feature points on a reference image.
FIG. 5 is a flowchart showing processing for detecting a shift amount of an image to be processed.
FIG. 6 is an explanatory diagram illustrating a specific example of a feature point detection method on a processing target image.
FIG. 7 is an explanatory diagram showing another embodiment in which feature points are detected by drawing a plurality of circles around a reference point.
FIG. 8 is an explanatory diagram showing another embodiment for detecting a feature point at each moving position while moving a reference point.
FIG. 9 is an explanatory diagram showing a specific example for obtaining reference points Ko and Mo.
FIG. 10 is a flowchart showing another registration process of reference data.
FIG. 11 is a flowchart showing another shift amount detection process of a processing target image.
FIG. 12 is a flowchart showing another derivation procedure of the density value g.
FIG. 13 is a flowchart showing another derivation procedure of the density value g.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 Image pick-up part 2 A / D conversion part 3 Image memory 4 D / A conversion part 5 Display control part 6 Monitor 7 CPU
8 Input unit 9 Reference image memory 10 Second image memory 71 ROM
72 RAM
73 Reference point deriving means 74 Density value deriving means 75 Feature point detecting means 76 Angle deviation detecting means 77 Deviation correcting means 78 Recognition processing means

Claims (7)

A reference point deriving means for obtaining a reference point of the image;
An input unit for setting a circle with a radius r centered on the reference point with respect to a reference image;
A display control unit that displays on the monitor a circle with a radius r centered on the reference image and the reference point set by the input unit;
Feature inspection for detecting a plurality of feature points having a predetermined feature from points on a circumference of radius r centered on a reference point of the reference image, and obtaining an angle of each feature point with the reference point as the center Means of exiting,
Angle deviation detecting means for obtaining an angle deviation of a plurality of points corresponding to the feature point with respect to the angle of the feature point from points on the circumference of the radius r centering on a reference point of the processing target image. An image processing apparatus for print inspection characterized by the above. 2. The feature point according to claim 1, wherein the feature point is a point having a density value larger or smaller than a predetermined threshold value, and a plurality of points on the processing target image corresponding to the plurality of feature points have a maximum accumulated density value at each point. An image processing apparatus for print inspection, which is a point of an angle that is a value or a minimum value. 2. The image processing apparatus for print inspection according to claim 1, wherein the feature point is a point where an absolute value of a difference value between a density value at a certain angle point and a density value at a neighboring angle point is larger than a threshold value. . 2. The image processing apparatus for printing inspection according to claim 1, wherein a plurality of circles having the predetermined radius r are concentrically set, and the feature points are detected from points on each circumference. The image processing apparatus for print inspection according to claim 1, further comprising a deviation correction unit that detects the angular deviation as a deviation amount in a rotation direction of the processing target image and performs rotation correction. A procedure for deriving a reference point of the reference image;
A procedure for setting a radius r circle centered on the reference point with respect to a reference image and projecting it on a monitor;
A procedure for detecting a plurality of feature points having a predetermined feature from points on a circumference of a radius r centered on a reference point of a reference image and obtaining an angle centered on the reference point;
A procedure for deriving a reference point of the processing target image;
A step of detecting a plurality of points to determine the angular deviation of the angle of the feature point corresponding to the feature point from the point on the circle of radius r centered at the reference point of the process target image, consisting of printing A machine-readable recording medium on which a rotation angle detection program for inspection is recorded. A procedure for deriving a reference point of the reference image;
Entering a circle of radius r centered on the reference point;
Projecting a circle of radius r centered on the reference point input to the reference image on a monitor;
A procedure for setting the circle so as to pass through a plurality of shade change portions in the reference image;
A procedure for detecting a plurality of feature points having a predetermined feature from points on a circumference of a radius r centered on a reference point of a reference image and obtaining an angle centered on the reference point;
A procedure for deriving a reference point of the processing target image;
Printing with a procedure for determining the angular deviation detecting a plurality of points with respect to the angle of the feature point corresponding to the feature point from the point on the circle of radius r centered at the reference point of the processing target image Image processing method for inspection .

Images