JP2000339458A - Image processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processor which can previously check whether the resetting of a search area is appropriate or not at the time of resetting. SOLUTION: A reference position coordinate P in a reference picture detection area for positioning D1 in a reference search area D2 is detected on picture data of a measurement object which is image-picked up and a measurement object position coordinate Q in a measurement object reference picture detection area D3 in a measurement search area D4 is detected. The propriety of an inspection object (position of label picture 70) is judged from the relative position relation of the measurement object position coordinate Q with respect to the reference potion coordinate P. When the reference search area D2 and the measurement search area D4 are reset, the reference search area D2 and the measurement search area D4 after resetting are judged to be within a whole take-in picture data area 100 or not. When they are not, direction arrow marks M and N to which a CCD camera 2 or the measurement objects are to be shifted are displayed.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus for defect inspection, and more particularly, to a method for detecting a defect (for example, a displacement of a label) of a semi-finished product or a product manufactured by being provided in a production line inspection system. Involved in image processing equipment,
More particularly, the present invention relates to a technique for enabling a user to check in advance whether resetting of a search area is appropriate or not at the time of resetting.

[0002]

2. Description of the Related Art FIG. 3 is also used in an embodiment which will be described later, and is a visual representation of captured image data which is captured by a CCD camera and temporarily stored in a frame memory. It is. Here, it is assumed that the measurement object is a container, and the inspection object is a label (two-dimensional position of the label) attached to the container. Sign 10
0 is the whole area of the captured image data, 50 is the container image, 51
Is a container body image, 60 is a cap image, 70 is a label image, and 80 is a background image. Here, for example, the cap image 60 is cap image data,
The label image 70 is label image data.

[0003] The determination as to whether or not the label image 70 is misaligned is performed as follows. First, it is necessary to determine a reference position. For example, the cap image 60
For example, a positioning reference image detection area D1 is set in the upper left corner, and a slightly larger reference search area D2 surrounding the positioning reference image detection area D1 is set around the positioning reference image detection area D1. And label image 7
The detection point of 0 is set to, for example, the lower right corner, and the measurement target reference image detection area D3 is set there, and a larger measurement search area D4 surrounding the measurement target reference image detection area D3 is set around the measurement target reference image detection area D3. The reference search area D2 is set at a position where the upper left corner of the cap image 60 is assumed to be present inside the entire area 100 of the image data captured by the CCD camera. The measurement search area D4 includes the container body image 51 and the background image 80. Border 8
Set to a position assumed to contain 1.

First, a reference search area D2 is searched at high speed in the whole area 100 of image data captured by a CCD camera to find a cap image 60, which is compared with template image data corresponding to the upper left corner of the cap image read from the memory. The positioning reference image detection area D1 is extracted based on the pattern matching to be performed, and the reference position coordinates P (X0, Y0) at the upper left corner of the cap image 60 are detected.

Next, the reference position coordinates P (X
0, Y0), the measurement search area D4 is set on the image data. This is performed, for example, as follows. A horizontal displacement .DELTA.X and a vertical displacement .DELTA.Y corresponding to the difference between the reference search area D2 and the measurement search area D4 registered in advance in the memory are calculated by calculation, and the reference position coordinates P (X0, Y0) are calculated. ) To the displacement ΔX, Δ
The coordinates at which the displacement of Y has been performed are represented by coordinates Q (X1, Y
The measurement search area D4 is set based on the measurement target position coordinates Q (X1, Y1). Here, X1 = X0 + ΔX (1) Y1 = Y0 + ΔY (1) Y1 = X0 + ΔX (1) Y1 = Y0 + ΔY (1) ... (2)

Then, a high-speed search is performed in the measurement search area D4 to confirm that the boundary 81 between the container body image 51 and the background image 80 is included.
Finding what seems to be 0, extracting a measurement target reference image detection area D3 based on pattern matching of comparing pixels with template image data corresponding to the lower right corner of the label image read from the memory and extracting the measurement target reference image detection area Calculate the degree of coincidence between the two image data in D3,
It is determined whether or not the degree of coincidence is equal to or greater than a predetermined threshold. If the degree of coincidence is equal to or greater than the threshold, it is determined that there is no defect, that is, there is no displacement. It is determined that there is a displacement. No defect means
This means that the position of the label attached to the actual container is normal or within an allowable range. Note that a case where there is a defect indicates a case where no label is attached, and this is determined when the degree of coincidence is equal to or less than a predetermined value.

[0007] Various positional deviations of the positioning reference image detection area D1 occur. For example, the direction of the CCD camera may change due to vibration, etc.
Even if the field of view of the camera changes and images are taken at the same shutter timing (trigger timing), the four regions D1 to D4 within the entire captured image data region 100 are misaligned. It is possible that the setting position of the CCD camera and the direction of the field of view yesterday have changed today. In some cases, it may fluctuate over time.

This will be described with reference to FIG. FIG. 4 is also used in an embodiment to be described later, in which the positioning reference image detection area is shifted from D1 in FIG. 3 to D1a. The state in the case of FIG. 3 is shown by a two-dot chain line. That is, it is assumed that the container image 50, the container body image 51, the cap image 60, and the label image 70 all have a positional shift of ΔCX in the horizontal direction and ΔCY in the vertical direction inside the entire captured image data area 100. Accordingly, the measurement target reference image detection area shifts from D3 to D3a. Note that the reference search area D2 and the measurement search area D4 are not changed.

When the container image 50 or the like is displaced in the entire captured image data area 100, the coordinates of the positioning reference image detection area D1a obtained as a result of the search in the reference search area D2 are expressed as Pa (X0a, Y0a). Then, the displacement amounts ΔCX, ΔC in the horizontal direction and the vertical direction
Y is ΔCX = X0a−X0... ...... (3) ΔCY = Y0a−Y0 ……………………………………… ... (4). Then, assuming that the measurement target position coordinates Qa (X1a, Y1a) of the measurement target reference image detection area D3a after the displacement based on the positioning reference image detection area D1a after the displacement, X1a = X0 + ΔX + ΔCX ... ... (5) Y1a = Y0 + ΔY + ΔCY (6) The correction may be made as shown in (6). Note that these equations (5),
(6) is obtained from the expressions (1) and (2) as follows: X1a = X1 + ΔCX (7) Y1a = Y1 + ΔCY (7) (8) is equivalent to correcting the coordinates Q (X1, Y1) of the original measurement target reference image detection area D3 by the positional deviation amounts ΔCX, ΔCY. Is equivalent.

[0010] In this manner, the displacement of the reference image detection area D3a to be measured is corrected. In the subsequent pattern matching, a search is performed in the measurement search area D4 to determine whether or not the degree of coincidence in pixel comparison between the image data and the template image data in the measurement target reference image detection area D3a is greater than a threshold value. Is determined.

When it is determined that there is a defect, that is, a position shift, an alarm or a warning is generally issued. At that time, the production line may be stopped immediately or after waiting for a while to see the situation.

[0012]

The above-mentioned prior art has the following problems. During operation of the production line, a problem such as a matching error may occur in the image processing of the pattern matching. That is, there is a case where a warning is issued that there is a displacement even though no displacement has occurred in the label. Or, conversely, there may be a case where a misalignment is determined to be no misalignment despite the misalignment of the label. In short, an error occurs, but if the error occurrence rate is high, the production yield decreases. Therefore, when such a situation occurs or is expected to occur, the reference search area D2 and the measurement search area D4 are reset.

Also, for some reason, the object to be measured may protrude outward from the field of view of the CCD camera, ie, the entire captured image data area 100. Even if the measurement object itself does not protrude, the measurement search area D4 may protrude. And such a situation continues,
It may not return to the original normal state. In this case, the pattern matching becomes impossible continuously or the precision of the pattern matching is greatly reduced. This leads to a decrease in production yield. Therefore, when such a situation occurs or is expected to occur, the reference search area D2 and the measurement search area D4 are reset as described above.

By resetting the reference search area D2 and the measurement search area D4, the error occurrence rate approaches zero. In this case, in some cases, the field of view is adjusted by changing the angle of view of the CCD camera.

Such resetting is performed by a manual operation (artificial operation) by an operator. The operation of resetting the search area according to this manual will be described. First, the position of the measurement target is adjusted so that the entire measurement target falls within the field of view of the CCD camera. At this time, of course, the transport means such as a conveyor for transporting the measurement object is stopped. An image of the object to be measured captured by the CCD camera is displayed on a monitor. The operator adjusts the position of the object to be measured or adjusts the field of view of the CCD camera while also taking into account the state of projection on the monitor.

After confirming that the relative positional relationship of the image of the object to be measured in the entire area 100 of the image data captured by the CCD camera is sufficient, the reference search area D2 and the measurement search area D4 are reset. . First, the reference search area D2 is reset, and then the measurement search area D4 is reset. First, the reference search area D
Regarding the setting of 2, the reference search area D2 is set around the cap image 60 such that the upper left corner of the cap image 60 is the reference image detection area D1 for positioning. Subsequently, the process proceeds to the setting of the measurement search area D4. For example, a measurement search area D4 is set around the label image 70 such that the lower right corner of the label image 70 is the measurement target reference image detection area D3.
All such work is done manually.

The problem of the prior art is that the reference search area D2 and the measurement search area D4 after resetting as described above are not checked to see if they are within the allowable range. As a result, the production line started to operate. This is because it does not have such a check function. for that reason,
If the setting is outside the allowable range, the operation is started without noticing that, and the setting error can be recognized only after a trouble occurs. If it is not known until a trouble occurs, there is a possibility that a defective product has already occurred before the trouble occurs, and there is a possibility that the yield may decrease. In addition, the production line must be stopped and resetting must be performed, resulting in a significant decrease in production efficiency. The work load is also heavy for the operator. In addition, the resetting does not necessarily eliminate the possibility of causing a trouble again, and does not guarantee that trouble will occur again.

In order for the user to know in advance, for example, the user performs a calculation on a desk or the like, so that the reference search area D2 or the measurement search area D4 as a result of resetting does not protrude from the whole area 100 of the captured image data. It is sufficient to check whether the setting is reset or not, but such a calculation is very troublesome.

The present invention has been made in order to solve the above-mentioned problem, and provides an image processing apparatus which can check in advance whether resetting of a search area is appropriate or not at the time of resetting. It is intended to be.

[0020]

The image processing apparatus according to the first aspect of the present invention, which aims to solve the above-mentioned problems, has the following configuration. To facilitate understanding, reference numerals used in the drawings relating to the embodiments described later are also described. For the image data of the imaged measurement target, the reference position coordinates P (X0, Y0) in the positioning reference image detection area D1 in the reference search area D2 are detected, and the measurement target reference image detection area D3 in the measurement search area D4. The coordinates Q (X1, Y1) of the measurement target position are detected, and the quality of the inspection target is determined from the relative positional relationship of the coordinates Q (X1, Y1) of the measurement target position with respect to the reference position coordinates P (X0, Y0). An image processing apparatus for performing initialization in a state where the relative positions of the reference search area D2 and the measurement search area D4 and the captured image entire area 100 are shifted from each other; By performing correction so that the relative positional relationship between the two search areas D2 and D4 with respect to 100 is the same even after resetting, only the measurement search area D4 is moved. In this case, it is determined whether or not the reference search area D2 needs to be reset, that is, whether the reference search area D2 and the measurement search area d4 after the reset are included in the entire captured image data area 100. It is configured to determine.
According to this configuration, the following operation is provided. That is,
In the resetting of the reference search area D2 and the measurement search area D4, it is determined whether or not the reset reference search area D2 and the measurement search area D4 fall within the entire captured image data area 100. Since the check can be already performed at the setting stage, in the actual measurement execution, even if the positional deviation of the reference position coordinate P is within the range of the reference search area D2, the position is reset regardless of the positional deviation. The trouble that the later reference search area D2 or measurement search area D4 protrudes from the whole captured image data area 100 does not occur. In addition, since the reference search area D2 and the measurement search area D4 after the resetting are automatically checked to determine whether or not they fall within the entire captured image data area 100, the operator can calculate each time on the desk. There is no annoyance of artificial judgment. Further, in the actual measurement execution, no protruding trouble occurs, and it is possible to suppress the occurrence of troubles such as the production line being stopped unexpectedly during its operation, and a decrease in the production efficiency due to the resetting of the setting is caused. You don't have to.

According to a second aspect of the present invention, in the first aspect, when the reference search area and the measurement search area after the resetting do not fall within the entire captured image data area, It is configured to display an instruction of a moving direction for changing the field of view of the imaging means or an instruction of a moving direction of the measurement target. According to this configuration, the operator who sees the instruction of the moving direction,
Since the imaging means or the object to be measured may be moved in accordance with the instruction, the work of the correction in the resetting can be performed quickly and easily.

According to a third aspect of the present invention, in the image processing apparatus according to the first and second aspects, the misalignment determination condition is corrected as necessary, and the corrected misalignment determination condition falls within an allowable range. It is configured to determine whether or not it fits. The operation of this configuration is as follows. There may be an algorithm in which the misalignment determination condition changes depending on the movement of the imaging unit or the movement of the measurement target. In this case, the misregistration determination condition is also corrected, and it is checked whether the condition is within the allowable range. If not, the misregistration determination condition is corrected again. Therefore, it is possible to automatically find an appropriate misalignment determination condition.

According to a fourth aspect of the present invention, there is provided the image processing apparatus according to any one of the first to third aspects, wherein the measurement target is transported, and the measurement target is located at a required inspection point on the transport route. An arrival detection means for detecting arrival is provided, and the detection signal from the arrival detection means is used as a trigger to image the measurement object and determine the quality of the inspection object. According to this configuration, even if the object to be measured is conveyed, the inspection object can be imaged with good timing, and the above-described operation can be obtained.

According to a fifth aspect of the present invention, in the image processing apparatus according to the first to fourth aspects, the inspection target of the measurement target is a two-dimensional position on image data. Judgment of the labeling position of the semi-finished product such as a container or the label attached to the product or the printing position of the printed contents or judgment of the sticking or printing, judgment of the position of the semiconductor chip pin, judgment of the printed circuit board In the image processing apparatus for determining the quality of the arrangement of the electronic components mounted thereon, the quality of the arrangement of the plurality of components placed on the transport tray, and the like, the above-described operation is effectively exerted. You.

[0025]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of an image processing apparatus according to the present invention will be described in detail with reference to the drawings.

FIG. 1 is a block diagram showing an electrical configuration of the image processing apparatus according to the embodiment. In FIG. 1, the symbol 1
Is a CCD camera comprising an optical system including a photographing lens and an aperture, and a CCD (Charge Coupled Device) which is a typical example of solid-state image pickup means. An optical image is formed on a CCD, and the formed optical image is photoelectrically converted by the CCD and output as an electric signal. An A / D converter 3 digitizes an analog video signal (CCD output signal) from the CCD camera 2 and converts it into image data.
Outputs a timing signal to the CCD camera 2, the A / D converter 3, and the frame memory 5 to control the timing of acquiring image data,
And a camera / display controller that outputs a timing signal to the D / A converter 11 to control the timing of displaying the acquired video signal, 5 is a frame memory as an example of image data temporary storage means, and 6 is the entire system. CPU (Central Processing Unit) as an example of control means for controlling the CPU, 7 is a ROM (Read Only Memory) storing a program for calculation and control by the CPU 6,
Reference numeral 8 denotes a RAM (random access memory) for assisting calculation and control of the CPU 6 and storing data, 9 denotes an input / output interface for inputting and outputting data and control signals to and from the outside, 10 denotes a CPU 6, ROM 7, RAM 8 ,
A bus connecting the camera / display controller 4, the frame memory 6 and the input / output interface 9, a D / A converter 11 for converting image data from the frame memory 5 via the camera / display controller 4 into an analog video signal, Reference numeral 12 denotes a monitor such as a CRT (cathode ray tube) or a liquid crystal display (LCD) connected to the image processing apparatus 1 via an interface (not shown) and a cable. The frame memory 5 is an image memory capable of storing at least one frame or more of image data.
AM, SRAM, DRAM, and the like are generally used. Here, it is assumed that a VRAM that can operate independently of the bus 10 is used. The camera / display controller 4 and the frame memory 5 are connected via a parallel bus line. Also, the input / output interface 9
Inputs such as a wired remote controller for setting and inputting parameters, threshold values, other conditions, necessary data, and the like necessary for the RAM 8 for initial values, judgment criteria, and the like, and for giving necessary instructions. It is possible to connect an alarm 14 and an indicator for notifying an operator or an operator of the situation or the judgment result inside the operation unit 13 or the image processing apparatus 1 via individual cables. Note that a wireless remote controller can be used instead of the wired remote controller. In this case, the output terminal of the remote controller receiver is connected to the input / output interface 9. As the alarm 14, an LED (light emitting diode), a fluorescent display tube or any other light emitting element, a lamp, or a buzzer such as a buzzer can be applied. Further, the input / output interface 9 has a necessary external storage device 15.
Can be connected. Examples of the external storage device 15 include a magnetic recording device such as a hard disk drive, a magneto-optical recording device such as an MO (Magneto Optics) disk drive and a DVD (Digital Versatile Disk) -RAM drive, a flash memory, and an EEPROM.
There are semiconductor storage devices such as OM and other nonvolatile memories.

FIG. 2 shows an outline of a production line inspection system 20 to which the image processing apparatus 1 having the above configuration is applied. In FIG. 2, reference numeral 21 denotes a conveyance unit such as a conveyor for conveying the measurement target 30, and 22 denotes an example of an arrival detection unit for detecting arrival of the measurement target 30 conveyed near the conveyance unit 21. The inspection point D
P. The photoelectric sensor 22 is connected to the input / output interface 9 of the image processing apparatus 1 via a cable 23. For convenience of explanation, FIG.
Although the CCD camera 2 is drawn outside the image processing apparatus 1, the CCD camera 2 is actually integrated with the image processing apparatus 1. However, the CCD camera 2 may be configured separately from the image processing apparatus 1 and both may be connected by a cable. X indicates the transport direction of the transport unit 21.

In FIG. 2, the measurement object 30 is
While cap 32 is sealed to container body 31,
The container 30 in which the label 40 is attached to the container body 31 is shown. Note that the container 30 may be anything such as a plastic container such as a glass bottle and a PET bottle, a paper pack container, and an aluminum can. Further, the contents of the container 30 may be anything such as a liquid, a viscous body, a powder, and a granule. The label 40 may be of any type, such as a label with a product name or design, or a description or specification of the product. The shape of the label 40 may be a rectangle, a square, an ellipse, a circle, or any other shape. In this case, the label 40 is assumed to be a rectangle. Furthermore, as will be described later, it is noted that the measurement target 30 need not be limited to a container, but may be any object as long as it can be inspected by image processing. Keep it. The container 30 here is only an example.

Next, the operation of the image processing apparatus 1 applied to the production line inspection system 20 in the embodiment configured as described above will be described.

A plurality of measuring objects 30 are continuously conveyed at predetermined intervals by the driven conveying means 21. When there is a measurement target 30 that has reached the inspection point DP, the arrival detection means 22 installed at the inspection point DP operates. When the arrival detecting means 22 is a photoelectric sensor, the following operation is performed. The photoelectric sensor 22 includes:
It comprises a light emitting element such as a laser diode and a light receiving element such as a photodiode. A laser beam or the like emitted from the light emitting element hits the measurement object 30 and is reflected. The reflected light is captured by the light receiving element, converted into an electric signal, and amplified. Thus, arrival detection is performed.

When the arrival detecting means 22 detects that the measurement object 30 has reached the inspection point DP, the arrival detecting means 22 sends the detection signal to the image processing apparatus 1 as a trigger signal. In the image processing apparatus 1, a trigger signal input via the input / output interface 9 is provided to the CPU 6 via the bus 10. When the CPU 6 receives the trigger signal, the camera / display controller 4
Output a start signal. Upon input of the activation signal, the camera / display controller 4 outputs a timing signal to the CCD camera 2, A / D converter 3, frame memory 5 and D / A converter 11.

When a timing signal is input to the CCD of the CCD camera 2, the electronic shutter is opened and operated, and an image of the object 30 to be measured is captured. That is, the optical image of the measurement target 30 is transmitted through the imaging lens to the CC.
An image is formed on the surface of D, and the CCD accumulates the optical image as a signal charge. When a timing signal is input, the CCD is transferred from the photodiode of the photosensitive section to the vertical transfer CCD and from the vertical transfer CCD to the horizontal transfer CCD. Transfer
It is output as a video signal via an output amplifier. The A / D converter 3 is activated by the input of a timing signal,
An analog video signal (CCD output signal) input from the camera 2 is converted into digital image data. This A /
If the bit number of the D converter 3 is, for example, 8 bits, the image data has 256 gradations. The frame memory 5 receives the timing signal, and stores the image data for one frame from the A / D converter 3 in synchronization with the A / D converter 3. It is needless to say that 8 bits are merely an example and may be changed as appropriate according to specifications.

The camera / display controller 4 reads out the written image data from the frame memory 5 in parallel with the writing of the image data to the frame memory 5,
The data is transferred to the D / A converter 11. The D / A converter 11 converts the transferred image data into an analog video signal and outputs it to the monitor 12. It is assumed that the video signal reaching the monitor 12 has been converted into a required format suitable for the monitor 12 such as the NTSC system by a required video encoder (not shown). In this way,
From the time when the arrival of the measurement target 30 is detected, an image in which the measurement target 30 is a subject image is projected on the monitor 12 in real time.

When the writing of one frame of image data to the frame memory 5 is completed, the camera / display controller 4 outputs a write completion signal to the CPU 6. The CPU 6 that has received the write completion signal outputs the RO
In accordance with the program read from M7 and the image processing calculation conditions read from RAM 8, frame memory 5
To read the image data for one frame stored in the frame memory 5. Then, an operation for required image processing is executed in a unit of one pixel or a block which is a set of a plurality of pixels, and the operation result for determination is represented by R
Store in AM8. Next, the calculation result is compared with a determination reference read from the RAM 8 to determine whether or not the calculation result is normal.

The RAM 8 has an input operation unit 13 in advance.
, Image processing calculation conditions and criteria are set and registered via the input / output interface 9 and the bus 10.
The image processing calculation conditions include coordinate data of a reference search area D2 for pattern matching and a measurement search area D4. The judgment criteria include template image data.

The specific image processing is as follows. FIG. 3 is an explanatory diagram of the operation of pattern matching. In FIG. 3, reference numeral 50 denotes a container image which is image data of the measurement object shown in FIG. 2, that is, the container 30, 51 denotes a container body image which is image data of the container body 31, and 6.
0 is a cap image which is image data of the cap 32, 70 is a label image which is image data of the label 40, and 80 is a background image. As shown in FIG.
In the entire captured image data area 100 captured by the CCD camera and stored in the frame memory 5, the reference search area D2 is searched at high speed and the cap image 60
Then, based on the pattern matching of comparing the pixel with the template image data corresponding to the upper left corner of the cap image read from the RAM 8 and extracting the reference image detection area D1 for positioning, the cap image 6
The reference position coordinate P (X0, Y0), which is the upper left corner of 0, is detected.

Next, the reference position coordinates P (X
0, Y0), the measurement search area D4 is set on the entire image data area 100. That is, a horizontal displacement amount ΔX and a vertical displacement amount ΔY corresponding to the difference between the coordinates of the reference search area D2 and the coordinates of the measurement search area D4 are calculated, and the displacement amounts ΔX, The measurement search area D4 is set with the coordinates at which the displacement of ΔY has been performed as a starting point.

Then, a high-speed search is performed in the measurement search area D4 to confirm that the boundary 81 between the container body image 51 and the background image 80 is included.
Based on the pattern matching in which a pixel which seems to be 0 and pixel comparison is performed with template image data corresponding to the lower right corner of the label image read from the RAM 8, a measurement target reference image detection area D3 is extracted, and the measurement target reference image detection is performed. The degree of coincidence between the two image data in the area D3 is calculated, and it is determined whether or not the degree of coincidence is equal to or more than a predetermined threshold. It is determined that there is no data, and if it is less than the threshold value, it is determined that there is a defect, that is, that there is a position shift. When the degree of coincidence is equal to or less than a predetermined value (this predetermined value is set considerably lower than the threshold value), it is determined that no label is attached. In the case of FIG. 3, it is determined that the label image 70 is at an appropriate position with respect to the container main body image 51. That is, the label 4
0 is affixed to the container body 31 in an appropriate positional relationship.

In the case of FIG. 4, the container image 50, the container main body image 51, the cap image 60, and the label image 70 are shifted by ΔCX in the horizontal direction and ΔCY in the vertical direction in FIG. In FIG.
The state of FIG. 3 is represented by a two-dot chain line. That is, the positioning reference image detection area D1a in FIG. 4 is shifted by (ΔCX, ΔCY) from the positioning reference image detection area D1 in FIG. Then, the measurement target reference image detection area D3 in FIG.
a is similarly shifted by (ΔCX, ΔCY) from the measurement target reference image detection area D3 in FIG. However, since the relative positional relationship of the label image 70 to the container body image 51 is the same, the measurement target position coordinates Qa (X1a, Y1a) by the measurement target reference image detection area D3a are appropriate, and the label sticking position Is determined to be normal. Note that the relative positional relationship between the positioning reference image detection area D1a and the measurement target reference image detection area D3a is the same as that in the case of FIG.

In the case of FIG. 5, the measurement target reference image detection area D
The measurement target position coordinates Qb (X1b, Y1b) in 3b are not appropriate. This is because the relative positional relationship between the label image 70 and the container body image 51 is shifted from the normal positional relationship. That is, the distance α1 is excessive compared to the regular distance α0. In this case, it is determined that the label affixing position has a defect. Note that the relative positional relationship between the positioning reference image detection area D1 and the measurement target reference image detection area D3b is different from that in the case of FIG.

In the case of FIG. 6, the reference image detecting area D1a for positioning is the same as that of FIG. However, the measurement target position coordinates Qc in the measurement target reference image detection area D3c
(X1c, Y1c) is not appropriate. It is a container body image 5
This is because the relative positional relationship of the label image 70 with respect to No. 1 is shifted from the normal positional relationship. That is, the distance α2 is smaller than the normal distance α0. In this case, it is determined that the label affixing position has a defect. Note that the relative positional relationship between the positioning reference image detection area D1a and the measurement target reference image detection area D3c is different from that in the case of FIG.

In the above description, the case where the relative positional relationship of the label image 70 with respect to the container body image 51 is inappropriate in the X direction, but may be incorrect in the Y direction. That is, the distance β0 may be too large or too small.

The result of the image processing by the pattern matching described above is obtained by the camera / display controller 4 and the D
It is displayed on the monitor 12 via the / A converter 11. FIG.
6 to FIG. 6 relate to image data.
The contents displayed in 2 are also shown for reference. That is, the degree of coincidence in the measurement target reference image detection area D3, the X coordinate value of the measurement target position coordinate Q and its determination result (OK or NG (No Good)), and the Y coordinate value and its determination result (OK or NG) Yes, these are displayed on the monitor 12. When there is a defect in the label attaching position, the CPU 6 sends the external alarm 14 via the bus 10 and the input / output interface 9.
Activate The same applies to the case where no label is attached. In the case where the label attachment position is defective or not attached, the determination result is transferred to the external storage device 15 via the bus 10 and the input / output interface 9 together with the image data of the defect. As described above, the external storage device 15 includes a hard disk and an M
There are an O disk, a DVD-RAM, an EEPROM, a flash memory, and the like.

Next, a process of resetting the reference search area D2 and the measurement search area D4 will be described with reference to FIGS. Needless to say, this process is a stage prior to the determination of whether or not the label is pasted and whether or not the label is pasted by the pattern matching described above.
This resetting is performed by the operator operating the input operation unit 13 while watching the display on the monitor 12.

(1) First, FIG. 7 shows a current setting state. In the RAM 8, a positioning reference image detection area D1 ', a reference search area D2', a measurement target reference image detection area D3 ', and a measurement search area D4' have already been set. For convenience of explanation, such element codes before resetting are denoted by a symbol “′” so as to be distinguished from those after resetting. I'm trying to reset it. The reason for the resetting is various as described above, but is to lower the error occurrence rate and improve the accuracy of defect detection.

(2) As shown in FIG.
Adjust the position. This position adjustment is performed after the transport means 31 is stopped. This position adjustment is performed in such a manner that the error occurrence rate is considered to be lower. In this case, if necessary, the direction of the field of view of the CCD camera 2 may be changed up and down, left and right, or up and down and left and right. It should be noted that 100 is the entire captured image data area, 50 is the container image, 51 is the container body image, 60 is the cap image, 70 is the label image, and O is the origin of the entire captured image data area 100.

At the stage shown in FIG. 8, resetting has not yet started. FIG. 8 shows the position of the container image 50 after the position adjustment within the entire captured image data area 100. In addition, the positioning reference image detection area D1 ', reference search area D2', measurement target reference image detection area D3 ', and measurement search area D in FIG.
4 'are all shown by two-dot chain lines. These are the targets for resetting.

(3) Next, as shown in FIG.
Is operated to set the reference position coordinates P (X0, Y0) for the positioning reference image detection area D1 indicated by a solid rectangle in the upper left corner of the cap image 60. The data resulting from this operation is stored in the RAM 8 via the input / output interface 9 and the bus 10. Needless to say, this processing is executed by the CPU 6.

Here, it is assumed that the RAM 8 has a sufficiently large storage capacity and is backed up to the RAM 8 so that the stored contents are not lost even when the power is turned off. The backup is
For example, a lithium battery or a large-capacity capacitor may be used.

(4) Next, as shown in FIG. 10, the positioning reference reset from the reference position coordinates P '(X0', Y0 ') of the positioning reference image detection area D1' in FIG. The reference position coordinates P (X0, Y0) of the image detection area D1
) Are calculated in the X and Y directions. These correction amounts ΔX1 and ΔY1 are stored in the RAM 8.

(5) Next, as shown in FIG. 11, a reference search area D2 is set around the positioning reference image detection area D1. Generally, the reference search area D2 to be reset has the same shape and size as the original reference search area D2 '. In this case, the coordinates are obtained by the following arithmetic processing. The coordinates of the four corners of the reference search area D2 are represented by A (Xa, Ya), B (Xb, Yb), C
(Xc, Yc) and D (Xd, Yd), and the coordinates of the four corners of the original reference search area D2 'are A' (X
a ', Ya'), B '(Xb', Yb '), C' (X
c ', Yc') and D '(Xd', Yd '). That is, for the coordinates A (Xa, Ya), Xa = Xa ′ + ΔX1 (9) Ya = Ya ′ + ΔY1... (9) ... (10), and the coordinates B (Xb, Yb) are calculated as follows: Xb = Xb ′ + ΔX1... ...... (11) ) Yb = Yb ′ + ΔY1... (12), and Xc = Xc ′ + ΔX1 for coordinates C (Xc, Yc). ... (13) Yc = Yc ′ + ΔY1... (14) ), Xd = Xd '+ ΔX1 (15) Yd = Yd' + ΔY1 (13) Yd = Yd '+ ΔY1 … (16) and Calculated Te. These coordinate data are stored in the RAM 8.

(6) Next, as shown in FIG. 12, the correction amount for the measurement target position coordinates Q '(X1', Y1 ') of the original measurement target reference image detection area D3' in FIG. Δ
Measurement target position coordinates Q (X1, Y
1) is calculated, and the measurement target reference image detection area D3 is reset.

X 1 = X 1 ′ + ΔX 1 (17) Y 1 = Y 1 ′ + ΔY 1 ……………………………………………… (18) Since the relative positional relationship between the position of the upper left corner of the cap 32 and the position of the lower right corner of the label 40 that is properly affixed is determined in advance in the actual container 30 as the measurement target shown in FIG. The target reference image detection area D3 can be determined based on the positioning reference image detection area D1. The coordinate data of the new measurement target position coordinates Q (X1, Y1) is stored in the RAM 8.

(7) Next, as shown in FIG. 13, a measurement search area D4 is set around the measurement target reference image detection area D3. The measurement search area D4 is set to include the lower right corner of the label image 70 and to include the boundary 81 between the container body image 51 and the background image 80. Generally, the measurement search area D4 to be reset has the same shape and size as the original measurement search area D4 '. In this case, the coordinates are obtained by the following arithmetic processing. The coordinates of the four corners of the measurement search area D4 are represented by E (Xe, Y
e), F (Xf, Yf), G (Xg, Yg), H (X
h, Yh), and the coordinates of the four corners of the original measurement search area D4 'are E' (Xe ', Ye') and F '(X
f ', Yf'), G '(Xg', Yg '), H' (X
h ′, Yh ′). That is, the coordinates E (Xe, Y
Regarding e), Xe = Xe ′ + ΔX1 (19) Ye = Ye ′ + ΔY1 …………………………………… ... (20), and the coordinates F (Xf, Yf) are calculated as follows: Xf = Xf ′ + ΔX1 (21) Yf = Yf ′ + ΔY1 (21) (22), and the coordinates G (Xg, Yg) are calculated as follows: Xg = Xg ′ + ΔX1. ... (23) Yg = Yg ′ + ΔY1... (24), and for the coordinates H (Xh, Yh), Xh = Xh '+ ΔX1 ……………………………………………………………………………………………… (25) Yh = Yh ′ + ΔY1 . These coordinate data are stored in the RAM 8.

(8) Next, it is checked whether or not the reference search area D2 and the measurement search area D4 reset as described above fall within the entire area 100 of image data captured by the CCD camera 2.

In the case of FIG. 14, it is determined that the reset reference search area D2 and measurement search area D4 fall within the entire captured image data area 100.
However, as shown in FIG.
The measurement search area D4 on the lower side with respect to 0 protrudes in the + Y direction, or the entire area 1 of the captured image data as shown in FIG.
When the reference search area D2 on the upper side of 00 is protruded in the -Y direction, it is determined that the area does not fit.
Also, as shown in FIG.
In contrast, the upper reference search area D2 protrudes in the −X direction, or as shown in FIG.
When the measurement search area D4 on the lower side of 0 protrudes in the + X direction, it is determined that it does not fit. The reason why the shape of the container image is changed is that the direction in which the image protrudes differs depending on the shape.

(9) If it is determined that the size does not fit,
The CPU 6 determines the direction to be accommodated, calculates the direction in which the measuring object 30 is to be moved or the direction in which the CCD camera 2 is to be moved in order to store the data, and converts the data of the direction into the camera / display controller 4 and the D / A conversion. Table 11
To the monitor 12 via the monitor, and displays the direction arrow mark to be moved on the monitor 12. In the case of FIG. 15, the direction arrow mark M to be moved about the CCD camera 2 is displayed downward, and in the case of FIG. 16, the direction arrow mark M to be moved about the CCD camera 2 is displayed upward. In the case of FIG. 17, the direction arrow mark M to be moved for the CCD camera 2 is displayed to the left, and the direction arrow mark N to be moved to the product as the measurement target 30 is displayed to the right. In the case of FIG. 18, the direction arrow mark M to be moved for the CCD camera 2 is displayed to the right, and the direction arrow mark N to be moved for the product as the measurement target 30 is displayed to the left. The display of the direction arrow marks M and N to be moved informs the operator that resetting of the reference search area D2 and the measurement search area D4 is not good. When protruding in both the X direction and the Y direction, a diagonal arrow mark may be displayed as the direction arrow mark to be moved, or a bidirectional arrow mark in the X direction and the Y direction may be displayed. The length of the direction arrow mark may be changed according to the degree of protrusion.

At this time, the CPU 6 may simultaneously output a warning signal. The warning signal may be sent to an externally connected alarm device 14 via the bus 10 and the input / output interface 9 to operate the alarm device 14 to give an audible alarm to the operator.

(10) The operator looks at the directions M and N to be moved displayed on the monitor 12 and moves the CCD camera 2 or the object 30 to be measured. Only the measurement object 30 may be moved, or a CCD
Only the camera 2 may be moved, or both the measurement target 30 and the CCD camera 2 may be moved. Regarding the movement of the CCD camera 2, it means shifting the direction of the field of view (angle of view). It is not necessary to change the installation position of the CCD camera 2 itself. However, in some cases, the installation position may be changed. Alternatively, when the CCD camera 2 includes a zoom lens, the zoom ratio may be changed.

(11) The above (3) to (10) are retried (retried) several times, and finally the judgment in (8) becomes affirmative, and the reset reference search area A situation is obtained in which D2 and the measurement search area D4 fall within the entire area 100 of image data captured by the CCD camera 2.

(12) When there are a plurality of measurement target reference image detection areas D3 as shown in FIG. 19, it is checked whether or not the above processing has been completed for all measurement target reference image detection areas D3. If not completed, the processing from the above (3) is repeated.

(13) When all the above processes are completed, the coordinate data for the reference search area D2 and the coordinate data for the measurement search area D4 are newly set and registered in the RAM 8. Instead of the RAM 8, various data may be stored in the EEPROM 16 connected to the bus 10 and shown by a two-dot chain line in FIG. Rather, it may be better. This is because the EEPROM is a nonvolatile memory, does not require a backup, and can be rewritten.

The resetting is completed by the above processing, and the reference search area D2 for the positioning reference image detection area D1 is set and registered in the storage means such as the RAM 8 and the EEPROM 16, and the measurement target image detection area D
Measurement search area D4 for RAM 3 is RAM8 or EEPR
The setting is registered in the storage means such as the OM16.
Subsequently, the process proceeds to actual measurement execution as shown in FIG.

As described above, in resetting the reference search area D2 and the measurement search area D4, it is determined whether or not the reference search area D2 and the measurement search area D4 fall within the whole captured image data area 100. You can already check at the reconfiguration stage,
In the actual measurement execution, there is no trouble that the reference search area D2 and the measurement search area D4 protrude from the whole captured image data area 100. In addition, since the reference search area D2 and the measurement search area D4 are automatically checked to determine whether or not they are within the entire captured image data area 100, the operator can manually calculate each time and perform artificial calculations. There is no troublesome judgment.

Further, since the occurrence of a protruding trouble in the actual measurement execution can be prevented, the occurrence of a trouble such as an unexpected stop of the production line during its operation can be suppressed, and the reduction of the production efficiency due to resetting is caused. You don't have to.

FIG. 20 shows an outline of the operation of the CPU 6 described above.
Is shown in the flowchart of FIG.

In the above embodiment, the reset reference search area D2 has the same shape and size as the original reference search area D2 '. However, the coordinates A (Xa, Ya) of the four corners of the reference search area D2. ), B (Xb, Yb), C (Xc,
Both Yc) and D (Xd, Yd) may be set independently of the coordinates of the four corners of the original reference search area D2 '. In the above-described embodiment, the reset measurement search area D4 has the same shape and size as the original measurement search area D4 '. However, the coordinates E (Xe, Ye) of the four corners of the measurement search area D4. , F (Xf, Yf), G
Any of (Xg, Yg) and H (Xh, Yh) may be set independently of the coordinates of the four corners of the original measurement search area D4 '. An outline of the operation in this case is shown in the flowchart of FIG.

It is to be noted that there may be an algorithm in which the displacement determination condition is changed by the movement of the CCD camera 2 or the movement of the object 30 to be measured. At that time, FIG.
The processing shown in FIG. 22 may be performed between step S7 and step S11 in the case of 0, and between step S26 and step S30 in the case of FIG. The position deviation determination condition is also corrected, and it is checked whether the condition is within an allowable range. If it is not within the allowable range, the misregistration determination condition is corrected again. It should be noted that, when there are a plurality of measurement target reference image detection areas D3, such correction of the misregistration determination condition and its check are performed for each of them. This is particularly effective when the type of the measurement target 30 changes. It is the reference position coordinate P
Measurement target position coordinates Q (X1, Y0) with respect to (X0, Y0)
This is because the relative positional relationship 1) changes. This is because such a case involves a change in the misalignment determination condition. By performing the processing as described above, it is possible to automatically find an appropriate misalignment determination condition.

Although the two embodiments have been described above, the present invention can include the following configurations.

(1) Instead of the frame memory 5, a field memory may be used, or another memory may be used.

(2) As described above, as a storage area for storing image processing calculation conditions and determination criteria,
EEPRO shown by a two-dot chain line in FIG.
M16, a flash memory, or another nonvolatile memory may be used. In this case, the nonvolatile memory may be connected to the bus 10 inside the image processing apparatus 1 or may be connected to the outside via the input / output interface 9.

(3) The frame memory 5 can be shared with the RAM 8 as a system memory.

(4) The arrival detecting means for detecting that the measurement object 30 has reached the predetermined inspection point DP is replaced by the CC instead of the photoelectric sensor 22 of the above embodiment.
The arrival detection may be determined by software based on image processing of image data obtained by imaging with the D camera 2, that is, by setting a search window for arrival detection for the image data. Good.

(5) The object 30 to be measured does not need to be limited to a container, and the object to be inspected does not need to be limited to the position where the label is attached or the presence or absence of the label. Whatever is possible may be the inspection target. The determination of the print position of the printed content printed on the semi-finished product or the product or the determination of the presence or absence of printing may be performed, the determination of the position of the semiconductor chip pins may be performed, and the arrangement of the electronic components mounted on the printed circuit board may be determined. Any judgment may be made, such as judgment of pass / fail and judgment of pass / fail of arrangement of a plurality of components placed on the transport tray.

(6) The camera / display controller 4 writes the image data into the frame memory 5
The written image data is read out from the frame memory 5, transferred to the D / A converter 11, and the video is displayed on the monitor 12 in real time. However, such real time display is not required. In other words, the monitor 12 may be displayed in real time only when there is a displacement, or may be used only when investigating the cause of a defect having a displacement. .

(7) When storing image data when there is a defect such as a position shift, the image data may be compressed and then stored. In this case, it is assumed that the image is expanded and displayed at the time of display.

(8) A similar non-volatile memory may be provided inside the image processing apparatus 1 in place of the external storage device 15 for storing image data when there is a defect. Also, R
The capacity of the AM 8 or the frame memory 5 may be increased to store image data or the like in them.

(9) It is also possible to use a modem card or an ISDN card to transmit image data and the like to a remote terminal via a public line or a dedicated line.

(10) As for any other items which are not directly related to the gist of the present invention, any known ones can be applied. It is needless to say that the present invention can be applied within a range not to be applied.

The above items (1) to (10) are independent of each other, and any of these items may be appropriately combined in any number.

[0081]

According to the first aspect of the present invention, in resetting the reference search area and the measurement search area, the reset reference search area and the measurement search area are included in the entire area of the captured image data. A check as to whether or not the data is within the range can be automatically performed at the time of resetting. That is, it is possible to check in advance whether or not the search area reset is appropriate at the time of resetting. This eliminates the hassle of having to manually determine by the operator, for example, calculating on a desk, and at the same time, reducing the actual measurement. Even when a position shift occurs in the reference search area during execution, it does not cause an overhang problem, can suppress the occurrence of problems such as unexpected stop of the production line during its operation, and can be set again. Fixing does not cause a drop in production efficiency.

According to the second aspect of the present invention, when the operator moves the imaging means or the object to be measured, the operator only has to look at the displayed instruction of the moving direction and move it in accordance with the instruction. Quick correction work,
It can be done easily.

According to the third aspect of the present invention, even when correcting the misregistration determination condition, it is configured to check whether or not the correction is appropriate, so that the appropriate misregistration determination condition is automatically found. be able to.

According to the fourth aspect of the present invention, the measurement object is imaged with good timing for the measurement object conveyed on the production line or the like, and the quality of the inspection object can be efficiently determined. The same effects as those of the first aspect can be obtained.

According to the fifth aspect of the present invention, it is determined whether or not a label affixed to a semi-finished product such as a container or a product, or a print position of a printed content, or a determination of whether or not a label is affixed or printed. Image processing for determining whether the pin positions of the chip are good, whether the electronic components mounted on the printed circuit board are good or not, and whether the multiple components placed on the transport tray are good or bad. In the device,
The above-described effects are favorably exhibited, and therefore, versatility can be enhanced.

[Brief description of the drawings]

FIG. 1 is a block diagram showing an electrical configuration of an image processing apparatus according to an embodiment of the present invention.

FIG. 2 is an explanatory diagram of an outline of a production line inspection system to which the image processing apparatus according to the embodiment is applied;

FIG. 3 is an explanatory diagram of an operation of pattern matching by an image processing device in the production line inspection system according to the embodiment (in the case where there is no displacement);

FIG. 4 is an explanatory diagram of an operation of pattern matching by the image processing apparatus (in the case of positional deviation correction with respect to FIG. 3)

FIG. 5 is an explanatory diagram of an operation of pattern matching by the image processing apparatus (corresponding to FIG. 3 and when there is a position shift)

FIG. 6 is an explanatory diagram of an operation of pattern matching by the image processing apparatus (corresponding to FIG. 4, in the case where there is a displacement)

FIG. 7 is an explanatory diagram showing a current setting state of each (original) area in resetting by the image processing apparatus;

FIG. 8 is an explanatory diagram of a stage of adjusting the position of the measurement target in resetting by the image processing apparatus.

FIG. 9 is an explanatory diagram of setting of a reference search area in resetting by the image processing apparatus.

FIG. 10 is an explanatory diagram of calculation of a correction amount in resetting by the image processing apparatus.

FIG. 11 is an explanatory diagram of setting of a reference image detection area for positioning in resetting by the image processing apparatus.

FIG. 12 is an explanatory diagram of setting of a measurement search area in resetting by the image processing apparatus.

FIG. 13 is an explanatory diagram of setting of a measurement target reference image detection area in resetting by the image processing apparatus.

FIG. 14 is an explanatory diagram when a reference search area and a measurement search area in resetting by the image processing apparatus are normal;

FIG. 15 is an explanatory diagram when the measurement search area in the resetting by the image processing apparatus protrudes the whole area of the captured image data in the + Y direction.

FIG. 16 is an explanatory diagram when the reference search area in the resetting by the image processing apparatus protrudes the whole area of the captured image data in the −Y direction.

FIG. 17 is an explanatory diagram when the reference search area in the resetting by the image processing apparatus protrudes the whole area of the captured image data in the −X direction.

FIG. 18 is an explanatory diagram when the measurement search area in the resetting by the image processing apparatus protrudes the whole area of the captured image data in the + X direction.

FIG. 19 is a diagram illustrating a case where a plurality of measurement target reference image detection areas are set by resetting by the image processing apparatus.

FIG. 20 is a schematic flowchart showing an operation of resetting by the image processing apparatus.

FIG. 21 is a schematic flowchart showing the resetting operation when changing the shape and size of the reference search area and the measurement search area at the time of resetting;

FIG. 22 is a schematic flowchart showing an operation of resetting when correcting a position shift determination condition.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Image processing apparatus, 2 ... CCD camera, 3 ... A / D converter, 4 ... Camera / display controller, 5 ... Frame memory, 6 ... CPU, 7 ... ROM, 8 ... RAM, 9 ... Input / output interface, 10 ... bus, 11 ... D / A converter,
12 monitor, 13 input operation unit, 14 alarm device, 15
... external storage device, 16 ... EEPROM, 20 ... production line inspection system, 21 ... transportation means, 22 ... arrival detection means (photoelectric sensor), 23 ... cable, 30 ... measurement object (container), 31 ... container body, 32 ... cap, 40 ... label, 50 ... container image, 51 ... container image, 60 ... cap image, 70 ... label image, 80 ... background image, 10
0: whole area of captured image data, DP: inspection point,
D1: positioning reference image detection area, D2: reference search area, D3: measurement target reference image detection area, D4: measurement search area, P: reference position coordinates, Q: measurement target position coordinates,
D1 ': Original positioning reference image detection area, D2':
Original reference search area, D3 '... Original measurement target reference image detection area, D4' ... Original measurement search area, P '... Original reference position coordinates, Q' ... Original measurement target position coordinates , Δ
X1, ΔY1: correction amount, M: directional arrow mark to move CCD camera, N: directional arrow mark to move measurement object

Continued on the front page F-term (reference) 2F065 AA03 AA49 BB15 CC00 EE00 FF04 FF26 JJ03 JJ26 LL06 NN11 PP03 PP05 PP15 QQ03 QQ23 QQ24 QQ25 QQ36 QQ39 SS09 SS13 5B057 AA02 BA02 CA08 CA13 CB08 DB07 DA02 AC42 5C054 AA01 AA05 CA04 CC02 CD05 CE14 CG02 CH03 CH04 DA01 EA05 EA07 FA01 FA02 FB01 FB03 FC12 FC15 FE22 FE28 FF02 FF03 FF07 GB12 GB15 GD09 HA03

Claims (5)

[Claims] 1. A method of detecting a reference position coordinate in a positioning reference image detection area in a reference search area for a captured image data of a measurement object, and a measurement target position in a measurement target reference image detection area in the measurement search area. An image processing apparatus that detects coordinates and determines the acceptability of an inspection target based on a relative positional relationship of the measurement target position coordinates with respect to the reference position coordinates, wherein a relative position between the reference search region and the measurement search region and a captured image is determined. At the time of resetting performed in a state where the position is shifted, by performing correction so that the relative positional relationship between the two search areas with respect to the captured image at the time of initial setting becomes the same even after resetting, only the measurement search area is The image processing apparatus is characterized in that it is not necessary to reset the reference search area even if is moved. 2. When the reference search area and the measurement search area after the resetting do not fall within the entire area of the captured image data, display of a moving direction instruction for changing the field of view of the imaging means or measurement target 2. The image processing apparatus according to claim 1, wherein an instruction of a moving direction of an object is displayed. 3. The apparatus according to claim 1, wherein the position deviation determination condition is corrected as required, and it is determined whether or not the corrected position deviation determination condition falls within an allowable range. The image processing apparatus according to claim 1. 4. An apparatus according to claim 1, wherein said measurement object is transported, and said arrival detection means detects that said measurement object has arrived at a required inspection point on said transport path. The image processing apparatus according to any one of claims 1 to 3, wherein the detection signal is used as a trigger to perform imaging of the measurement target and determination of whether the inspection target is good or not. 5. The image processing apparatus according to claim 1, wherein the inspection target of the measurement target is a two-dimensional position on the image data.