JP2004340770A - Imaging inspection system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a novel imaging inspection system which inspects even a spindle-shaped soft capsule or the like as an object to be inspected being conventionally difficult to be selected as an imaging inspection object, photographs the object by using a camera, and can automatically discriminate a shape defect, a foreign variety mixed defect (color defect), a faulty defect or the like. <P>SOLUTION: The imaging inspection system is made up so that a work W such as the soft capsule which is mounted and held on a work transferring section 4, is photographed by using an optical imaging section 2 employing a CCD camera 10 as a main member, in order to enable the shape defect, the color defect, the faulty defect or the like to be discriminated. The work transferring section 4 holding the work W is illuminated from the opposite side in the photographing direction, and a light saturated state is made, thereby suppressing effects of the work transferring section 4 appearing in the background of the work W on a screen. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to an inspection system for inspecting a gelatin capsule or the like used as a container for facilitating taking an internal medicine or the like, and particularly to an imaging inspection for visually inspecting such a capsule or the like. It concerns the system.
[0002]
BACKGROUND OF THE INVENTION
For example, there is a medicine in which a pharmaceutical product having an unpleasant odor or bitterness is filled into a soft capsule formed of gelatin to make it easy to take. Many of these types of soft capsules are formed into substantially spheroidal or spindle-shaped granules, but during the production thereof, for example, poor capsule shapes, poor mixing of different types with different surface colors, black spots appearing on the capsule surface There are defects such as defects and bubbles (bubbles), and such defective products cannot be eliminated. Conventionally, inspection of such a defective product is performed by a manual operation exclusively, that is, a method of visually observing by an operator or measuring with a caliper or the like is often employed, which requires time and labor. In particular, when this kind of product is a food or a pharmaceutical product, it is often the case that a full quantity inspection (not a sampling inspection) is performed, and the tendency that time and labor are required is further promoted.
[0003]
Of course, in performing such an inspection, an attempt has been made to identify non-defective and defective products by photographing the capsule with a camera. However, in this type of capsule, the outline is not clearly reproduced on the screen displaying the imaging result, so to speak, in a so-called blurred state, particularly because the outer peripheral shape is a smooth curved surface shape such as a spindle shape. They tended to be displays. For this reason, the outer shape cannot be clearly grasped, so that the subsequent judgment (identification) cannot be performed accurately.
In addition, this kind of capsule has a glossy surface (brilliancy), and therefore, when the external appearance is photographed, reflection of light applied to the capsule is one of the factors that make it difficult to perform clear imaging. .
For this reason, although there is an idea to use a camera as an inspection method, such an imaging inspection system has not yet reached the stage of practical use, especially for pharmaceuticals and foods that require a highly accurate determination level. Was the actual situation.
[0004]
[Technical issues that we attempted to develop]
The present invention has been made in recognition of such a background, and conventionally, a soft capsule having a substantially spheroidal shape or a spindle shape, which has been difficult to be subjected to an imaging inspection, is to be inspected. This is an attempt to develop a new imaging inspection system which can automatically sort out defective shapes, mixed defects of different types (color defects), defective defects, and the like with high accuracy by photographing the objects with a camera.
[0005]
[Means for Solving the Problems]
In other words, the imaging inspection system according to the first aspect of the present invention captures a workpiece held on a mounting body by an optical imaging unit having a camera as a main member, and can identify a shape defect, a color defect, a defect defect, and the like of the workpiece. In the above system, the mounting body holding the work is illuminated from the opposite side of the imaging direction to form a saturated state of light, thereby suppressing the influence of the mounting body reflected on the background of the work on the screen. This is characterized by the above.
According to the present invention, in order to suppress the influence of the mounting body due to the saturation state of the light, instead of erasing the mounting body by setting the threshold value of binarization on the screen, the outer shape and the surface density value of the work are determined. More accurate detection is possible. For this reason, the imaging determination of such a work, which has been stopped at the idea stage until now, is made realistic.
[0006]
An imaging inspection system according to a second aspect is characterized in that, in addition to the requirements described in the first aspect, when imaging the work, the work is imaged a plurality of times while changing the angle of the work.
According to the present invention, a so-called all-around inspection in which a workpiece is photographed not only from one surface but also from various surfaces can be efficiently performed, and inspection can be performed at a high level.
[0007]
Furthermore, in the imaging inspection system according to claim 3, in addition to the requirements described in claim 1 or 2, a black point smaller than the work is previously formed on the mounting body, and the work is placed on the mounting body during imaging. , The black spot disappears on the screen.
According to the present invention, so-called halation can be prevented. That is, for example, when a dark-colored work (eg, yellow-orange) is mixed while a dark-colored work (eg, black-brown) is inspected, the light-colored work (eg, yellow-orange) is too bright to fly on the screen, and nothing is captured. However, if black spots are formed on the mounting body in advance, even if nothing is displayed on the screen, the black spots are erased, so that the presence of different types of workpieces can be detected.
[0008]
The imaging inspection system according to claim 4 is characterized in that, in addition to the requirements described in claim 1, 2, or 3, the workpiece is a spindle-shaped gelatin capsule having a glossy surface.
According to the present invention, a spindle-shaped work having a glossy surface is particularly easy to blur at a peripheral end (contour), but such a work can be inspected at a high level.
[0009]
An imaging inspection system according to a fifth aspect is characterized in that, in addition to the requirements described in the first, second, third or fourth aspect, the camera is a monochrome type CCD camera.
According to the present invention, the imaging inspection apparatus can be manufactured relatively inexpensively.
[0010]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, the present invention will be described based on the illustrated embodiments. In the description, first, an example of the imaging inspection apparatus 1 that implements the present system will be described, and then the imaging inspection system of the present invention will be described together with the operation mode of the apparatus.
According to the present invention, a work W to be inspected is photographed by a camera, and the work W is automatically sorted into non-defective products, defective products, re-examined products, and the like. The work W in the present embodiment is, for example, a soft-type gelatin capsule (hereinafter referred to as a soft capsule and having the same symbol W as the work) filled with medicines, nutrients, health food extracts, seasonings, and the like. Is applied). In addition, the defective products here include defects in shape, defects in mixing different kinds of different colors, defects such as black spots and bubbles (bubbles) floating on the capsule surface due to the fact that the work W is the soft capsule W. (See FIG. 4).
[0011]
As shown in FIG. 1 as an example, the imaging inspection apparatus 1 includes an optical imaging unit 2, an image processing unit 3, and a work transport unit 4 for mounting and transporting a soft capsule W. Each component will be further described.
First, the optical imaging unit 2 will be described. This is a part for substantially photographing the soft capsule W held on a mounting body (corresponding to the work transporting unit 4 and corresponding to a roller conveyor described later in the present embodiment). The optical imaging unit 2 includes, as an example, a monochrome type CCD camera 10 as a main member, and is capable of imaging three soft capsules W at a time here (see FIG. 2). Reference numeral 11 denotes a lens, and reference numeral 11a denotes a close-up ring attached to the lens 11. Further, an area where the imaging of the soft capsule W is substantially performed is defined as an imaging zone Z.
[0012]
Here, reference numeral 12 denotes a dome-shaped illumination for uniformly illuminating the surface of the soft capsule W with diffused light, which is formed in a double dome structure as shown in the sectional view of FIG. 1 as an example. A plurality of white LEDs 13 are equally arranged on the bottom of the double dome so as to uniformly illuminate the soft capsule W sent to the imaging zone Z. When the inside and outside of the double dome are indicated separately, the inside dome is identified as 12a and the outside dome is identified as 12b.
Incidentally, the irradiation method by the dome-shaped illumination 12 will be specifically described. Light emitted from the white LED 13 is reflected by the outer dome 12b, and is diffused in various directions when the light passes through the inner dome 12a. This illuminates the soft capsule W evenly. The reason for irradiating the soft capsule W evenly during imaging is to minimize the occurrence of shadows that hinder imaging.
[0013]
Further, in the present embodiment, since the soft capsule W is imaged (viewed) from almost right above, a hole is opened directly above the dome-shaped illumination 12, and the lens 11 is used to look into the work W therefrom. Take an image. Therefore, immediately below the dome opening (lens 11), the amount of diffused light from the dome-shaped illumination 12 tends to decrease, and a coaxial epi-illumination 14 is provided directly above the dome opening to compensate for this reduction in the amount of light. ing.
The coaxial epi-illumination 14 includes a half mirror 15 and a white LED 16 as an example. For example, about half of the light emitted from the white LED 16 is reflected and radiated to a soft capsule W placed almost directly below. ing. Of course, with such a configuration, the lens 11 captures an image of the soft capsule W on the mounting body (work transport unit 4) via the half mirror 15.
[0014]
Reference numeral 17 denotes a transmission illumination for illuminating the mounting body from the opposite side of the imaging direction, that is, a so-called backlight, which suppresses the influence of the mounting body formed on the screen as a background of the soft capsule W as much as possible. . That is, in the present invention, a saturated state of light is formed by the transmitted illumination 17, whereby the mounting body can be erased on the screen. Of course, the transmitted illumination 17 not only suppresses the influence of the mounting body but also illuminates the soft capsule W from behind, so that the contour and surface density value (light and dark density value) of the capsule can be detected more accurately. -Defects can be determined at a higher level. In addition, the code | symbol P in a figure shows the power supply for illumination.
[0015]
As described above, in the present invention, the luminance value of the mounting body is saturated by the irradiation of the transmissive illumination 17, and therefore, for example, when binarizing the captured image in the determination (whether the brightness is dark or white) ), The threshold value can be set to a stable value (for example, 254 when the brightness of the image is represented by 256 levels from 0 to 255 [saturation state]).
Incidentally, the CCD camera 10 converts light into electrons by using the photoelectric effect, and creates an image by counting the converted electrons. In other words, the monochrome type CCD camera 10 expresses each point on the screen such that a portion with many electrons is brightened and a portion with few electrons is darkened. Cannot be determined. For this reason, in the present embodiment, a density value (brightness histogram) of the soft capsule W is created, and a color difference (whether or not of a different kind) is determined based on this.
[0016]
With such an optical imaging unit 2, the shape and the like of the soft capsule W can be more clearly imaged and recognized as compared with the related art. However, the outline of the soft capsule W tends to be blurred, and will be described below. The enlarged view of FIG. 2 shows an example of an imaging state of the soft capsule W. Since the coaxial epi-illumination 14 mainly irradiates the vicinity of the apex of the capsule, an image mainly by this light is shown. Light from the dome-shaped illumination 12 mainly irradiates a relatively wide portion around the top of the capsule, and an image mainly by this light is captured. Then, on the outer periphery, a background caused by light entering through a gap at the bottom of the dome is reflected. Further, a roller is reflected on the outer periphery by light reflected by the mounting body (roller). As described above, the soft capsule W has a curved surface (spindle shape) and a glossy surface, so that the contour becomes more vague at the peripheral edge, and the soft capsule W is easily blurred.
[0017]
Next, the image processing unit 3 will be described. This is a part that captures an image captured by the CCD camera 10 and appropriately processes this into data necessary for inspection. The image processing unit 3 has a function of checking whether or not the soft capsule W being imaged is a non-defective product, and includes the image processing device 20 and the monitor 21 as main members.
The image processing device 20 is loaded with an appropriate visual inspection program according to the work W, processes the image captured by the CCD camera 10 as appropriate, and detects, for example, an abnormal shape of the soft capsule W, an abnormal mixture of other types, an abnormal defect, and the like. Things.
The monitor 21 displays an input image of the soft capsule W, a state during the inspection, a setting screen of various parameters required for the inspection, and the like. For example, a liquid crystal monitor is applied.
Reference numeral 22 denotes a keyboard for inputting numerical values of various parameters required for inspection mainly at the time of maintenance. Reference numeral 23 denotes a trackball for setting various parameters by operating an arrow cursor on the monitor 21, and is mainly used during operation.
[0018]
Next, the work transport unit 4 will be described. This is a mounting body for holding the work W in the imaging zone Z. In this embodiment, the roller conveyor 5 is applied because the soft capsules W are sequentially fed into the imaging zone Z.
In the above description, such a work transport unit 4 is described as a mounting body that is a general concept of the work transport unit 4 because it is not always necessary to transport (work) the work W during the inspection. . That is, for example, the work W is placed in an immobile state, and the CCD camera 10 can be rotated at an appropriate angle about the work W, so that an image similar to that of the present embodiment can be taken. It is. Needless to say, such an operation only needs to relatively move the work W and the CCD camera 10, and both can be formed to be movable.
[0019]
As shown in FIG. 1 as an example, the roller conveyor 5 includes a plurality of rollers 26 disposed so as to pass through the imaging zone Z, a chain 27 rotatably supporting the rollers 26, and the chain 27 wound around the rollers 26. The roller 26 is configured to pass through the imaging zone Z while rotating (rotating) by rotation of the sprocket 28. As a result, the work W (soft capsule W) sequentially approaches the imaging zone Z while rolling on the roller 26 during the inspection, and has a transport mode of passing therethrough. Here, the imaging timing of the CCD camera 10 is synchronized with the roller conveyor 5 so that one soft capsule W is imaged three times at different angles (for example, about 130 ° each). (See FIG. 3). In the embodiment shown in FIG. 3, the same soft capsule W (“work A” in the figure) is photographed three times while being sequentially sent from right to left.
[0020]
In the roller 26, for example, a concave portion 29 for stably receiving the soft capsule W is formed at a substantially central portion. Thereby, the soft capsule W is held at a substantially constant position in the longitudinal direction of the roller 26, and the imaging zone Z (imaging position) is stabilized. Here, the concave portion 29 is mainly formed in one center in one roller 26. However, two or more concave portions can be formed. Incidentally, when two concave portions 29 are formed, six soft capsules W are imaged at a time.
In addition, since each roller 26 is configured to be rotatable, a gap is inevitably formed between them. In this case, particularly, this gap allows the light of the transmitted illumination 17 to pass from behind the soft capsule W. It also acts.
The roller 26 can be appropriately changed depending on the color (brightness or darkness) of the soft capsule W to be inspected.
[0021]
Further, for example, when a dark color soft capsule W is inspected, if a light color soft capsule W is mixed, the light color capsule will fly too bright on the screen, and nothing will be displayed. (Hale Shaun) is conceivable. In this case, of course, the image cannot be recognized on the screen as a video, so that mixing of different capsules (mixing of different types) cannot be detected. For this reason, in the present embodiment, a black spot 30 smaller than the soft capsule W, for example, having a diameter of about 3 mm is formed in advance in the recess 29 to prevent erroneous recognition (overlooking) due to such halation. is there. That is, by forming a black spot 30 having a diameter of about 3 mm in the concave portion 29 of the roller 26 in advance, even if a different capsule is not shown on the screen, if this black spot 30 disappears on the screen, it is possible to judge that foreign matter is mixed. Like that.
[0022]
In order to sequentially feed the works W into the imaging zone Z, not only the roller conveyor 5 but also a slat conveyor can be applied. Of course, in this case, the influence of the slats reflected on the background of the work W on the screen is minimized by forming an appropriate gap between each slat or providing a transmission hole for the backlight on the slat itself. , So that the slat can be erased from the screen.
[0023]
The imaging inspection apparatus 1 embodying the present invention has the above basic structure. Hereinafter, an actual inspection method using this apparatus will be described in detail based on the flowchart of FIG. Next, an imaging inspection system of the present invention will be described. Note that the inspection and identification here mainly include the defect of the shape of the soft capsule W, the defect of heterogeneous mixture, and the defect of defects such as black spots and bubbles floating on the surface of the capsule as described above.
[0024]
Prior to the substantial inspection, settings such as the size of the soft capsule W captured by the CCD camera 10, that is, the size of the soft capsule W to be displayed on the monitor 21 (inspection window setting), or the type of capsule to be inspected are set in advance. is there.
Along with this, a reference value for determining whether the capsule is good or bad is registered by teaching or the like. Here, teaching means that prior to inspection, a non-defective sample is placed on the roller conveyor 5 and the area of the capsule, the length of the main shaft, the length of the sub-shaft, the circumference, the density value, etc. are determined from the non-defective capsule image for each type. This is the work (operation) of learning and setting. As a result of the teaching, an intermediate value is obtained from the maximum value and the minimum value of each measured item and used as a reference value. Of course, such input of the reference value and the like can also be performed by the keyboard 22 and the like.
[0025]
(1) Shape defect judgment (shape inspection processing)
When the shape of the soft capsule W is imaged by the CCD camera 10, the shape looks almost two-dimensional elliptical. Therefore, in the shape inspection, the length of the major axis (major axis), the length of the minor axis (minor axis), and the area of the elliptical shape are determined. , Circumference, etc. are measured and compared with non-defective ones.
[0026]
(A) Filter processing and smoothing processing
In performing image processing, unnecessary parts are first removed from a captured image, and then processing is performed. Specifically, a filter process is performed on the capsule image captured by the CCD camera 10 to remove noise on the monitor screen, uneven gloss of the capsule, and the like.
In addition, when the density difference (contrast) between the roller 26 and the soft capsule W is strong due to such a filtering process, an appropriate smoothing process (for example, about 6 × 6) is performed. It is preferable that the roller 26 and the soft capsule W have an appropriate density difference. If the difference is too strong, for example, the soft capsule W tends to be deformed or distorted on the screen (for example, the main shaft). The image is taken with both ends depressed inside the capsule). The smoothing process is a process of reproducing (imaging) the original elliptical shape of the capsule by intentionally blurring such an excessively strong contrast.
[0027]
(B) Binarization processing
After that, the capsule image from which unnecessary portions have been removed is subjected to binarization processing to facilitate measurement of the size, area, and the like of the soft capsule W (see FIG. 6A). In this case, the brightness value of the roller 26 serving as the background of the soft capsule W is saturated by the transmitted light 17, so that the threshold value for binarization is set to a stable value (250 to 254, particularly preferably 254). it can. The image after the binarization shown in FIG. 6A is an image obtained by processing the above-mentioned FIG. 4A, and the downward arrow described in FIG. This indicates that the conversion process is performed.
[0028]
(C) Feature extraction (binary measurement)
The capsule portion is taken out from the binarized image, and the area, perimeter, main shaft length, sub shaft length, bending, and the like of the soft capsule W are measured (see FIG. 6B). Here, the term “bend” refers to the deformation of the soft capsule W. When straight lines (accurately, semi-straight lines) are drawn from the center of the capsule to both ends in the main axis (up and down) direction, the main axis (screen The above shows the bending angle with respect to the upper and lower vertical lines. For example, if there is no deformation, it overlaps with the main axis, so that the bending is 0 degree.
[0029]
(D) Judgment
To determine the quality of the capsule, whether it is good or bad, a tolerance value of ± is set for the reference value measured and registered in advance by teaching or the like, and a product out of the range is determined as a defective product or a retest product. Note that the allowable value is generally set to a constant value according to the work W. However, in the case where the same work W is to be delivered quickly, the allowable range can be set somewhat larger.
[0030]
(2) Defect defect detection (defect detection processing)
In the defect detection processing, since the defect may be the same as the luminance value of the capsule surface, an image in which the defect is deleted is once created, and this is compared with the capsule captured image (the original capsule image in FIG. 5). By processing, only the defective part is extracted. In the following description and FIG. 7, the millet appears white on the screen, so it is regarded as a bright defect, and the black point is defined as a large black point.
(A) Inversion of binarized outline image (outline binarization)
The outer shape image of the soft capsule W binarized in the previous shape detection is inverted between black and white. Thereby, the capsule portion is represented by white and the back surface of the capsule is represented by black. Although FIG. 7 shows the image captured by the camera, as described above, if the capsule outer shape has already been input in the previous shape detection, this data is generally used. .
[0031]
(B) Capsule image shrinkage (labeling)
In the inverted image, the capsule outer shape is contracted, and defect detection is performed within the contracted range. This is to prevent erroneous detection due to the capsule peripheral edge.
In the present embodiment, since one soft capsule W is imaged three times at different angles, even if the defective portion is reflected at the peripheral edge at a certain angle and disappears due to shrinkage, it is not used at other times. However, since this defect always falls within the non-shrinkage range, the defect is not overlooked. Conversely, in order to prevent such a situation, a so-called all-around inspection is performed. Note that the labeling in the figure is for registering the extracted capsule part as data.
[0032]
(C) Compositing (combining captured images)
The binarized contracted image and the capsule captured image (camera captured image) are combined to create a defect detection image.
[0033]
(D) Creation and search of density histogram
From the capsule portion, a density histogram is created in which the horizontal axis represents the density value (0 to 255) and the vertical axis represents the number of pixels, from which the bright peak level, the shadow peak level, and the shadow edge level are extracted. Here, the shadow portion of the shadow peak level indicates an elongated dark portion that appears almost along the outer shape of the soft capsule W on the image (here, mainly appears on the left and right), and a bright portion of the bright peak level. Indicates a relatively light portion excluding a shadow portion and a bright defect. The shadow part edge level is used to cut out the shadow part with an appropriate margin in the subsequent processing. Here, the shadow part edge level is set to an equivalent value (approximate value) with respect to the shadow part peak level across a valley. Is defined as the shadow edge level.
[0034]
(E) Shading imaging of capsule outer shape (light area shading imaging)
Using the bright peak level, the contour of the capsule is shaded.
[0035]
(F) Light area shrinkage (light area shrinkage)
After that, in order to increase the detection sensitivity of the center portion of the capsule, the capsule outer shape converted into a gray image is further contracted to create the center portion of the bright portion. This is a process for preventing a defect from being detected in the central portion of the bright portion, that is, for temporarily eliminating a defect that appears in the central portion of the capsule.
[0036]
(G) Binary shadow
The shadow part is binarized using the shadow edge level extracted from the histogram.
[0037]
(H) Shadow shading image
The binarized shadow part is converted into a grayscale image at the shadow part peak level.
[0038]
(I) Background image composition
The three images of the above-described outer shape (bright portion shade image), contraction (bright portion contraction image), and shadow portion (shadow portion contrast image) are combined, and thereby a background image from which the defective portion has been once deleted is created.
[0039]
(J) Difference processing between captured image and background image (difference image)
Difference processing is performed on the background image from which the defect portion has been deleted and the capsule captured image, and only the defect is detected.
[0040]
(K) Defect binary image (binary image)
The defective portion is clarified by an appropriate threshold value (set value). Here, the large black spot and the bright defect are displayed on the same screen. However, when binarizing, it is common to detect them separately and finally display them on the same screen.
[0041]
(3) Different kind detection processing
The different kind detection processing is performed using the density value of the soft capsule W extracted in the middle of the defect detection processing, and is compared with the density value registered in advance by teaching or the like. Is what you do.
Here, since it is assumed that different types of different colors are detected after performing shape detection, it has been described that different types are mainly detected based on density values. In such a case, different kinds of inspections can be performed depending on the shape of the capsule, depending on the shape of the capsule.
[0042]
[Other embodiments]
The present invention is based on the above-described embodiment as one basic technical idea. However, the following modifications can be considered. That is, in the above-described basic embodiment, a soft gelatin capsule in which a medicine, a nutrient, a health food extract, a seasoning, and the like are filled is used as the work W. However, as the workpiece W, it is also possible to inspect a machined component, an electronic device component, and the like. In addition to such a mechanical product, a seed or the like can be used as the workpiece W. In this case, the germination state can be inspected by imaging with a camera. As described above, the workpiece W can be applied not only to chemicals and foods in the form of granules or pellets, but also to anything that requires a visual check. ) Is suitable for those in which the shadow of the mounting body or the like easily enters the screen or that in which the outer shape is easily blurred due to the curved surface of the work W.
[0043]
Further, in the above-described basic embodiment, the monochrome CCD camera 10 is applied. However, a color CCD camera can be applied to perform inspection with higher accuracy. Data can be created.
[0044]
Furthermore, in the above-described basic embodiment, the description has been made such that the quality of the product is determined by the present system for imaging the workpiece W. However, the present system is not necessarily limited to such determination. Not something. That is, for example, even if the soft capsules W have the same color and shape, if the contents are different, the capsule itself may be marked with a laser. The present imaging inspection system can be applied.
[0045]
In the case of soft capsules W having similar shapes and sizes, there is a demand that different colored coatings be applied to the film according to the filler. In such a case, by taking a coating density histogram (luminance histogram), it is possible to leave an objective guarantee that the same color coating is applied before shipment (delivery). Available.
[0046]
【The invention's effect】
According to the present invention, since the transmission illumination 17 is provided, the roller 26 for placing and transporting the work W can be illuminated from the opposite side in the imaging direction (CCD camera 10). The influence of the roller 26 can be suppressed as much as possible. For this reason, the shape and the surface density value of the work W can be detected more accurately, and the inspection can be performed at a high level.
In particular, in the case of a work W having a glossy surface and a curved surface such as a spindle shape, the peripheral edge (contour) of the work W is inevitably blurred on the screen. Also, inspection can be performed with high accuracy by, for example, performing imaging multiple times at different angles.
Further, for example, a black point 30 smaller than the work W is formed in advance on the roller 26, and when the work W is sent onto the roller 26, the black point 30 is set to disappear on the screen. For example, it is possible to reliably detect that a light-colored work W has been mixed while a dark-colored work W is being inspected.
[Brief description of the drawings]
FIG. 1 is a perspective view illustrating an example of an imaging inspection apparatus that implements an imaging inspection system of the present invention, and a cross-sectional view illustrating an optical imaging unit of the apparatus.
FIG. 2 is an explanatory diagram showing a state in which a soft type gelatin capsule is imaged by an imaging inspection device.
FIG. 3 is an explanatory view showing a state in which a workpiece is imaged three times while changing the angle little by little.
FIG. 4 is an explanatory view showing a shape defect and a defect defect of a soft capsule.
FIG. 5 is a flowchart of performing a shape inspection, a defect detection, and a different kind inspection of a soft capsule by the imaging inspection system of the present invention.
6A and 6B are an image (a) after binarizing the soft capsule and an image (b) in which binarization measurement is performed when inspecting the shape of the soft capsule.
FIG. 7 is an explanatory view showing stepwise a state in which a defect of the soft capsule is inspected.
[Explanation of symbols]
1 Imaging inspection equipment
2 Optical imaging unit
3 Image processing unit
4 Work transfer unit
5 Roller conveyor
10 CCD camera
11 lenses
11a Close-up ring
12 Dome type lighting
12a Inner dome
12b Outside dome
13 White LED
14 Coaxial epi-illumination
15 Half mirror
16 White LED
17 Transmission illumination
20 Image processing device
21 monitors
22 Keyboard
23 Trackball
26 rollers
27 chain
28 sprockets
29 recess
30 sunspots
P Lighting power supply
W soft capsule (work)
Z imaging zone

Claims (5)

By an optical imaging unit having a camera as a main member, by photographing the work held on the mounting body, a shape defect of the work, a color defect, a defect defect and the like can be identified, a system,
By illuminating the mounting body holding the work from the opposite side of the imaging direction and forming a saturated state of light, the effect of the mounting body reflected on the background of the work on the screen is suppressed. Imaging inspection system. The imaging inspection system according to claim 1, wherein the imaging of the work is performed a plurality of times while changing the angle of the work. A black spot smaller than the work is previously formed on the mounting body, and the black point disappears on the screen when the work is positioned on the mounting body during imaging. 2. The imaging inspection system according to 2. 4. The imaging inspection system according to claim 1, wherein the workpiece is a spindle-shaped gelatin capsule having a glossy surface. 5. The imaging inspection system according to claim 1, wherein the camera is a monochrome type CCD camera.

Images