TW201608484A - Method for setting inspection condition for fastener element, and method for inspecting fastener element - Google Patents

Abstract

The present invention has a camera (12) for capturing an image of the surface of a fastener element (24) of a slide fastener (20), and an illumination device (14) for illuminating the fastener element (24). A plurality of control factors which affect the image captured by the camera (12) are selected, and an image of each of a plurality of fastener elements (24) is captured simultaneously in a plurality of conditions of the control factors. Color image data in an individual unit region of each of the fastener elements (24) are extracted for a plurality of color images captured of the plurality of fastener elements (24) by the camera (12). Luminance characteristic values for each of the three primary colors of light are obtained for each pixel of the color image data of the unit regions of the fastener elements (24). An error variance in the color of a fastener element (24) is calculated on the basis of the computed characteristic values for the three primary colors of light. The SN ratio and sensitivity of the image data of each fastener element (24) is computed for each set condition of the control factors on the basis of the obtained error variance, and the set condition of a control factor for which the SN ratio and sensitivity values are relatively large is selected from among the computed SN ratios and sensitivities.

Description

Method for setting inspection condition of chain teeth and method for detecting chain teeth

The present invention relates to a method for setting inspection conditions for a fastener element for detecting whether a product is a good product, and a method for detecting a fastener element, for detecting the color of the surface of the fastener element of the zipper.

In the past, as for the quality management of the color of the fastener element of the zipper, since the element to be inspected is relatively small and the number is large, there is a slight error in the color caused by the subtle unevenness of the surface, so that it is difficult to achieve automation. It is done by manual visual inspection. However, in the visual inspection, even if the same sprocket material is used, the person who inspects has different ways of capturing the color, and the sensation is judged by the sensation. Therefore, the criterion for determining whether it is a good product is not fixed.

On the other hand, as a technique for quantitatively evaluating the color of the surface of the product and numerically determining the state of the color of the metal product, an inspection method as disclosed in Patent Document 1 has been proposed. The inspection method disclosed in Patent Document 1 divides a captured image of a surface of a metal material such as a steel material into a specific area, and acquires color information of red (R) green (G) blue (B) which is the primary color of light. The obtained information is digitized, compared with the pre-acquired information, and the non-corrosive surface is taken from the surface of the metal material to calculate the numerical range of the color ratio of the non-corrosive surface. Then, the corrosion portion of each of the divided surfaces is extracted, and the ratio of the area of the extracted corrosion portion to the surface area of the photographed metal is calculated, and the degree of deterioration of the metal surface is evaluated based on the area ratio of the corrosion portion. The step of extracting the non-corrosive surface is: in the first stage, the non-corrosive surface is obtained by comparing the numerical data of the divided surfaces with the numerical data of the previously obtained corrosion surface; and the second Stage, which is the non-corrosive surface taken in the first stage The numerical data is evaluated based on the Mahalanobis distance (mahalanobis), and the surface having the specific Mahalanobis distance is determined as a non-corrosive surface.

Similarly, in Patent Documents 2 and 3, there is also proposed an inspection apparatus that acquires information on the three primary colors of light on the surface of a metal material such as a steel material, and determines a good product and a defective product based on the ratio of the values of the respective color components.

Further, Patent Document 4 discloses a method of converting a RGB color system into an L*a*b* color system and extracting pixels of a specific value, thereby specifying a rust color region. Further, Patent Document 5 discloses a surface inspection apparatus that performs color imaging on a surface of an inspection object to obtain an RGB signal, and converts the RGB signal into a uniformity of an L*a*b* color system by the signal conversion unit. The color space signal is used for each pixel of the obtained inspection image, and the defect detecting unit detects whether or not the component of the divided region formed by dividing the color gamut (hue or chroma) of the uniform color space is obtained, thereby obtaining the corresponding segmentation. A binarized image of the hue or chroma of the area, based on which the colored defects of the surface are detected.

[Previous Technical Literature] [Patent Literature]

[Patent Document 1] Japanese Patent Laid-Open Publication No. 2007-256050

[Patent Document 2] Japanese Patent Laid-Open Publication No. 2003-216930

[Patent Document 3] Japanese Patent Laid-Open Publication No. 2012-149944

[Patent Document 4] Japanese Patent Laid-Open Publication No. 2005-291984

[Patent Document 5] Japanese Patent Laid-Open Publication No. 2005-233826

The surface inspection method disclosed in Patent Documents 1 to 5 is to photograph a surface of a large material such as a steel material integrally formed of the same material, and to process the image, the entire photographic image is the surface of the inspection object. The image, and for the inspection object, can obtain a sufficient amount of image information relatively easily.

However, when the inspection object such as the fastener element of the zipper is attached to a different type of material, the area of the information of the component to be obtained is small, and if the other components such as the zipper chain cloth are not accurately shielded, In the photographic image, information such as other components such as a fastener chain other than the sprocket is included, and it is difficult to perform accurate evaluation. Further, the chain teeth are small and the number is large, and it is also difficult to perform accurate shielding.

Moreover, since the type of the light source or the camera and the manner in which the image is captured are also affected by the judgment, it is difficult to accurately and stably evaluate the surface of the fastener element. Therefore, the inspection of the fastener elements of the zipper has no other method than visual inspection, and a system which can be quantitatively measured and evaluated is expected.

The present invention has been made in view of the above-described background art, and an object of the invention is to provide a method for setting an inspection condition and a fastener inspection method for accurately and stably evaluating whether or not the color of a fastener element of a slide fastener is good.

The present invention relates to a method for setting an inspection condition of a fastener element, which is based on an image obtained by photographing a surface of a fastener element of a fastener and an illumination device for illuminating the fastener element, and capturing an image of the fastener element Whether the color of the surface of the sprocket is a good one, which has a photographing step of selecting a plurality of controllable factors affecting the image taken by the camera, and setting a specific plurality of conditions for each controllable factor, Taking the plurality of the sprocket of the zipper at the same time by the above plurality of conditions of the controllable factors, the image capturing step is performed for the plurality of the sprocket having the camera obtained by the camera a color image for capturing color image data in each unit area of each of the fastener elements; and a luminance value calculation step of determining light of each pixel of the color image data of the unit area of each of the fastener elements a luminance value of each of the three primary colors; an error variance calculation step based on each of the three primary colors of the light calculated in the luminance value calculation step Luminance value, the calculation error of the color dispersion of the above-described fastener; controllable factors and selecting step which is based on a dispersion of the error obtained for each of the above can be The SN (Signal Noise) ratio and the sensitivity of the color of each of the fastener elements are calculated for each of the control factors, and the controllable factor is relatively large among the calculated SN ratio and the sensitivity. The setting conditions.

The error dispersion calculation step calculates the error dispersion by determining a feature value for each luminance value of each of the three primary colors of the light of each pixel of the color image data, and the feature value is light of each pixel of the color image data. The ratio of the luminance values of the three primary colors to the average of the luminance values of the three primary colors of the light corresponding to the plurality of sprocket teeth in the color image.

Further, the present invention relates to a sprocket inspection method for discriminating an image based on a camera that photographs a surface of a sprocket of a zipper and an illumination device that illuminates the sprocket, and images the sprocket Whether the color of the surface of the tooth is good or not, which has a photographing step of selecting a plurality of controllable factors affecting the image taken by the camera, and setting the conditions most suitable for the inspection for each controllable factor, And the plurality of conditions of the above controllable factors, and simultaneously capturing a plurality of the sprocket of the zipper; and an image capturing step for capturing a color image of the plurality of sprocket teeth obtained by the camera And extracting color image data in each unit area of each of the element teeth; and calculating a brightness value by determining each of the three primary colors of the light of each pixel of the color image data of the unit area of each of the element teeth a brightness value; and a determining step of calculating the color of the element based on the brightness value of each of the three primary colors of the light calculated in the brightness value calculating step With a particular value of the threshold value, and determines whether the color of the surface fastener of the above-described non-defective.

Further, the determining step is based on the luminance value of each of the three primary colors of the light calculated in the luminance value calculating step, the error dispersion of the color of the element is calculated, and the surface of the element is determined based on the obtained error dispersion. Whether the color is good. The optimum conditions of the above-mentioned controllable factors in the above-described photographing step are selected and set by the above-described controllable factor selection step using the above-described element inspection method.

According to the method for setting the inspection condition of the fastener element of the present invention and the method of detecting the element, it is possible to automatically and quickly and accurately determine whether or not the color of the fastener element of the fastener is good, so that good quality management can be stably performed.

10‧‧‧Inspection device

12‧‧‧ camera

14‧‧‧Lighting device

16‧‧‧ platform

18‧‧‧Clamp

19‧‧‧ Keeping Department

20‧‧‧ zipper

22‧‧‧Zipper chain cloth

24‧‧‧ sprocket

30‧‧‧Inspection device

32‧‧‧Lighting device

A1‧‧‧ level

A2‧‧‧ level

A3‧‧‧ level

B1‧‧‧ level

B2‧‧‧ level

B3‧‧‧ level

C1‧‧‧ level

C2‧‧‧ level

C3‧‧‧ level

D1‧‧ level

D2‧‧‧ level

D3‧‧‧ level

E1‧‧‧ level

E2‧‧‧ level

E3‧‧‧ level

F1‧‧‧ level

F2‧‧‧ level

F3‧‧‧ level

G1‧‧‧ level

G2‧‧‧ level

G3‧‧‧ level

H1‧‧ level

H2‧‧‧ level

H3‧‧‧ level

N1‧‧‧ conditions

N2‧‧ conditions

BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a schematic view showing an inspection apparatus according to an embodiment of the present invention.

Fig. 2 is a schematic view showing an inspection apparatus using another illumination device according to an embodiment of the present invention.

Fig. 3 is a schematic view showing a fastener element of a slide fastener photographed by the inspection apparatus of the embodiment.

Fig. 4 is a graph showing the SN ratio by the inspection condition setting method of the present invention.

Fig. 5 is a graph showing the sensitivity by the inspection condition setting method of the present invention.

Fig. 6 is a graph showing a confirmation experiment of error dispersion by optimal conditions by the inspection method of the present invention.

Fig. 7 is a graph showing a confirmation experiment of error dispersion by worst-case conditions by the inspection method of the present invention.

Hereinafter, an embodiment of the present invention will be described based on the drawings. As shown in Fig. 1, the inspection device 10 for detecting the condition of the fastener element of the zipper of the present embodiment and the inspection device 10 used in the fastener inspection method include a camera 12 including a CCD (Charge Coupled Device) or C- An imaging element such as MOS (Complementary Metal Oxide Semiconductor) can acquire image data of red (R), green (G), and blue (B), which are primary colors of light; and illumination device 14, The object is illuminated by light-collecting between dome-type illuminations such as LEDs (Light Emitting Diode) lamps using white light. The zipper 20 is held by the jig 18 disposed on the stage 16 on the opposite side of the illuminating device 14 from the camera 12.

The jig 18 is provided with a pair of holding portions 19 that sandwich the zipper chain 22 on both sides of the zipper 20, and the sprocket 24 of the zipper 20 is located between the holding portions 19. Here, the zipper 20 to be inspected is cut into a string-like member formed as a long strip of the zipper chain in the preceding stage of the single zipper 20, and intermittently conveyed to the jig 18 by the following photographic method The sprocket 24 is photographed.

Further, in order to set the inspection condition of the fastener element, the inspection device 30 of the illumination device 32 having the ring illumination shown in Fig. 2 is prepared as another configuration of the illumination device that affects the control factor of the measurement of the inspection object. The illumination surface of illumination device 32 is orthogonal to the optical axis of camera 12, and the center of the ring of illumination device 32 is concentric with the optical axis of camera 12.

By means of the inspection devices 10, 30, the images are taken in such a manner that, as shown in FIG. 3, the images of the plurality of zippers 20 are located at the center and include the image. For example, 6 chain teeth 24 are used. The photographed image data is processed by the following method, and the color or state of the surface of the fastener element 24 is evaluated to determine whether it is a good product.

Next, a method of setting the inspection condition for determining the fastener element inspection method of the present embodiment will be described below. First, selecting a plurality of controllable factors affecting the image captured by the camera 12, respectively, setting a specific plurality of conditions for each controllable factor, respectively, in a plurality of conditions of the controllable factors, respectively, in the plural of the zipper 20 Shooting is performed within the range of the sprocket 24 .

Here, the controllable factors as the inspection conditions are shown in Table 1. For example, there are 8 controllable factors, which are set as the level of a plurality of conditions for each controllable factor, and the level of the plurality of conditions is 2 or 3 parameters. As shown in Table 1, as the eight controllable factors, the camera type (F), illumination type (C), shutter speed (A), illumination intensity (D), and camera angle (G) are the basic elements of shooting. )Wait. Further, in order to observe the change in the stability caused by the increase or decrease in the number of teeth of the measurement target within the assumed range, the number of measured element teeth (B) is increased, and in order to observe the influence of the background color as an error factor, the addition is greater than, equal to, and less than The three measurement area sizes (E) of the sprocket 24 are added to confirm the influence of the heat generated by the LED. LED dead time (H).

Further, as shown in Table 2, the presence or absence of the ambient light and the background color was selected as an error factor affecting the measurement result. The condition N1 is set to ambient light and the background color is J1, the condition N2 is set to be no ambient light, and the background color is J2, and the condition is likely to cause an error.

Photographing the conditions of each level and error factors under these controllable factors to obtain the required amount of photographic data. Here, the acquired photographic data does not necessarily have to be photographic data obtained by photographing each of the fastener elements 24 under all the conditions of Tables 1 and 2. For example, it is sufficient to obtain photographic data within the range required for the L18 orthogonal table in the quality engineering, as long as the photographic data required for the inspection conditions required for the evaluation of the sprocket 24 is selected.

Next, for each color image of the plurality of sprocket 24 captured by the camera 12, the color image data in each unit area of each of the sprocket teeth 24 is extracted. Here, the unit area refers to a range of sizes selected from three regions larger than, equal to, and smaller than the chain teeth 24 according to the setting of the measurement region size of the above controllable factors.

Thereafter, the luminance values of the three primary colors of the light of each pixel of the color image data of the unit area of each element 24 are obtained. Further, for the image data of each pixel of the unit area of each element 24 of the image captured by the camera 12, the characteristic value y _kn (k is obtained for each RGB based on the luminance value of each pixel is obtained. Sample No., n is the characteristic value No. of the sample). Then, based on the characteristic values, the error dispersion of each sample is calculated by the following formulas (1) to (7). The error dispersion can be obtained for each zipper 20, or can be obtained for each fixed length of the zipper chain 22.

R _ij is a pixel that outputs red image data, and the position of the pixel represents the value of the brightness of i, j (ij is an arbitrary natural number). G _ij and B _{ij are} also the same. , , It is an average value of the brightness of each RGB of the sprocket of the object to be inspected.

( The average value of k = 1~10 for y _kn )

[Number 3] Change: S _T (k)S _T (k)=y _k1 ' ² +y _k2 ' ² +...y _kn ' ² (3)

[Number 4] The magnitude of the deviation: S _m (k)S _m (k)=(y _k1 '+y _k2 '+...y _kn ') ² /n (4)

[Number 5] Dispersion: V _e V _e = (S _T (k) - S _m (k)) / (n-1) (5)

[Number 6] Dispersion of good products as a whole: V ₀ V ₀ = (S _T (1~10)-S _m (1~10)) / (10‧(n-1)) (6)

[Number 7] Error dispersion: D(k)D(k)={(S _m (k)+V _e (k))/V ₀ } ^1/2 (7)

As described above, based on the formula (7), the value of the error dispersion of the luminance values of the fastener elements 24 is obtained for each sample. Here, the obtained error dispersion is D(1) to D(k), and the discoloration processing amount X ₁ to X of the fastener element 24 of the zipper 20 of each sample is set for the error factors N1 and N2 of the measurement environment. _k , the error dispersion is obtained for each zipper 20. The amount of discoloration treatment refers to a value in which the surface of the fastener element 24 is previously discolored in order to set the inspection condition of the fastener element 24, and the degree of discoloration differs depending on the specific heat treatment time. This sample was used to obtain data for setting of inspection conditions performed before actual inspection, and was used in the following verification experiment. Table 3 shows the correspondence between the amount of color change processing and the error dispersion obtained in this way.

Thereafter, in order to select a controllable factor of the optimum condition, the SN ratio and the sensitivity are obtained by the following equation.

[Number 9] Effective divisor: r ₁ r ₁ = r ₂ = X ₁ ² + X ₂ ² + ... + X _k ² (9)

[Number 10] Linear formula: L ₁ , L ₂ L ₁ = X ₁ × D(1) + X ₂ × D(2) + ... + X _k × D(k) L ₂ = X ₁ × D(1) '+X ₂ ×D(2)'+...+X _k ×D(k)' (10)

[Number 11] Variation of the proportional term: S _β S _β = (L ₁ + L ₂ ) ² / (r ₁ + r ₂ ) (11)

[Number 12] Variation of the difference between the proportional terms: S _{N × β} S _{N × β} = (L ₁ ² / r ₁ ) ‧ (L ₂ ² / r ₂ ) (12)

[Number 13] Error variation: S _e S _e =S _T -S _β -S _N×β (f=k+k'-2) (13)

[Number 14] Change: S _N S _N =S _N×β +S _e (f=k+k'-2) (14)

[Number 15] Deviation dispersion: V _e ' V _e '=S _e /f (15)

[Number 16] Comprehensive deviation dispersion: V _N V _N =S _N /f (16)

[Number 17] SN ratio: η η = 10‧log[{1/(r ₁ +r ₂ )}×{(S _β -V _e ')/V _N }] (17)

[Number 18] Sensitivity: SS=10‧log[{1/(r ₁ +r ₂ )}×(S _β -V _e ')] (18)

Based on the above formula, for the above eight controllable factors, the error dispersion is calculated in the above manner based on the luminance values obtained for each RGB from the photographic image, and further, the SN ratio and the sensitivity are calculated based on the equations (17) and (18). According to this value, the optimal condition of the controllable factor is selected. As shown in the experimental results shown in FIG. 4 and FIG. 5 below, the optimal conditions for each controllable factor selected according to the SN ratio and the sensitivity are selected based on the values of the SN ratio and the sensitivity, and are based on FIG. 4 and FIG. The indication is selected for the rendering.

The combination of ○ and ◇ shown in the effect diagrams of Fig. 4 and Fig. 5 indicates that SN ratio and sensitivity are higher in combination with (○), and (SN) indicates that the SN ratio and sensitivity are relatively low. The combination of the worst conditions. Thereby, the setting conditions of the ○ mark shown in the figure are set as the optimum conditions for the product inspection for each controllable factor. For example, in the present embodiment, regarding the type of illumination, the dome type illumination shown in FIG. 1 is superior to the ring type illumination device shown in FIG. 2 in terms of sensitivity, and the measurement area size is equal to that of the element teeth 24. In the case, the SN ratio gives better results. Similarly, for other controllable factors, the conditions for obtaining good results are also determined based on the SN ratio and sensitivity, and the inspection is performed.

If the controllable factors for the optimal conditions for inspection are selected by the above-mentioned inspection method for the condition of the fastener elements, the level of each controllable factor is set to the selected optimum condition in the subsequent inspection. Under this condition, the sprocket 24 is photographed.

Next, for the obtained color image of the plurality of sprocket 24 images, the color image data in each unit area of each sprocket 24 is extracted, and the color image data of the unit area of each sprocket 24 is obtained. The luminance values of the three primary colors of the light of each pixel are calculated based on the luminance values of the three primary colors of the calculated light, and the error dispersion of the color of the fastener elements 24 is calculated by the same calculation process as described above. Then, based on the obtained error dispersion, it is determined whether or not the color of the surface of the element 24 is good based on whether or not the error dispersion is equal to or less than a fixed value.

Moreover, the determination may not calculate the error dispersion, but the determination of the optimal controllable factor Under the conditions, other color evaluations are performed, for example, color evaluation is performed based on the value of the L*a*b* color system.

According to the sprocket inspection condition setting method and the sprocket inspection method of the present embodiment, it is possible to objectively and quantitatively determine whether or not the color of the sprocket 24 of the zipper 20 is good, and it is possible to automatically and quickly determine whether the surface color is good or not. Thereby, good quality management can be performed stably.

Further, the method for setting the inspection conditions of the fastener elements of the present invention and the method for detecting the fastener elements are not limited to the above-described embodiments, and the controllable factors or the error factors can be appropriately set, and the number of factors can be appropriately selected.

Example

Next, an embodiment of the method for setting the inspection conditions of the fastener element of the present invention and the method of detecting the fastener element will be described below. Here, the experimental results obtained by verifying the test condition setting method and the fastener element inspection method of the fastener element of the present invention are shown. First, the measurement target is assumed to be a defective product having a different color, and a product subjected to the staged color change treatment X ₁ to X _k and an unprocessed product (good product) are prepared. The output value of the camera 12 or the output value from a computer (not shown) obtained by processing the output from the camera 12 is a luminance value obtained for each pixel of the imaging element of the camera 12, and each color R is used in 256 tones. , G, B value.

The experimental results are shown in the effect diagrams of FIGS. 4 and 5. Regarding ○ and ◇, based on the effect map, (○) indicates a combination of the optimum conditions of the SN ratio and the sensitivity, and (◇) indicates a combination of the worst conditions in which the SN ratio and the sensitivity are relatively low. Thereby, the setting conditions of the ○ mark shown in the figure are set as the optimum conditions for the product inspection for each controllable factor. The screening of the best conditions and the worst conditions is shown in Table 4.

The results obtained by measuring under the best conditions and the worst conditions are shown in Fig. 6 and Fig. 7. Under the optimal conditions shown in Fig. 6, under the above two conditions of N1 and N2, as the amount of processing increases, the error dispersion becomes larger with the same tendency, and it can be known that it is not affected by the error factor. Determine the change in color. Further, under the worst conditions shown in Fig. 7, the tendency to be completely different under the conditions of N1 and N2 was confirmed, and it was confirmed that the measurement was largely affected by the error factor, and stable measurement could not be performed.

Table 5 shows the optimum conditions of the SN ratio and sensitivity calculated based on the experiment of the L18 orthogonal table used in the present invention, the SN ratio of the worst condition, the estimated value and the gain of the sensitivity, and the confirmation experiment. The result and gain of the SN ratio and sensitivity obtained. The gain obtained by the confirmation experiment is about 3 [db] lower than the estimated value, and the sensitivity is about 40 higher than the estimated value, which is the same tendency, and the validity and reproducibility of the factor can be confirmed.

According to the above results, it has been confirmed that in the color measurement of the fastener elements of the slide fastener, the conditions for stably identifying the products having different colors can be selected, and the color of the fastener elements of the slide fastener can be examined with high quality.

10‧‧‧Inspection device

12‧‧‧ camera

14‧‧‧Lighting device

16‧‧‧ platform

18‧‧‧Clamp

19‧‧‧ Keeping Department

20‧‧‧ zipper

22‧‧‧Zipper chain cloth

24‧‧‧ sprocket

Claims (4)

A method for setting inspection condition of a fastener element based on a camera (12) for photographing a surface of a fastener element (24) of a zipper (20), and an illumination device (14) for illuminating the fastener element (24) And photographing the image of the sprocket (24) to determine whether the color of the surface of the sprocket (24) is good, and the method includes: a photographing step, wherein the selection affects the photograph taken by the camera (12) a plurality of controllable factors of the image, respectively, a specific plurality of conditions are set for each controllable factor, and the plurality of the above-mentioned fastener elements of the zipper (20) are simultaneously simultaneously performed by the plurality of conditions of the above controllable factors ( 24) performing a photographing; an image capturing step of capturing a plurality of color images obtained by the camera (12) and having a plurality of the sprocket teeth (24), and taking the sprocket (24) a color image data in each unit area; a luminance value calculating step of determining luminance values of respective three primary colors of light of each pixel of the color image data of the unit area of each of the element teeth (24); a dispersion calculation step based on the step of calculating the brightness value Calculating the error dispersion of the color of the sprocket (24) in the above-mentioned brightness values of the three primary colors calculated in the light; and controlling the factor selection step based on the obtained error dispersion, for each of the above controllable factors For each of the setting conditions, the SN ratio and the sensitivity of the color of each of the fastener elements (24) are calculated, and among the calculated SN ratio and the sensitivity, the setting condition of the controllable factor having a relatively large selection value is determined. The method for setting an inspection condition of a fastener element according to claim 1, wherein the error dispersion calculation step calculates the error dispersion by determining a feature value for each luminance value of each of three primary colors of light of each pixel of the color image data, and The characteristic value is a brightness value of each of the three primary colors of the light of each pixel of the color image data relative to the color image The ratio of the average values of the luminance values of the three primary colors of the light corresponding to the plurality of sprocket teeth (24). A sprocket inspection method based on a camera (12) that photographs a surface of a sprocket (24) of a zipper (20) and an illumination device (14) that illuminates the sprocket (24) The image of the sprocket (24) determines whether the color of the surface of the sprocket (24) is good or not, and is characterized by: a photographing step of selecting an image captured by the camera (12) a plurality of controllable factors, respectively setting conditions that are most suitable for inspection for each controllable factor, and photographing a plurality of the aforementioned fastener elements (24) of the zipper (20) simultaneously with the plurality of conditions of the above controllable factors An image capturing step of capturing color in each unit area of each of the sprocket teeth (24) for a color image obtained by the camera (12) and having a plurality of the sprocket teeth (24) An image data; a luminance value calculation step of determining luminance values of respective three primary colors of light of each pixel of the color image data in the unit area of each of the element teeth (24); and a determining step Based on each of the three primary colors of the light calculated in the above-described luminance value calculation step The value of the color of the element (24) calculated by the brightness value is compared with a specific threshold value, and it is determined whether or not the color of the surface of the element (24) is good. The sprocket inspection method according to claim 3, wherein the discriminating step calculates the error dispersion of the color of the sprocket (24) based on the luminance value of each of the three primary colors of the light calculated in the luminance value calculation step, and based on The above-mentioned error dispersion is obtained, and it is determined whether or not the color of the surface of the fastener element (24) is good.