TWI583942B - Check the device and check the method - Google Patents

Check the device and check the method Download PDF

Info

Publication number
TWI583942B
TWI583942B TW105108180A TW105108180A TWI583942B TW I583942 B TWI583942 B TW I583942B TW 105108180 A TW105108180 A TW 105108180A TW 105108180 A TW105108180 A TW 105108180A TW I583942 B TWI583942 B TW I583942B
Authority
TW
Taiwan
Prior art keywords
hue value
workpiece
distribution profile
peaks
inspection
Prior art date
Application number
TW105108180A
Other languages
Chinese (zh)
Other versions
TW201641932A (en
Inventor
Tadayuki Fujiwara
Original Assignee
Shimadzu Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shimadzu Corp filed Critical Shimadzu Corp
Publication of TW201641932A publication Critical patent/TW201641932A/en
Application granted granted Critical
Publication of TWI583942B publication Critical patent/TWI583942B/en

Links

Description

檢查裝置以及檢查方法Inspection device and inspection method

本發明是有關於一種使用圖像進行形成於工件(work)的膜的良否判定的檢查裝置以及檢查方法。The present invention relates to an inspection apparatus and an inspection method for determining the quality of a film formed on a work using an image.

對太陽電池單元或半導體裝置中使用的基板等工件,進行使用了工件的圖像的外觀檢查(例如參照專利文獻1)。使用了圖像的外觀檢查中採用各種方法。An appearance inspection of an image using a workpiece is performed on a workpiece such as a substrate used in a solar battery cell or a semiconductor device (see, for example, Patent Document 1). Various methods are used in the visual inspection using images.

例如,關於形成於工件的膜的膜質或膜厚等的均勻性,能夠根據成膜後的工件的色彩進行良否判定。即,根據由工件的彩色圖像而獲得的各色的強度針對圖像的每個點算出色相(HUE)值,對於HUE值將度數作圖而獲得HUE值分佈輪廓(distribution profile)。然後,以所獲得的HUE值分佈輪廓的度數波峰(peak)的高度或寬度為基準進行良否判定。通常,在膜不均勻的情況下,HUE值分佈輪廓的度數波峰寬度變寬。因此,在度數波峰寬度為規定的寬度以下的情況下,判定為正常地成膜。 [現有技術文獻] [專利文獻]For example, the uniformity of the film quality, the film thickness, and the like of the film formed on the workpiece can be determined based on the color of the workpiece after film formation. That is, a hue (HUE) value is calculated for each point of the image based on the intensity of each color obtained from the color image of the workpiece, and a degree profile is plotted for the HUE value to obtain an HUE value distribution profile. Then, the quality is judged based on the height or width of the peak of the obtained HUE value distribution profile. Generally, in the case where the film is not uniform, the peak width of the HUE value distribution profile is widened. Therefore, when the peak width of the power is equal to or smaller than the predetermined width, it is determined that the film is formed normally. [Prior Art Document] [Patent Literature]

[專利文獻1]日本專利特開2012-7952號公報[Patent Document 1] Japanese Patent Laid-Open Publication No. 2012-7952

[發明所欲解決之課題][Problems to be solved by the invention]

在工件上正常地成膜的情況下的HUE值分佈輪廓的度數波峰數為一個,從而在具有多個度數波峰的情況下應判定為不良。然而,在多個度數波峰接近地存在的情況下,多個度數波峰重疊而HUE值分佈輪廓整體的度數波峰寬度變窄。此時,在使用度數波峰寬度進行良否判定的情況下,有判定次品為良品,而良否判定的精度下降之虞。The number of peaks of the HUE value distribution profile in the case where the film is normally formed on the workpiece is one, and it is judged to be defective in the case of having a plurality of power peaks. However, when a plurality of power peaks are present in close proximity, the plurality of power peaks overlap and the peak width of the entire HUE value distribution profile is narrowed. In this case, when the quality peak width is used to determine the quality, the quality of the defective product is determined to be good, and the accuracy of the quality determination is lowered.

鑒於所述問題,本發明的目的在於提供使用圖像高精度地進行形成於工件的膜的良否判定的檢查裝置以及檢查方法。 [解決課題之手段]In view of the above problems, an object of the present invention is to provide an inspection apparatus and an inspection method for accurately determining the quality of a film formed on a workpiece using an image. [Means for solving the problem]

根據本發明的一形態,提供一種檢查裝置,包括:(a)圖像獲取裝置,獲取經成膜處理的工件的檢查圖像;以及(b)判定裝置,對檢查圖像的各點算出HUE值,將HUE值的度數作圖而作成HUE值分佈輪廓,在HUE值分佈輪廓的度數波峰數為一個的情況下判定工件為良品,在度數波峰數為多個的情況下判定工件為不良。According to an aspect of the present invention, an inspection apparatus includes: (a) an image acquisition device that acquires an inspection image of a film-formed workpiece; and (b) a determination device that calculates a HUE for each point of the inspection image The value is plotted as a HUE value distribution profile, and when the number of peaks of the HUE value distribution profile is one, the workpiece is judged to be good, and when the number of peaks is plural, the workpiece is judged to be defective.

根據本發明的另一形態,提供一種檢查方法,包括下述步驟:(a)獲取經成膜處理的工件的檢查圖像,(b)對檢查圖像的各點算出HUE值,將HUE值的度數作圖而作成HUE值分佈輪廓,以及(c)在HUE值分佈輪廓的度數波峰數為一個的情況下判定工件為良品,在度數波峰數為多個的情況下判定工件為不良。 [發明的效果]According to another aspect of the present invention, there is provided an inspection method comprising the steps of: (a) acquiring an inspection image of a film-formed workpiece, and (b) calculating an HUE value for each point of the inspection image, and setting the HUE value When the degree map is plotted, the HUE value distribution profile is created, and (c) when the number of peaks of the HUE value distribution profile is one, the workpiece is judged to be good, and when the number of peaks is plural, the workpiece is judged to be defective. [Effects of the Invention]

根據本發明,可提供使用圖像高精度地進行形成於工件的膜的良否判定的檢查裝置以及檢查方法。According to the present invention, it is possible to provide an inspection apparatus and an inspection method for accurately determining the quality of a film formed on a workpiece using an image.

接下來,參照圖式對本發明的實施形態進行說明。在以下的圖式的記載中,對相同或類似的部分附上相同或類似的符號。其中,應留意圖式為示意性的圖。而且,以下所示的實施形態例示用以將該發明的技術思想具體化的裝置或方法,該發明的實施形態並非將構成零件的構造、配置等特定為下述內容。該發明的實施形態在申請專利範圍內可添加各種變更。Next, an embodiment of the present invention will be described with reference to the drawings. In the description of the following drawings, the same or similar reference numerals are attached to the same or similar parts. Wherein, the intentional expression is a schematic diagram. In addition, the embodiment described below exemplifies an apparatus or method for embodying the technical idea of the invention, and the embodiment of the invention does not specify the structure, arrangement, and the like of the component parts as follows. Embodiments of the invention may be modified in various ways within the scope of the patent application.

(第1實施形態) 圖1所示的本發明的第1實施形態的檢查裝置1根據工件100的色彩對形成於工件100的膜的均勻性進行檢查,並進行工件100的良否判定。檢查裝置1包括:照明裝置10,對經成膜處理的工件100照射檢查光L;圖像獲取裝置20,對照射了檢查光L的工件100進行拍攝而獲取工件100的檢查圖像;以及判定裝置30,使用根據檢查圖像製作的HUE值分佈輪廓進行工件100的良否判定。(First Embodiment) The inspection apparatus 1 according to the first embodiment of the present invention shown in Fig. 1 inspects the uniformity of the film formed on the workpiece 100 based on the color of the workpiece 100, and determines whether or not the workpiece 100 is good or bad. The inspection apparatus 1 includes an illumination device 10 that irradiates the film 100 subjected to the film formation process with the inspection light L, and an image acquisition device 20 that images the workpiece 100 irradiated with the inspection light L to acquire an inspection image of the workpiece 100; The device 30 performs the quality determination of the workpiece 100 using the HUE value distribution profile created from the inspection image.

判定裝置30的輪廓製作部31根據由圖像獲取裝置20獲取的彩色的檢查圖像對各種光算出HUE值。例如,藉由輪廓製作部31,根據紅色(R)光、綠色(G)光及藍色(B)光的強度對檢查圖像的各點算出HUE值,針對每種顏色製作將HUE值的度數作圖而成的HUE值分佈輪廓。The contour creating unit 31 of the determining device 30 calculates an HUE value for various lights based on the color inspection image acquired by the image acquiring device 20. For example, the contour creating unit 31 calculates an HUE value for each point of the inspection image based on the intensities of the red (R) light, the green (G) light, and the blue (B) light, and creates an HUE value for each color. The HUE value distribution profile drawn by the degree.

判定裝置30的判定部32對各色的HUE值分佈輪廓檢測HUE值的度數波峰。然後,判別度數波峰數為一個還是多個,在度數波峰數為一個的情況下,判定工件100為良品,在度數波峰數為多個的情況下,判定工件100為次品。The determination unit 32 of the determination device 30 detects the degree peak of the HUE value for the HUE value distribution profile of each color. Then, the number of peaks of the degree of determination is one or more, and when the number of peaks is one, the workpiece 100 is determined to be good, and when the number of peaks is plural, the workpiece 100 is determined to be defective.

另外,HUE值分佈輪廓的HUE值的總數根據圖像獲取裝置20的解析度而規定。例如,在圖像獲取裝置20的解析度為2048畫素×2048畫素的情況下,HUE值的總數為2048×2048個。圖像獲取裝置20中能夠採用例如電荷耦合元件(charge coupled device,CCD)相機或互補型金屬氧化膜半導體(complementary metal oxide semiconductor,CMOS)相機等。圖像獲取裝置20所拍攝到的圖像資料D作為檢查圖像發送至判定裝置30。Further, the total number of HUE values of the HUE value distribution profile is defined in accordance with the resolution of the image acquisition device 20. For example, in the case where the resolution of the image acquisition device 20 is 2048 pixels × 2048 pixels, the total number of HUE values is 2048 × 2048. For example, a charge coupled device (CCD) camera or a complementary metal oxide semiconductor (CMOS) camera or the like can be employed in the image acquisition device 20. The image data D captured by the image acquisition device 20 is sent to the determination device 30 as an inspection image.

而且,為了如所述般根據檢查圖像對多種顏色分別製作HUE值分佈輪廓,準備能夠出射可獲得所需顏色的檢查圖像的檢查光L的照明裝置10。照明裝置10中能夠採用例如將紅色(R)光、綠色(G)光及藍色(B)光同時或個別輸出的發光二極體(Light Emitting Diode,LED)等。為了將形成於工件100的膜的分佈容易表示為HUE值的分佈而選擇檢查光L的波長。Further, in order to create an HUE value distribution profile for each of the plurality of colors based on the inspection image as described above, the illumination device 10 capable of emitting the inspection light L of the inspection image of the desired color is prepared. For example, a light-emitting diode (LED) that emits red (R) light, green (G) light, and blue (B) light simultaneously or individually can be used for the illumination device 10. The wavelength of the inspection light L is selected in order to easily express the distribution of the film formed on the workpiece 100 as the distribution of the HUE value.

在根據色彩進行工件100的良否判定的情況下,形成於工件100的膜均勻的良品中,在檢查圖像的整個區域HUE值大致固定。因此,如圖2所示,良品的HUE值分佈輪廓的HUE值的度數波峰數為一個,且度數波峰的寬度窄。另一方面,在形成於工件100的膜的膜厚或膜質不均勻的情況下,一般而言如圖3所示,HUE值分佈輪廓中的HUE值的度數波峰的寬度W變寬。因此,基於良品的HUE值分佈輪廓來設定度數波峰的寬度W的規定值,在度數波峰的寬度W超過規定值的情況下,可判定工件100為次品。When the quality of the workpiece 100 is determined based on the color, the film is formed in a uniform film of the workpiece 100, and the HUE value is substantially constant over the entire area of the inspection image. Therefore, as shown in FIG. 2, the number of peaks of the HUE value of the HUE value distribution profile of the good product is one, and the width of the power peak is narrow. On the other hand, when the film thickness or film quality of the film formed on the workpiece 100 is not uniform, generally, as shown in FIG. 3, the width W of the power peak of the HUE value in the HUE value distribution profile is widened. Therefore, the predetermined value of the width W of the power peak is set based on the HUE value distribution profile of the good product, and when the width W of the power peak exceeds a predetermined value, the workpiece 100 can be determined to be defective.

然而,存在如下情況,即,多個度數波峰接近地存在,該些度數波峰重疊而HUE值分佈輪廓整體的度數波峰寬度窄。若在該情況下基於度數波峰的寬度W進行良否判定,則有將作為次品的工件100誤判定為良品之虞。例如圖4所示,即便在HUE值分佈輪廓中顯現出兩個度數波峰P1、度數波峰P2的情況下,在將兩個度數波峰重合而成的整體的度數波峰的寬度W比規定的判定值窄的情況下,亦會將次品誤判定為良品。However, there are cases where a plurality of power peaks are closely present, the peaks of the plurality of degrees overlap, and the peak width of the entire HUE value distribution profile is narrow. In this case, if the quality W is determined based on the width W of the power peak, the workpiece 100 which is a defective product is erroneously determined to be a good one. For example, as shown in FIG. 4, even when two degree peaks P1 and a number of peaks P2 appear in the HUE value distribution profile, the width W of the entire power peak obtained by superimposing the two power peaks is larger than a predetermined determination value. In the case of a narrow case, the defective product will also be mistakenly judged as a good product.

與此相對,檢查裝置1中,因HUE值分佈輪廓中的HUE值的度數波峰數為多個,故將具有圖4所示的HUE值分佈輪廓的工件100正確地判定為次品。On the other hand, in the inspection apparatus 1, since the number of peaks of the HUE value in the HUE value distribution profile is plural, the workpiece 100 having the HUE value distribution profile shown in FIG. 4 is correctly determined as a defective product.

如以上說明般,根據本發明的第1實施形態的檢查裝置1,能夠進行精度高的良否判定。其結果,防止次品的工件100進入到後續步驟,而可抑制無用處理的執行。因此,可藉由檢查裝置1實現製造成本的削減及品質提高。As described above, the inspection apparatus 1 according to the first embodiment of the present invention can perform high-precision determination. As a result, the workpiece 100 of the defective product is prevented from entering the subsequent step, and the execution of the useless processing can be suppressed. Therefore, it is possible to reduce the manufacturing cost and improve the quality by the inspection device 1.

另外,檢查裝置1不僅將HUE值分佈輪廓的度數波峰的數量,還將度數波峰的寬度或位置、高度等參數與規定的判定值進行比較,藉此可綜合性地進行工件100的良否判定。例如,即便度數波峰數為一個,在度數波峰的寬度比判定值寬的情況下、度數波峰的高度比判定值低的情況下、度數波峰的HUE值不處於判定值的範圍的情況下中的至少任一情況下,判定部32判定工件100為次品。Further, the inspection apparatus 1 can perform not only the number of the peaks of the HUE value distribution profile but also the parameters such as the width, the position, and the height of the peak, and the predetermined determination value, thereby comprehensively determining the quality of the workpiece 100. For example, when the number of peaks is one, and the width of the power peak is wider than the determination value, and the height of the power peak is lower than the determination value, and the HUE value of the power peak is not within the range of the determination value, In at least either case, the determination unit 32 determines that the workpiece 100 is a defective product.

(第2實施形態) 本發明的第2實施形態的檢查裝置1如圖5所示,判定裝置30進而包括將檢查圖像分割為多個分割區域的分割部33。關於其他構成,與圖1所示的第1實施形態相同。圖5所示的檢查裝置1中,對各個分割區域製作HUE值分佈輪廓,並檢測度數波峰的數量。(Second Embodiment) As shown in Fig. 5, the inspection apparatus 1 according to the second embodiment of the present invention further includes a division unit 33 that divides the inspection image into a plurality of divided regions. The other configuration is the same as that of the first embodiment shown in Fig. 1 . In the inspection apparatus 1 shown in FIG. 5, an HUE value distribution profile is created for each divided area, and the number of power peaks is detected.

存在如下情況,即,形成於工件100的膜的膜厚或膜質等異常的異常區域局部地存在於工件100的一部分區域。該情況下,起因於異常區域的HUE值分佈輪廓的度數波峰有時未顯現為檢查圖像整體的HUE值分佈輪廓。There is a case where an abnormal region such as a film thickness or a film quality of the film formed on the workpiece 100 is partially present in a partial region of the workpiece 100. In this case, the power peak of the HUE value distribution profile due to the abnormal region may not appear as the HUE value distribution profile of the entire inspection image.

例如,如圖6所示,考慮僅在工件100的檢查圖像200的一部分產生異常區域210的情況。此時,如圖7所示,存在如下情況,即,起因於異常區域210的HUE值分佈輪廓的度數波峰Pf隱藏於整體的度數波峰Pa中。該情況下,僅檢測到工件100整體的度數波峰Pa,而未檢測到起因於異常區域210的度數波峰Pf。因此,在根據工件100整體的度數波峰的數量進行良否判定的情況下,所檢測到的度數波峰數為一個,從而會將工件100誤判定為良品。For example, as shown in FIG. 6, a case where the abnormal region 210 is generated only in a part of the inspection image 200 of the workpiece 100 is considered. At this time, as shown in FIG. 7, there is a case where the power peak Pf of the HUE value distribution profile resulting from the abnormal region 210 is hidden in the entire power peak Pa. In this case, only the power peak Pa of the entire workpiece 100 is detected, and the power peak Pf due to the abnormal region 210 is not detected. Therefore, in the case where the quality is determined based on the number of peaks of the entire workpiece 100, the number of detected peaks is one, and the workpiece 100 is erroneously determined to be good.

然而,根據第2實施形態的檢查裝置1,可防止所述誤判定。以下,對圖5所示的檢查裝置1的檢查方法進行說明。However, according to the inspection apparatus 1 of the second embodiment, the erroneous determination can be prevented. Hereinafter, an inspection method of the inspection apparatus 1 shown in FIG. 5 will be described.

首先,分割部33將由圖像獲取裝置20獲取的檢查圖像分割為多個分割區域。例如,將圖6所示的檢查圖像200如圖8所示般分割為分割區域201~分割區域204。First, the division unit 33 divides the inspection image acquired by the image acquisition device 20 into a plurality of divided regions. For example, the inspection image 200 shown in FIG. 6 is divided into the divided region 201 to the divided region 204 as shown in FIG. 8 .

繼而,輪廓製作部31對分割區域的各點算出HUE值,針對每個分割區域製作HUE值分佈輪廓。即,對各個分割區域201~分割區域204製作HUE值分佈輪廓。Then, the contour creating unit 31 calculates an HUE value for each point of the divided region, and creates an HUE value distribution profile for each divided region. That is, an HUE value distribution profile is created for each of the divided regions 201 to 204.

然後,判定部32對每個分割區域的HUE值分佈輪廓檢測HUE值的度數波峰,並判別度數波峰數是一個還是多個。判定部32在所有分割區域中HUE值分佈輪廓的度數波峰數為一個的情況下,判定工件100為良品。另一方面,在至少一個分割區域中HUE值分佈輪廓的度數波峰數為多個的情況下,判定部32判定工件100為次品。另外,判定部32的良否判定可在所有的分割區域同時進行,亦可針對每個分割區域依次進行。Then, the determination unit 32 detects the peak of the HUE value for the HUE value distribution profile of each divided region, and determines whether the number of peaks is one or more. When the number of peaks of the HUE value distribution profile is one in all the divided regions, the determination unit 32 determines that the workpiece 100 is a good product. On the other hand, when there are a plurality of power peak numbers of the HUE value distribution profile in at least one divided region, the determination unit 32 determines that the workpiece 100 is a defective product. Further, the determination of the quality of the determination unit 32 may be performed simultaneously in all of the divided areas, or may be sequentially performed for each of the divided areas.

圖8所示的例中,對不包含異常區域的分割區域201、分割區域202及分割區域204,如圖9所示般檢測各自的一個度數波峰。然而,對包含異常區域的分割區域203,如圖10所示般檢測多個度數波峰。其結果,工件100被判定為次品。In the example shown in FIG. 8, each of the divided peaks 201, the divided regions 202, and the divided regions 204 that do not include the abnormal region is detected as shown in FIG. However, for the divided region 203 including the abnormal region, a plurality of power peaks are detected as shown in FIG. As a result, the workpiece 100 is judged to be defective.

另外,如圖8所示般,較佳為分割區域201~分割區域204的外緣部彼此重合。藉此,能夠確實地檢測分割區域的邊界處的異常。Further, as shown in FIG. 8, it is preferable that the outer edge portions of the divided regions 201 to 204 overlap each other. Thereby, it is possible to reliably detect an abnormality at the boundary of the divided region.

所述以上例示性地敍述了將檢查圖像分割為四個分割區域的情況,但分割區域的數量當然不限於四個。分割區域的數量越多,能夠檢測到越小面積的異常區域或越微小的不均勻性。另一方面,分割區域的數量越多則檢查時間越多。因此,根據能夠容許的異常區域的面積或不均勻性及處理時間,適當設定分割區域的數量即可。The above exemplarily describes the case where the inspection image is divided into four divided regions, but the number of divided regions is of course not limited to four. The larger the number of divided regions, the smaller the abnormal area or the smaller the unevenness can be detected. On the other hand, the more the number of divided regions, the more inspection time. Therefore, the number of divided regions may be appropriately set in accordance with the area or unevenness of the abnormal region that can be tolerated and the processing time.

如以上說明,根據第2實施形態的檢查裝置1,即便在異常區域僅局部存在於工件100的一部分區域的情況下,亦能夠進行高精度的良否判定。其他與第1實施形態實質相同,並省略重複記載。As described above, according to the inspection apparatus 1 of the second embodiment, even when the abnormal region exists only partially in a part of the workpiece 100, it is possible to perform high-precision determination. Others are substantially the same as those of the first embodiment, and the repeated description is omitted.

(其他實施形態) 如所述般,本發明由實施形態記載,但不應理解成為該揭示的一部分的論述及圖式為限定本發明者。根據該揭示,本領域技術人員可知各種代替實施形態、實施例及運用技術。(Other Embodiments) As described above, the present invention is described by the embodiments, but the description and drawings which are a part of the disclosure are not to be construed as limiting the invention. Based on this disclosure, various alternative embodiments, examples, and operational techniques will be apparent to those skilled in the art.

以上的說明中,表示了判定裝置30根據檢查圖像對多種顏色分別製作HUE值分佈輪廓的例。然而,也可僅針對一種顏色製作HUE值分佈輪廓。例如藉由僅對膜厚或膜質的不均勻性容易顯現的顏色製作HUE值分佈輪廓,而可縮短良否判定所需的時間。In the above description, an example in which the determination device 30 creates an HUE value distribution profile for each of a plurality of colors based on the inspection image is shown. However, it is also possible to create an HUE value distribution profile for only one color. For example, by forming a HUE value distribution profile only for a color that is easy to appear in film thickness or film quality unevenness, the time required for good or bad determination can be shortened.

如所述般,本發明當然包含此處未記載的各種實施形態等。因此,本發明的技術範圍僅由根據上述說明而來的適當的申請專利範圍所限定的發明特定事項而規定。As described above, the present invention naturally includes various embodiments and the like not described herein. Therefore, the technical scope of the present invention is defined only by the specific matters of the invention as defined by the scope of the Applicable Patent Application.

1‧‧‧檢查裝置
10‧‧‧照明裝置
20‧‧‧圖像獲取裝置
30‧‧‧判定裝置
31‧‧‧輪廓製作部
32‧‧‧判定部
33‧‧‧分割部
100‧‧‧工件
200‧‧‧檢查圖像
201~204‧‧‧分割區域
210‧‧‧異常區域
D‧‧‧圖像資料
L‧‧‧檢查光
P1、P2‧‧‧度數波峰
Pa‧‧‧整體的度數波峰
Pf‧‧‧起因於異常區域的HUE值分佈輪廓的度數波峰
W‧‧‧度數波峰的寬度
1‧‧‧Checking device
10‧‧‧Lighting device
20‧‧‧Image acquisition device
30‧‧‧Determining device
31‧‧‧Contour Production Department
32‧‧‧Decision Department
33‧‧‧ Division
100‧‧‧Workpiece
200‧‧‧Check the image
201~204‧‧‧Divided area
210‧‧‧Abnormal area
D‧‧‧Image data
L‧‧‧Check light
P1, P2‧‧‧degree peaks
Pa‧‧‧ overall peaks
Pf‧‧‧degree peaks due to the distribution of HUE values in anomalous regions
W‧‧‧degree peak width

圖1是表示本發明的第1實施形態的檢查裝置的構成的示意圖。 圖2是表示良品的HUE值分佈輪廓的例的示意圖。 圖3是表示次品的HUE值分佈輪廓的例的示意圖。 圖4是表示次品的HUE值分佈輪廓的另一例的示意圖。 圖5是表示本發明的第2實施形態的檢查裝置的構成的示意圖。 圖6是表示檢查圖像的例的示意圖。 圖7是表示圖6所示的檢查圖像的HUE值分佈輪廓的示意圖。 圖8是表示對檢查圖像進行分割的例的示意圖。 圖9是表示不包含異常區域的分割區域的HUE值分佈輪廓的示意圖。 圖10是表示包含異常區域的分割區域的HUE值分佈輪廓的示意圖。FIG. 1 is a schematic view showing a configuration of an inspection apparatus according to a first embodiment of the present invention. FIG. 2 is a schematic diagram showing an example of a HUE value distribution profile of a good product. Fig. 3 is a schematic diagram showing an example of a HUE value distribution profile of a defective product. 4 is a schematic view showing another example of a HUE value distribution profile of a defective product. Fig. 5 is a schematic diagram showing the configuration of an inspection apparatus according to a second embodiment of the present invention. Fig. 6 is a schematic diagram showing an example of an inspection image. Fig. 7 is a schematic diagram showing an HUE value distribution profile of the inspection image shown in Fig. 6. FIG. 8 is a schematic diagram showing an example of dividing an inspection image. FIG. 9 is a schematic diagram showing an HUE value distribution profile of a divided region that does not include an abnormal region. FIG. 10 is a schematic diagram showing an HUE value distribution profile of a divided region including an abnormal region.

1‧‧‧檢查裝置 1‧‧‧Checking device

10‧‧‧照明裝置 10‧‧‧Lighting device

20‧‧‧圖像獲取裝置 20‧‧‧Image acquisition device

30‧‧‧判定裝置 30‧‧‧Determining device

31‧‧‧輪廓製作部 31‧‧‧Contour Production Department

32‧‧‧判定部 32‧‧‧Decision Department

100‧‧‧工件 100‧‧‧Workpiece

D‧‧‧圖像資料 D‧‧‧Image data

L‧‧‧檢查光 L‧‧‧Check light

Claims (6)

一種檢查裝置,其特徵在於包括:圖像獲取裝置,獲取經成膜處理的工件的檢查圖像;以及判定裝置,對所述檢查圖像的各點算出色相值,將所述色相值的度數作圖而作成色相值分佈輪廓,在所述色相值分佈輪廓的度數波峰的寬度在規定值的範圍內,且度數波峰數為一個的情況下判定所述工件為良品,在所述度數波峰數為多個的情況下判定所述工件為不良。 An inspection apparatus, comprising: an image acquisition device that acquires an inspection image of a film-formed workpiece; and a determination device that calculates a hue value for each point of the inspection image, and calculates a degree of the hue value Performing a chromatographic value distribution profile, and determining that the workpiece is a good product, and the number of peaks in the degree is determined when the width of the peak of the color value distribution profile is within a predetermined value range and the number of peaks is one. In the case of a plurality of cases, it is determined that the workpiece is defective. 如申請專利範圍第1項所述的檢查裝置,其中所述判定裝置根據所述檢查圖像對多種顏色分別製作所述色相值分佈輪廓。 The inspection apparatus according to claim 1, wherein the determination means creates the hue value distribution profile for each of the plurality of colors based on the inspection image. 如申請專利範圍第1項或第2項所述的檢查裝置,其中所述判定裝置將所述檢查圖像分割為多個分割區域,針對所述分割區域的每一個製作所述色相值分佈輪廓,在所有的所述分割區域中所述色相值分佈輪廓的度數波峰數為一個的情況下,判定所述工件為良品,在至少一個所述分割區域中所述色相值分佈輪廓的度數波峰數為多個的情況下,判定所述工件為不良。 The inspection apparatus according to claim 1 or 2, wherein the determination means divides the inspection image into a plurality of divided regions, and the hue value distribution contour is created for each of the divided regions And determining, in a case where the number of peaks of the hue value distribution profile is one in all the divided regions, determining that the workpiece is a good product, and the number of peaks of the hue value distribution profile in at least one of the divided regions In the case of a plurality of cases, it is determined that the workpiece is defective. 一種檢查方法,其特徵在於包括下述步驟:獲取經成膜處理的工件的檢查圖像;對所述檢查圖像的各點算出色相值,將所述色相值的度數作圖而作成色相值分佈輪廓;以及在所述色相值分佈輪廓的度數波峰的寬度在規定值的範圍 內,且度數波峰數為一個的情況下,判定所述工件為良品,在所述度數波峰數為多個的情況下判定所述工件為不良。 An inspection method comprising the steps of: acquiring an inspection image of a film-formed workpiece; calculating a hue value for each point of the inspection image, and plotting the degree of the hue value to form a hue value a distribution profile; and a width of the peak of the degree of the distribution of the hue value in a range of a prescribed value When the number of peaks is one, it is determined that the workpiece is a good product, and when the number of peaks is plural, it is determined that the workpiece is defective. 如申請專利範圍第4項所述的檢查方法,其中根據所述檢查圖像對多種顏色分別製作所述色相值分佈輪廓。 The inspection method according to claim 4, wherein the hue value distribution profile is separately produced for a plurality of colors based on the inspection image. 如申請專利範圍第4項或第5項所述的檢查方法,其進而包括將所述檢查圖像分割為多個分割區域的步驟,針對所述分割區域的每一個製作所述色相值分佈輪廓,在所有的所述分割區域中所述色相值分佈輪廓的度數波峰數為一個的情況下,判定所述工件為良品,在至少一個所述分割區域中所述色相值分佈輪廓的度數波峰數為多個的情況下,判定所述工件為不良。 The inspection method of claim 4 or 5, further comprising the step of dividing the inspection image into a plurality of divided regions, wherein the hue value distribution contour is created for each of the divided regions And determining, in a case where the number of peaks of the hue value distribution profile is one in all the divided regions, determining that the workpiece is a good product, and the number of peaks of the hue value distribution profile in at least one of the divided regions In the case of a plurality of cases, it is determined that the workpiece is defective.
TW105108180A 2015-05-20 2016-03-17 Check the device and check the method TWI583942B (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2015102588A JP6319184B2 (en) 2015-05-20 2015-05-20 Inspection apparatus and inspection method

Publications (2)

Publication Number Publication Date
TW201641932A TW201641932A (en) 2016-12-01
TWI583942B true TWI583942B (en) 2017-05-21

Family

ID=57580835

Family Applications (1)

Application Number Title Priority Date Filing Date
TW105108180A TWI583942B (en) 2015-05-20 2016-03-17 Check the device and check the method

Country Status (2)

Country Link
JP (1) JP6319184B2 (en)
TW (1) TWI583942B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111413352A (en) * 2020-05-25 2020-07-14 广西我的科技有限公司 Artificial board surface defect detection device and method

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007102270A (en) * 2005-09-30 2007-04-19 Omron Corp Image processing apparatus
TW200741194A (en) * 2006-03-10 2007-11-01 Omron Tateisi Electronics Co Apparatus and method for inspecting defects
JP2009080004A (en) * 2007-09-26 2009-04-16 Mitsubishi Electric Engineering Co Ltd Inspection device
US20120326037A1 (en) * 2010-02-26 2012-12-27 Aisin Seiki Kabushiki Kaisha Coating film inspection apparatus and inspection method

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09203664A (en) * 1996-01-25 1997-08-05 C G A Kk Hue inspecting apparatus
JP3181543B2 (en) * 1997-10-31 2001-07-03 東京電力株式会社 Deterioration / corrosion detection method for surface-treated steel
EP1096249B1 (en) * 1999-10-26 2013-05-01 Hitachi-GE Nuclear Energy, Ltd. Nondestructive flaw inspection method and apparatus
JP4250931B2 (en) * 2002-08-30 2009-04-08 日本電気株式会社 Appearance inspection apparatus and appearance inspection method
JP2004144545A (en) * 2002-10-23 2004-05-20 Sumitomo Chem Co Ltd Inspection method of color irregularity
JP5006147B2 (en) * 2007-09-21 2012-08-22 株式会社名南製作所 Wood inspection method, apparatus and program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007102270A (en) * 2005-09-30 2007-04-19 Omron Corp Image processing apparatus
TW200741194A (en) * 2006-03-10 2007-11-01 Omron Tateisi Electronics Co Apparatus and method for inspecting defects
JP2009080004A (en) * 2007-09-26 2009-04-16 Mitsubishi Electric Engineering Co Ltd Inspection device
US20120326037A1 (en) * 2010-02-26 2012-12-27 Aisin Seiki Kabushiki Kaisha Coating film inspection apparatus and inspection method

Also Published As

Publication number Publication date
TW201641932A (en) 2016-12-01
JP2016217865A (en) 2016-12-22
JP6319184B2 (en) 2018-05-09

Similar Documents

Publication Publication Date Title
CN106796179B (en) Inspection apparatus and inspection method
CN109923402B (en) Ceramic body defect inspection device and defect inspection method
US10890537B2 (en) Appearance inspection device, lighting device, and imaging lighting device
US10060859B2 (en) Method of inspecting foreign substance on substrate
JP5354335B2 (en) Laser processing quality determination method and apparatus
TWI620929B (en) Inspecting device and method for inspecting inspection target
JP2015148447A (en) Automatic visual inspection apparatus
US11680909B2 (en) Automated inspection of foreign materials, cracks and other surface anomalies
TWI588468B (en) Method for searching for area of ​​interest of electronic components and method and device for detecting defect of electronic components using the same
JP2015068668A (en) Appearance inspection device
JP6474756B2 (en) Defect inspection method and apparatus
RU2696346C2 (en) Tire production control device on production line
KR20110089486A (en) Mounting boards inspection apparatus and method thereof
JP6691541B2 (en) Method and apparatus for checking tires on a production line
JP2007240431A (en) Defect inspection device and defect inspection method
TWI583942B (en) Check the device and check the method
JP2008064715A (en) Defect inspection device and defect inspection method
JP6526514B2 (en) Inspection apparatus, method and program
US9230337B2 (en) Analysis of the digital image of the internal surface of a tyre and processing of false measurement points
JP6248819B2 (en) Inspection apparatus and inspection method
JP2020101486A (en) Inspection device
EP3516683B1 (en) Method for defocus detection
KR20150137474A (en) Vision inspecting method using color image separation
US20220178840A1 (en) Method for checking compliance of a mechanical part of a vehicle
JP2010175558A (en) Inspection device

Legal Events

Date Code Title Description
MM4A Annulment or lapse of patent due to non-payment of fees