TWI722861B - Classification method and a classification system - Google Patents
Classification method and a classification system Download PDFInfo
- Publication number
- TWI722861B TWI722861B TW109111742A TW109111742A TWI722861B TW I722861 B TWI722861 B TW I722861B TW 109111742 A TW109111742 A TW 109111742A TW 109111742 A TW109111742 A TW 109111742A TW I722861 B TWI722861 B TW I722861B
- Authority
- TW
- Taiwan
- Prior art keywords
- image
- tested
- classification
- machine learning
- training
- Prior art date
Links
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
Description
本發明涉及一種分類方法及分類系統,特別是一種利用自動光學檢測裝置及機器學習模型進行待測物分類的分類方法及分類系統。The invention relates to a classification method and a classification system, in particular to a classification method and a classification system for classifying an object to be tested by using an automatic optical detection device and a machine learning model.
自動光學檢測裝置(Automated Optical Inspection, AOI)已經普遍地被應用於各種檢測場合中。但自動光學檢測裝置在實際應用中,常會發生誤判的問題,為此造成相關業者的困擾。Automated Optical Inspection (AOI) has been widely used in various inspection occasions. However, in actual applications of automatic optical inspection devices, misjudgments often occur, which causes troubles for related industries.
本發明公開一種分類方法分類系統,主要用以改善利用自動光學檢測裝置(AOI)對各式待測物進行檢測時,自動光學檢測裝置(AOI)容易出現誤判的問題。The invention discloses a classification method classification system, which is mainly used to improve the problem that the automatic optical detection device (AOI) is prone to misjudgment when various types of test objects are detected by the automatic optical detection device (AOI).
本發明的其中一實施例公開一種分類方法,其適用於一分類系統,分類系統包含一自動光學檢測裝置、一處理裝置及一分類裝置,分類系統能執行分類方法以將一待測物分類至一良品區或一不良品區,分類方法包含:一自動光學檢測裝置分類步驟及一機器學習分類步驟。自動光學檢測裝置分類步驟包含:一影像擷取步驟及一影像分類步驟。影像擷取步驟:利用自動光學檢測裝置,對待測物進行一影像擷取,以產生一待測影像;影像分類步驟:利用自動光學檢測裝置或處理裝置分析待測影像,以判斷待測影像屬於一良品類別及N個預設瑕疵類別中的哪一類;其中,N為大於1的正整數;若判斷待測影像屬於良品類別,則利用分類裝置將待測物移載至良品區;若判斷待測影像屬於N個預設瑕疵類別中的其中一類,則執行一機器學習分類步驟;處理裝置儲存有對應於N個預設瑕疵類別的N個機器學習模型,N個機器學習模型是分別利用不完全相同的一訓練圖集(training set)進行模型訓練,且各個訓練圖檔包含對應於N個預設瑕疵類別中的其中一類的多個訓練圖檔及至少一個良品圖檔;機器學習分類步驟包含:一載入步驟:依據影像分類步驟的分類結果,將待測影像載入至相對應的其中一個機器學習模型中;一判斷步驟:利用載入有待測影像的機器學習模型,判斷待測影像為一覆判良品或一不良品;若利用載入有待測影像的機器學習模型判斷待測影像為覆判良品,則利用分類裝置將待測物移載至良品區;若利用載入有待測影像的機器學習模型判斷待測影像為不良品,則利用分類裝置將待測物移載至不良品區。One of the embodiments of the present invention discloses a classification method, which is suitable for a classification system. The classification system includes an automatic optical inspection device, a processing device and a classification device. The classification system can execute the classification method to classify a test object into A good product area or a defective product area, the classification method includes: an automatic optical inspection device classification step and a machine learning classification step. The classification step of the automatic optical inspection device includes: an image capturing step and an image classification step. Image capture step: use an automatic optical inspection device to capture an image of the object to be tested to generate an image to be tested; image classification step: use an automatic optical inspection device or processing device to analyze the image to be tested to determine whether the image to be tested belongs to A good product category and which of the N preset defect categories; where N is a positive integer greater than 1; if it is determined that the image to be tested belongs to the good product category, the classification device is used to move the object to be tested to the good product area; if judged If the image to be tested belongs to one of the N preset defect categories, a machine learning classification step is performed; the processing device stores N machine learning models corresponding to the N preset defect categories, and the N machine learning models are used separately A training set that is not exactly the same for model training, and each training image file includes multiple training images and at least one good product image file corresponding to one of the N preset defect categories; machine learning classification The steps include: a loading step: load the image to be tested into one of the corresponding machine learning models according to the classification result of the image classification step; a judging step: use the machine learning model loaded with the image to be tested to determine The image to be tested is a good product or a defective product; if the machine learning model loaded with the image to be tested is used to determine that the image to be tested is a good product, the classification device is used to transfer the object to be tested to the good product area; if used The machine learning model loaded with the image to be tested determines that the image to be tested is a defective product, and the classification device is used to transfer the object to be tested to the defective product area.
本發明的其中一實施例公開一種分類系統,其包含:一自動光學檢測裝置、一處理裝置及一分類裝置,分類系統能執行一分類方法以將一待測物分類至一良品區或一不良品區,分類方法包含:一自動光學檢測裝置分類步驟及一機器學習分類步驟。自動光學檢測裝置分類步驟包含:一影像擷取步驟:利用自動光學檢測裝置,對待測物進行一影像擷取,以產生一待測影像;一影像分類步驟:利用自動光學檢測裝置或處理裝置分析待測影像,以判斷待測影像屬於一良品類別及N個預設瑕疵類別中的哪一類;其中,N為大於1的正整數;若判斷待測影像屬於良品類別,則利用分類裝置將待測物移載至良品區;若判斷待測影像屬於N個預設瑕疵類別中的其中一類,則執行一機器學習分類步驟;處理裝置儲存有對應於N個預設瑕疵類別的N個機器學習模型,N個機器學習模型是分別利用不完全相同的一訓練圖集(training set)進行模型訓練,且各個訓練圖檔包含對應於N個預設瑕疵類別中的其中一類的多個訓練圖檔及至少一個良品圖檔;機器學習分類步驟包含:一載入步驟:依據影像分類步驟的分類結果,將待測影像載入至相對應的其中一個機器學習模型中;一判斷步驟:利用載入有待測影像的機器學習模型,判斷待測影像為一覆判良品或一不良品;若利用載入有待測影像的機器學習模型判斷待測影像為覆判良品,則利用分類裝置將待測物移載至良品區;若利用載入有待測影像的機器學習模型判斷待測影像為不良品,則利用分類裝置將待測物移載至不良品區。One of the embodiments of the present invention discloses a classification system, which includes: an automatic optical inspection device, a processing device, and a classification device. The classification system can execute a classification method to classify a test object into a good product area or a non-defective area. In the good product area, the classification method includes: an automatic optical inspection device classification step and a machine learning classification step. The automatic optical inspection device classification step includes: an image capture step: use the automatic optical inspection device to capture an image of the object to be tested to generate an image to be tested; an image classification step: use the automatic optical inspection device or processing device to analyze The image to be tested is used to determine which of a good product category and N preset defect categories the image to be tested belongs to; where N is a positive integer greater than 1; if it is determined that the image to be tested belongs to a good product category, the classification device will be used to The test object is transferred to the good product area; if it is determined that the image to be tested belongs to one of the N preset defect categories, a machine learning classification step is performed; the processing device stores N machine learnings corresponding to the N preset defect categories Model, N machine learning models use a different training set (training set) for model training, and each training image file contains multiple training image files corresponding to one of the N preset defect categories And at least one good product image file; the machine learning classification step includes: a loading step: according to the classification result of the image classification step, the image to be tested is loaded into one of the corresponding machine learning models; a judging step: using loading There is a machine learning model for the image to be tested to determine whether the image to be tested is a good product or a defective product; if the machine learning model loaded with the image to be tested is used to determine that the image to be tested is a good product, the classification device is used to The object to be tested is transferred to the good product area; if the machine learning model loaded with the image to be tested is used to determine that the image to be tested is defective, the classification device is used to transfer the object to be tested to the defective product area.
綜上所述,本發明的分類方法及分類系統通過自動光學檢測裝置分類步驟及機器學習分類步驟等設計,以及使被判定屬於不同預設瑕疵類別的待測影像,利用相對應的機器學習模型進行再次確認等設計,可以大幅改善習知僅利用自動光學檢測裝置進行待測物分類時,自動光學檢測裝置容易發生誤判的問題。In summary, the classification method and classification system of the present invention are designed through automatic optical inspection device classification steps and machine learning classification steps, and make the images to be tested that are judged to belong to different preset defect categories, using corresponding machine learning models Designs such as reconfirmation can greatly improve the problem that the automatic optical inspection device is prone to misjudgment when the conventional automatic optical inspection device is used to classify the object to be tested.
為能更進一步瞭解本發明的特徵及技術內容,請參閱以下有關本發明的詳細說明與附圖,但是此等說明與附圖僅用來說明本發明,而非對本發明的保護範圍作任何的限制。In order to further understand the features and technical content of the present invention, please refer to the following detailed descriptions and drawings about the present invention, but these descriptions and drawings are only used to illustrate the present invention, and do not make any claims about the protection scope of the present invention. limit.
於以下說明中,如有指出請參閱特定圖式或是如特定圖式所示,其僅是用以強調於後續說明中,所述及的相關內容大部份出現於該特定圖式中,但不限制該後續說明中僅可參考所述特定圖式。In the following description, if it is pointed out, please refer to the specific drawing or as shown in the specific drawing, it is only used to emphasize that in the subsequent description, most of the related content appears in the specific drawing. However, it is not limited that only the specific drawings can be referred to in this subsequent description.
請參閱圖1,其顯示為本發明的分類系統的方塊示意圖。本發明的分類系統100包含:一自動光學檢測裝置1、一處理裝置2、一儲存裝置3及一分類裝置4。自動光學檢測裝置(Automated Optical Inspection, AOI)包含一影像擷取器11,影像擷取器11用以對一待測物進行影像擷取,以產生一待測影像111。處理裝置2電性連接自動光學檢測裝置1,而處理裝置2能接收自動光學檢測裝置1所傳遞的所述待測影像111。Please refer to FIG. 1, which shows a block diagram of the classification system of the present invention. The
處理裝置2例如可以是各式電腦、伺服器等設備,而處理裝置2例如可以是包含有中央處理器(Central Processing Unit, CPU)或繪圖處理器(graphics processing unit)。儲存裝置3可以是各式記憶體、硬碟等,且儲存裝置3可以是與處理裝置2整合為一獨立的設備(例如伺服器設備、工業電腦設備等),於此不加以限制。分類裝置4電性連接處理裝置2,分類裝置4能依據處理裝置2所傳遞的指令,而將通過自動光學檢測裝置1的待測物,移載至一良品區或一不良品區。在實際應用中,分類裝置4具體所包含的硬體構件,可以是依據待測物的種類、外型、尺寸等變化,於此不加以限制。The
本發明的分類系統100用以執行本發明的一分類方法,以將一待測物分類至所述良品區或所述不良品區。本發明的分類方法包含:一自動光學檢測裝置分類步驟S1及一機器學習分類步驟S2,分類系統100是依序執行所述自動光學檢測裝置分類步驟S1及所述機器學習分類步驟S2,以決定將所述待測物分類至所述良品區或所述不良品區。The
請一併參閱圖1及圖2,圖2顯示為本發明的分類方法的自動光學檢測裝置分類步驟的流程示意圖,所述自動光學檢測裝置分類步驟S1包含:Please refer to FIG. 1 and FIG. 2 together. FIG. 2 is a schematic flowchart of the automatic optical inspection device classification step of the classification method of the present invention. The automatic optical inspection device classification step S1 includes:
一影像擷取步驟S11:利用自動光學檢測裝置1,對待測物進行一影像擷取,以產生一待測影像111;An image capturing step S11: using the automatic
一影像分類步驟S12:利用自動光學檢測裝置1或所述處理裝置2分析待測影像111,以判斷待測影像111屬於一良品類別及N個預設瑕疵類別中的哪一類;其中,N為大於1的正整數;An image classification step S12: use the automatic
若判斷待測影像111屬於良品類別,則利用分類裝置4將待測物移載至良品區;若判斷待測影像111屬於N個預設瑕疵類別中的其中一類,則執行所述機器學習分類步驟S2。換句話說,自動光學檢測裝置1及處理裝置2能分析待測影像,以判斷待測影像屬於N+1個類別(1個良品類別+N個預設瑕疵類別)中的哪一個。If it is determined that the image to be tested 111 belongs to the good product category, the
請參閱圖3,其顯示為本發明的分類方法的實際例子的示意圖,假設待測物為隱形眼鏡,且隱形眼鏡(待測物)於生產過程中容易出現3種瑕疵態樣,其分別為長條狀刮痕、破洞及不規則狀雜物,則相關人員可以是將此3種瑕疵態樣分別定義為一第一預設瑕疵類別、一第二預設瑕疵類別及一第三預設瑕疵類別。Please refer to FIG. 3, which shows a schematic diagram of a practical example of the classification method of the present invention. It is assumed that the object to be tested is a contact lens, and the contact lens (the object to be tested) is prone to 3 types of defects during the production process, which are respectively For long scratches, holes, and irregular debris, the relevant personnel can define the three types of defects as a first preset type, a second preset type, and a third preset. Set the defect category.
於上述影像分類步驟S12中,自動光學檢測裝置1(或處理裝置2)將判斷待測影像中,是否出現屬於第一預設瑕疵類別的瑕疵、屬於所述第二預設瑕疵類別的瑕疵或屬於所述第三預設瑕疵類別的瑕疵,亦即,自動光學檢測裝置1(或處理裝置2)將通過待測影像111,來判斷待測物是否出現長條狀刮痕、破洞或不規則狀雜物的其中一種瑕疵。In the above-mentioned image classification step S12, the automatic optical inspection device 1 (or the processing device 2) will determine whether there are defects belonging to the first preset defect category, defects belonging to the second preset defect category, or The defects belonging to the third preset defect category, that is, the automatic optical inspection device 1 (or the processing device 2) will use the
若是自動光學檢測裝置1(或處理裝置2)判斷所述待測影像111中未出現屬於第一預設瑕疵類別的瑕疵、屬於第二預設瑕疵類別的瑕疵或屬於第三預設瑕疵類別的瑕疵(即,自動光學檢測裝置1通過待測影像111,判斷待測物未出現長條狀刮痕、破洞或不規則狀雜物的瑕疵)時,自動光學檢測裝置1(或處理裝置2)將判定所述待測影像111屬於所述良品類別,而自動光學檢測裝置1(或處理裝置2)將據以控制分類裝置4將此待測物移載至良品區。If the automatic optical inspection device 1 (or the processing device 2) determines that there are no defects belonging to the first preset defect category, defects belonging to the second preset defect category, or defects belonging to the third preset defect category in the image to be tested 111 Defects (that is, when the automatic
相對地,若自動光學檢測裝置1(或處理裝置2)判斷所述待測影像111中出現屬於第一預設瑕疵類別的瑕疵、屬於第二預設瑕疵類別的瑕疵或屬於第三預設瑕疵類別的瑕疵(即,自動光學檢測裝置1通過待測影像111,判斷待測物出現長條狀刮痕、破洞或不規則狀雜物)時,自動光學檢測裝置1將判定所述待測影像屬於所述第一預設瑕疵類別、屬於第二預設瑕疵類別的瑕疵或屬於第三預設瑕疵類別的瑕疵,而後處理裝置2將執行所述機器學習分類步驟S2。In contrast, if the automatic optical inspection device 1 (or the processing device 2) determines that a defect belonging to the first preset defect category, a defect belonging to the second preset defect category, or a third preset defect appears in the image to be tested 111 Type of defects (ie, the automatic
在實際應用中,處理裝置2可以是儲存有對應於N個預設瑕疵類別的N筆預設灰階規則21。於所述影像分類步驟S12中,自動光學檢測裝置1將先計算待測影像111中的至少一區域內的所有像素的一灰階值,而後,自動光學檢測裝置將判斷至少一區域內的所有像素的灰階值是否符合N筆預設灰階規則22。若自動光學檢測裝置1判斷至少一區域內的所有像素的灰階值,符合其中一個預設灰階規則22,則判定待測影像111屬於預設灰階規則22所對應的預設瑕疵類別。其中,依據實際待測物的不同,自動光學檢測裝置1可以是計算待測影像中所有像素的灰階值,或者,僅計算待測影像中的一部分的區域內的所有像素的灰階值。In practical applications, the
承接上述例子,假設待測物為隱形眼鏡,所述分類系統100是要對隱形眼鏡的中心區域A(即隱形眼鏡實際用來矯正使用者視力的區域)進行檢測,以判斷隱形眼鏡於中心區域A的範圍內是否出現長條狀刮痕、破洞及不規則雜物的其中一種瑕疵;當然,瑕疵的類型不以此三種為限,其可依據需求加以變化,舉例來說,瑕疵還可以是包含有直線瑕疵、實心圓瑕疵、空心圓瑕疵等。假設隱形眼鏡的中心區域A未出現上述任何一種瑕疵時,待測影像111於所述中心區域A的所有像素的平均灰階值大致為200,而隱形眼鏡的中心區域A出現長條狀刮痕的瑕疵時,所述瑕疵所對應的所有像素的灰階值大致介於120~150,隱形眼鏡的中心區域A出現破洞時,所述瑕疵所對應的所有像素的灰階值大致介於70~80,而隱形眼鏡的中心區域A出現不規則狀雜物時,所述瑕疵所對應的所有像素的灰階值大致介於20~50。處理裝置2可以是具有三個預設灰階規則其分別為:規則1:中心區域A內的至少50~100個像素的灰階值介於120~150;規則2:中心區域A內的部分的像素的灰階值介於70~80;規則3:中心區域A內的部分像素的灰階值介於20~50。需說明的是,上述規則1、規則2及規則3是相關人員依據實際所欲分類的瑕疵種類進行設計,也就是說,在實際應用中,規則的數量及規則具體包含的內容,可以依據待測物的不同及瑕疵種類、外型等不同而設計。Continuing the above example, assuming that the test object is a contact lens, the
承上,在分類系統100執行所述影像分類步驟S12時,自動光學檢測裝置1將會計算待測影像111的中心區域A的所有像素的灰階值,並且判斷各個所述像素的灰階值是否介於120~150、70~80或20~50,若中心區域中超過50個像素的灰階值是介於120~150,則自動光學檢測裝置1將判定所述待測影像111屬於第一預設瑕疵類別;若中心區域中部分像素的灰階值是介於70~80,則自動光學檢測裝置1將判定所述待測影像111屬於第二預設瑕疵類別;若中心區域中部分像素的灰階值是介於20~50,則自動光學檢測裝置1將判定所述待測影像111屬於第三預設瑕疵類別。In summary, when the
在不同實施例中,所述待測影像可以是通過二值化(Binarization)處理後的影像,也就是說,自動光學檢測裝置1的影像擷取器11擷取待測物的影像後,將對該影像進行二值化處理,以產生所述待測影像,而所述待測影像中,瑕疵的部分將呈現為白色(灰階值255),其餘部分則呈現為黑色(灰階值0),或者是,瑕疵部分呈黑色,其餘部分呈白色。如圖4及圖5所示,其分別顯示為兩種不同的待測影像的示意圖。在實際應用中,相關人員可以是使自動光學檢測裝置1依據兩筆不同的預設灰階規則21,將圖4及圖5所示的兩張待測影像分類至兩個不同的預設瑕疵類別中。具體來說,自動光學檢測裝置1的其中一筆預設灰階規則21可以是:判斷待測影像中所有灰階值為255的像素所共同構成的圖樣的長度是否大於100像素,且圖樣的長寬比為100:1;另一筆預設灰階規則21則可以是:判斷待測影像中所有灰階值為255的像素所共同構成的圖樣的面積是否大於500像素,且圖樣的長寬比為1:1。In different embodiments, the image to be measured may be an image processed by binarization, that is, after the
另外,值得一提的是,自動光學檢測裝置1的影像擷取器11擷取待測物的彩色影像後,可以是先將該彩色影像依據三原色(RGB)分離出三張僅分別保留紅色、綠色及藍色的影像,而後再分別將三張影像進行二值化處理,最後利用預設灰階值規則,分別判斷三張影像中是否出現符合預設灰階規則的圖樣,若其中一張影像出現符合預設灰階值規則的圖樣,則判定該影像屬於對應於該預設灰階值規則的預設瑕疵類別。In addition, it is worth mentioning that after the
在不同的實施例中,自動光學檢測裝置1的影像擷取器11擷取待測物的彩色影像後,可以是先將彩色影像中R、G、B三個數值取平均值、最高值或最低值後,再將該彩色影像轉換為黑白影像,接著,在進行二值化處理,以產生出所述待測影像,最後,自動光學檢測裝置1則是判斷所述待測影像中是否存在符合預設灰階值規則的圖樣,以判定所述待測影像屬於哪一個預設瑕疵類別或為良品類別。In different embodiments, after the
請一併參閱圖1及圖6,圖6顯示為本發明的分類方法的機器學習分類步驟的流程示意圖。在實際應用中,處理裝置2儲存有N個預設灰階規則21及對應於N個預設瑕疵類別的N個機器學習模型22,而儲存裝置3則儲存有N個訓練圖集(training set)31,各個訓練圖集31包含至少一個良品圖檔311及對應於N個預設瑕疵類別中的其中一類的多個不良品訓練圖檔312。N個機器學習模型22是對應利用N個所述訓練圖集31進行模型訓練,亦即,N個機器學習模型22是分別利用不完全相同的一個所述訓練圖集31進行模型訓練。其中,在實際實施中,各個訓練圖集31可以是包含有相同的良品圖檔311,但不以此為限。Please refer to FIG. 1 and FIG. 6 together. FIG. 6 is a schematic flowchart of the machine learning classification step of the classification method of the present invention. In practical applications, the
當分類系統100執行完所述自動光學檢測裝置分類步驟S1後,且自動光學檢測裝置1判斷當前的待測影像屬於N個預設瑕疵類別中的其中一個時,分類系統100將執行所述機器學習分類步驟S2,所述機器學習分類步驟S2包含:After the
一載入步驟S21:依據影像分類步驟S1的分類結果,將待測影像111載入至相對應的其中一個機器學習模型22中;A loading step S21: load the image to be tested 111 into one of the corresponding
一判斷步驟S22:利用載入有待測影像111的機器學習模型22,判斷待測影像111為一覆判良品或一不良品;A judging step S22: using the
若利用載入有待測影像111的機器學習模型22判斷待測影像111為覆判良品,則利用分類裝置4將待測物移載至良品區;若利用載入有待測影像111的機器學習模型22判斷待測影像111為不良品,則利用分類裝置4將待測物移載至不良品區。特別說明的是,在具體的應用中,分類系統100可以是具有N個不良品區,N個不良品區對應於N個預設瑕疵類別,而當機器學習模型22判斷待測影像為不良品時,處理裝置2可以是控制分類裝置4將待測物,移載至相對應的不良品區中。If the
請一併參閱圖1、圖7及圖8,圖7顯示為本發明的分類系統的儲存裝置的其中一個實施例的方塊示意圖,圖8為本發明的分類方法的其中一個實際例子的說明示意圖。承接上述例子,在實際應用中,儲存裝置3中可以是儲存有三個機器學習模型及三個訓練圖集。三個機器學習模型分別定義為一第一機器學習模型22A、一第二機器學習模型22B及一第三機器學習模型22C。三個訓練圖集31分別定義為一第一訓練圖集31A、一第二訓練圖集31B及一第三訓練圖集31C。第一訓練圖集31A中例如可以是儲存有三張不良品訓練圖檔312A1、312A2、312A3,其中一張不良品訓練圖檔312A1的中心區域A的左下方出現一個的長條狀刮痕D11,且長條狀刮痕D11的長度方向是由左上向右下延伸;其中一張不良品訓練圖檔312A2的中心區域A的右上方出現一個長條狀刮痕D12,且長條狀刮痕D12的長度方向是由左上向右下延伸;其中一張不良品訓練圖檔312A3的中心區域A的中心位置出現一個長條狀刮痕D13,且長條狀刮痕D13的長度方向是由右上向左下延伸。Please refer to FIG. 1, FIG. 7 and FIG. 8. FIG. 7 is a block diagram of one embodiment of the storage device of the classification system of the present invention, and FIG. 8 is an explanatory diagram of an actual example of the classification method of the present invention . Following the above example, in practical applications, the
第二訓練圖集31B中例如可以是儲存有三張不良品訓練圖檔312B1、312B2、312B3,其中一張不良品訓練圖檔312B1的中心區域A的左下方出現一個的不規則狀破洞D21;其中一張不良品訓練圖檔312B2的中心區域A的右上方出現一個不規則狀破洞D22;其中一張不良品訓練圖檔312B3的中心區域A的中心位置出現一個不規則狀破洞D23;且三張不良品訓練圖檔312B1、312B2、312B3中出現的不規則狀破洞D21、D22、D23的外型及尺寸不完全相同。For example, the second training atlas 31B may store three defective training image files 312B1, 312B2, 312B3, and one of the defective training image files 312B1 has an irregular hole D21 in the lower left of the central area A; An irregular hole D22 appears in the upper right of the central area A of one of the defective product training files 312B2; an irregular hole D23 appears in the center of the central area A of one of the defective product training files 312B3; In addition, the irregular holes D21, D22, and D23 appearing in the three defective training image files 312B1, 312B2, and 312B3 have different shapes and sizes.
第三訓練圖集31C中例如可以是儲存有三張不良品訓練圖檔312C1、312C2、312C3,其中一張不良品訓練圖檔312C1的中心區域A的左下方出現一個的不規則狀雜物D31;其中一張不良品訓練圖檔312C2的中心區域A的右上方出現一個不規則狀雜物D32;其中一張不良品訓練圖檔312C3的中心區域A的中心位置出現一個不規則狀雜物D33;且三張不良品訓練圖檔312C1、312C2、312C3中出現的不規則狀雜物D31、D32、D33的外型及尺寸不完全相同。For example, the third training atlas 31C may store three defective training image files 312C1, 312C2, 312C3, and one of the defective training image files 312C1 has an irregular debris D31 at the lower left of the central area A; An irregular debris D32 appeared at the upper right of the central area A of one of the defective training image files 312C2; an irregular debris D33 appeared at the center of the central area A of one of the defective training image files 312C3; Moreover, the appearance and size of the irregular debris D31, D32, and D33 appearing in the three defective product training image files 312C1, 312C2, and 312C3 are not exactly the same.
假設自動光學檢測裝置1對待測物進行影像擷取後,所產生的待測影像111如圖8所示,則於上述自動光學檢測裝置分類步驟S1中,所述待測影像111將被判定屬於前述第一預設瑕疵類別,而於上述機器學習分類步驟S2中,處理裝置2將會把所述待測影像111輸入至第一機器學習模型22A中,而後,處理裝置2將可以利用第一機器學習模型22A判斷出所述待測影像111具有所述第一瑕疵類別的瑕疵,而處理裝置2將可據以判定所述待測影像111屬於不良品,最後,處理裝置2將可以控制分類裝置4將待測物移載至不良品區。Assuming that after the automatic
依上所述,由於第一訓練圖檔集31A中所包含的各個不良品訓練圖檔312僅具有第一瑕疵類別的瑕疵,而第一訓練圖檔集31A中的各個不良品訓練圖集31並不具有其他瑕疵類別的瑕疵,因此,當如圖5所示的從未出現於第一訓練圖檔集31A中的待測影像111,被輸入至第一機器學習模型22A中時,第一機器學習模型22A能夠精確地判斷出,圖5的待測影像111出現有屬於第一瑕疵類別的瑕疵。As described above, since each defective product
如上述說明,相反來說,假設單一個機器學習模型的訓練圖集中,包含有多種不同瑕疵類型的圖檔,則所述單一個機器學習模型在輸入一個從未出現於訓練圖集中的圖檔時,機器學習模型將容易出現誤判所述圖檔所具有的瑕疵所屬的類型的問題。另外,申請人在實際的實驗中,發現使單一個機器學習模型僅針對單一種瑕疵類型進行訓練,所述機器學習模型到達預定的判斷準確率所需的訓練時間,將明顯低於單一個機器學習模組同時對多種瑕疵類型進行訓練,所述機器學習模型判斷各種瑕疵類型到達相同的判斷準確率所需的訓練時間。As explained above, on the contrary, assuming that the training atlas of a single machine learning model contains multiple types of images with different defect types, then the single machine learning model inputs an image that never appears in the training atlas At this time, the machine learning model will be prone to misjudge the type of the defect of the image file. In addition, in actual experiments, the applicant found that a single machine learning model is only trained for a single defect type. The training time required for the machine learning model to reach a predetermined judgment accuracy rate will be significantly lower than that of a single machine. The learning module trains multiple defect types at the same time, and the machine learning model judges the training time required for the various defect types to reach the same judgment accuracy rate.
綜上所述,本發明的分類方法及分類系統,先利用自動光學檢測裝置1對待測物進行影像擷取以產生待測影像,並利用自動光學檢測裝置1對待測影像進行分析,以判斷待測影像中是否出現有符合N個預設瑕疵類別中的任一個瑕疵,若出現N個預設瑕疵類別中的其中一個瑕疵時,則再利用僅對特定類別瑕疵進行訓練的機器學習模型,來對待測影像進行再一次的判別,藉此,再次確認待測影像中是否出現特定類別的瑕疵,本發明的分類方法及分類系統,透過自動光學檢測裝置及機器學習模型的相互配合,不但可以準確地判斷出待測物是否出現瑕疵外,還可以準確地判斷出待測物是否出現預設類別的瑕疵。In summary, the classification method and classification system of the present invention first use the automatic
需說明的是,對於生產廠商而言,對其所生產出的產品進行瑕疵檢測是一種常規的流程,而對生產廠商而言更重要的是判斷出待測物出現何種瑕疵,如此生產廠商才得以依據瑕疵種類,來對生產流程進行調校,是以,本發明的分類方法及分類系統通過自動光學檢測裝置及N個機器學習模型等設計,不但可以準確地判斷出待測物是否具有瑕疵外,還可以準確地判斷出瑕疵屬於哪一種類型。It should be noted that for manufacturers, it is a routine process to detect defects in their products, and it is more important for manufacturers to determine what defects are present in the object to be tested, so the manufacturer It is possible to adjust the production process according to the types of defects. Therefore, the classification method and classification system of the present invention are designed through automatic optical detection devices and N machine learning models, etc., not only can accurately determine whether the object to be tested has In addition to flaws, it is also possible to accurately determine which type of flaw belongs to.
請一併參閱圖1及圖9,其顯示為發明的分類方法的機器學習分類步驟的另一實施例的流程示意圖。本實施例與前述實施例最大不同之處在於:於所述判斷步驟S22中,是利用機器學習模型22判斷待測影像為覆判良品、不良品或一未知品。Please refer to FIG. 1 and FIG. 9 together, which show a schematic flowchart of another embodiment of the machine learning classification step of the inventive classification method. The biggest difference between this embodiment and the previous embodiments is that in the determining step S22, the
若機器學習模型22判斷待測影像111為未知品,則利用分類裝置4將待測物移載至一未知品區,且處理裝置2將發出一提示資訊23,以提醒覆判人員對設置於未知品區的待測物進行人工查驗。在實際應用中,提示資訊22例如可以是一控制訊號,而分類方法的相關發光裝置、發聲裝置,接收所述控制訊號(提示資訊22)後,將發出特定的光束、聲音;當然,提示資訊22也可以是被顯示於一顯示裝置中。If the
如圖1所示,分類系統100還可以包含有一輸入裝置5,輸入裝置5鄰近於未知品區設置,輸入裝置5用以提供使用者操作,以對應產生一判定結果資訊51。若設置於未知區的待測物經人工查驗,且輸入裝置5被操作而產生所述判定結果資訊51,而處理裝置2依據判定結果資訊51判定待測物屬於N個預設瑕疵類別中的其中一類,則處理裝置2將待測影像111儲存於相對應的預設瑕疵類別對應的機器學習模型22的訓練圖集31中,且處理裝置2將依據所述判定結果資訊,控制分類裝置4將待測物移載至「良品區」或「不良品區」。在實際應用中,分類系統100於未知品區的周圍還可以是設置有一顯示裝置,顯示裝置能顯示待測影像,而使用者即可通過顯示裝置觀看設置於未知品區的待測物所對應的待測影像,並據以判斷待測影像中的瑕疵是屬於哪一種類型,而後,使用者可以通過操作輸入裝置5(例如各式觸控螢幕、輸入按鍵等)來產生所述判定結果資訊51。As shown in FIG. 1, the
請參閱圖10,其顯示為本發明的分類方法的實際例子的示意圖,承接前述的本發明的分類方法應用於隱形眼鏡的分類的例子,在實際應用中,假設待測影像111中實際存在的瑕疵為「破洞」,但自動光學檢測裝置1錯誤地判斷待測影像111中具有「長條刮痕」,而待測影像111被對應輸入至第一機器學習模型22A中,此時,第一機器學習模型22A將為把待測影像111判定為「未知品」。在具體實施中,各個機器學習模型可以是利用邏輯回歸的Sigmoid函數,對應計算出待測影像為覆判良品的機率及待測影像為不良品的機率,假設機器學習模型所計算出的待測影像為覆判良品的機率及待測影像為不良品的機率都不超過預定的閥值(例如不超過0.8),則機器學習模型將會把所述待測影像判定為「未知品」。Please refer to FIG. 10, which shows a schematic diagram of an actual example of the classification method of the present invention, which inherits the foregoing example of the classification method of the present invention applied to the classification of contact lenses. The defect is a "hole", but the automatic
依上所述,通過使機器學習模型增加「未知品」的判斷機制的設計,將可以讓使用者更清楚地瞭解自動光學檢測裝置1在面對何種待測影像時可能發生哪一種誤判,藉此,相關人員可以對應修改自動光學檢測裝置1判斷待測影像的相關規則。As mentioned above, by adding the "unknown" judging mechanism to the machine learning model, the user will be able to understand more clearly what kind of misjudgment may occur when the automatic
請一併參閱圖11及圖12,圖11及圖12分別顯示為通過二值化處理的待測影像。如圖11所示,在實際應用中,若是通過二值化處理後的待測影像中,出現不連續的類似於直線狀瑕疵的圖樣,則自動光學檢測裝置1將難以正確地判斷出所述待測影像中所出現的瑕疵屬於哪一種預設瑕疵類別,此時若是自動光學檢測裝置1將圖11的待測影像分類至直線狀瑕疵的預設瑕疵類別,則所述待測影像通過相對應的機器學習模組的判斷後,將可被正確地判斷出待測影像是否屬於直線狀瑕疵的預設瑕疵類別。另外,若是分類方法於所述判斷步驟S22中,是利用機器學習模型22判斷待測影像為覆判良品、不良品或未知品,則自動光學檢測裝置1也可以是將出現不連續的類似於直線狀瑕疵的圖樣的待測影像分類為未知品。Please refer to FIG. 11 and FIG. 12 together. FIG. 11 and FIG. 12 respectively show the image to be tested through the binarization process. As shown in Figure 11, in practical applications, if a discontinuous pattern similar to a linear defect appears in the image to be tested after the binarization process, it will be difficult for the automatic
如圖12所示,在實際應用中,若是待測影像中,除了出現直線狀的瑕疵外還出現灰色條紋(雜訊),則自動光學檢測裝置1將難以正確地判斷出所述待測影像中所出現的瑕疵屬於哪一種預設瑕疵類別,此時自動光學檢測裝置1無論是將所述待測影像分類為直線狀瑕疵的預設瑕疵類別,或是,將所述待測影像分類為未知品類別,所述待測影像內所包含的瑕疵,都可以在後續的過程中,被正確地判斷出來。As shown in FIG. 12, in practical applications, if the image to be tested has gray stripes (noise) in addition to linear flaws, it will be difficult for the automatic
依上所述,本發明的分類方法及分類系統,即使在待測影像中出現不連續的瑕疵圖像或是出現干擾圖樣,仍可以通過後續的機器學習模型或是將待測影像判斷為未知品等步驟,而正確地對待測物進行分類。As mentioned above, the classification method and classification system of the present invention, even if discontinuous flaw images or interference patterns appear in the image to be tested, the subsequent machine learning model or the image to be tested can still be judged as unknown. And other steps, and correctly classify the object to be tested.
在上述各實施例中,本發明的分類方法還可以包含有一訓練集擴充步驟:利用處理裝置2將被機器學習模型22判斷為覆判良品或不良品的待測影像111,依據影像分類步驟的分類結果,存入相對應的其中一個機器學習模型22所對應的訓練圖集31中。而後,處理裝置2可以是在訓練圖集31所包含的圖檔增加至一預定數量時,使各個機器學習模型利用擴充後的訓練圖集31再次進行模型訓練,如此,將可提升各機器學習模型的判斷準確度。In the above-mentioned embodiments, the classification method of the present invention may further include a training set expansion step: using the
在不同的實施例中,於所述訓練集擴充步驟中,處理裝置2也可以是將被機器學習模型22判斷為覆判良品或不良品的待測影像111,依據影像分類步驟的分類結果,隨機地存入相對應的其中一個機器學習模型22所對應的訓練圖集31中或相對應的其中一個機器學習模型22所對應的一驗證圖集(Validation Dataset)中,所述驗證圖集中儲存有多張已經被確認(例如是已經被標籤化)的良品圖檔、不良品圖檔。更具體來說,各個機器學習模型在進行模型訓練過程中,是利用相對應的訓練圖集進行模型訓練,而利用相對應的驗證圖集來進行訓練結果驗證。透過使被機器學習模型判斷為覆判良品或不良品的待測影像「隨機地」存入相對應的訓練圖集或是驗證圖集中的設計,將可以避免於訓練圖集中新增過多的待測影像,而使得機器學習模型再次訓練後,發生過度學習(Overfitting)的問題。In a different embodiment, in the training set expansion step, the
上述本發明的分類方法及分類系統中的N個機器學習模型,可以是利用卷積神經網路(Convolutional Neural Network,CNN)模型,配合N個訓練圖集及N個驗證圖集,進行訓練來生成,但各個機器學習模型21不侷限於利用卷積神經網路模型生成。在實際實施中,處理裝置2或是儲存裝置3可以是預先儲存有三個不同深度的卷積神經網路模型,在對N個機器學習模型21進行模型訓練時,處理裝置2例如可以是先依據N個預設瑕疵類別所對應的訓練圖集,判斷N個訓練圖中所存在的瑕疵的難易度(例如是利用瑕疵面積標準差、瑕疵灰階值標準差、瑕疵長寬比等),而後,處理裝置2將依據判斷結果於三個不同深度的卷積神經網路模型中擇一作為生成N個機器學習模型21的基本模型。The N machine learning models in the above-mentioned classification method and classification system of the present invention can be trained by using a Convolutional Neural Network (CNN) model with N training atlases and N verification atlases. However, each
若是處理裝置2選擇其中一個深度相對較低的卷積神經網路模型配合N個訓練圖集及N個驗證圖集,生成N個機器學習模型21,且超過預定數量的機器學習模型的準確度(Accuracy)、精確率(Precision)或召回率(Recall)未達預定的標準時,處理裝置2則可以是改用深度相對較深的卷積神經網路模型,再重新配合N個訓練圖集及N個驗證圖集,以重新生成新的N個機器學習模型。在實際應用中,處理裝置2可以是反覆地更換卷積神經網路模型,直到生成N個符合預定準確度的機器學習模型21。If the
補充說明的是,上述所指不同深度的卷積神經網路模型,是表示三個卷積神經網路模型具有不同數量的卷積層(Convolution Layer)、池化層(Pooling Layer)及全連接層(Fully connection Layer),舉例來說,深度較低的卷積神經網路模型可以是依據具有第一卷積層、第一池化層、第二卷積層、第二池化層及全連接層,深度較深的卷積神經網路模型可以是依據具有第一卷積層、第一池化層、第二卷積層、第二池化層、第三卷積層、第三池化層、第一全連接層及第二全連接層。In addition, the above-mentioned convolutional neural network models of different depths mean that the three convolutional neural network models have different numbers of convolution layers (Convolution Layer), pooling layer (Pooling Layer), and fully connected layer (Fully connection Layer), for example, a low-depth convolutional neural network model can be based on having a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, and a fully connected layer. The deeper convolutional neural network model can be based on the first convolutional layer, the first pooling layer, the second convolutional layer, the second pooling layer, the third convolutional layer, the third pooling layer, and the first full The connection layer and the second fully connected layer.
值得一提的是,在不同的實施例中,於所述影像分類步驟S12及所述載入步驟S21之間,還可以是包含有一影像切割步驟,所述影像切割步驟包含:利用自動光學檢測裝置1或處理裝置2,對所述待測影像進行分割,以由所述待測影像中切割出一瑕疵影像,而於所述載入步驟S21中所載入的待測影像,則是所述瑕疵影像。舉例來說,假設自動光學檢測裝置1對待測物進行影像擷取而產生的待測影像為1000像素*1000像素,而後,若自動光學檢測裝置1判斷待測影像中,出現長度為100像素且瑕疵對應圖樣的長寬比為100:1的瑕疵,則自動光學檢測裝置1將待測影像切割為200像素*200像素的瑕疵影像,而所述瑕疵影像中則是包含有長度為100像素且瑕疵對應圖樣的長寬比為100:1的瑕疵,接著,於所述載入步驟S21中,則是載入200像素*200像素的瑕疵影像至相對應的機器學習模型中。依上所述,通過所述影像切割步驟的設計,將可以加速機器學習模型進行影像辨識的速度。It is worth mentioning that in different embodiments, between the image classification step S12 and the loading step S21, an image cutting step may also be included, and the image cutting step includes: using automatic optical inspection The
另外,在分類方法包含所述影像切割步驟及訓練集擴充步驟的實施例中,被存入於其中一個機器學習模型22所對應的訓練圖集31中的影像即為所述瑕疵影像。In addition, in an embodiment where the classification method includes the image cutting step and the training set expansion step, the image stored in the
綜上所述,本發明的分類方法及分類系統通過自動光學檢測裝置分類步驟及機器學習分類步驟等設計,以及使被判定屬於不同預設瑕疵類別的待測影像,利用相對應的機器學習模型進行再次確認等設計,可以大幅改善習知僅利用自動光學檢測裝置進行待測物分類時,自動光學檢測裝置容易發生誤判的問題。In summary, the classification method and classification system of the present invention are designed through automatic optical inspection device classification steps and machine learning classification steps, and make the images to be tested that are judged to belong to different preset defect categories, using corresponding machine learning models Designs such as reconfirmation can greatly improve the problem that the automatic optical inspection device is prone to misjudgment when the conventional automatic optical inspection device is used to classify the object to be tested.
以上所述僅為本發明的較佳可行實施例,非因此侷限本發明的專利範圍,故舉凡運用本發明說明書及圖式內容所做的等效技術變化,均包含於本發明的保護範圍內。The above descriptions are only the preferred and feasible embodiments of the present invention, which do not limit the scope of the present invention. Therefore, all equivalent technical changes made by using the description and drawings of the present invention are included in the protection scope of the present invention. .
100:分類系統 1:自動光學檢測裝置 11:影像擷取器 111:待測影像 2:處理裝置 21:預設灰階規則 22、22A、22B、22C:機器學習模型 23:提示資訊 3:儲存裝置 31:訓練圖集 311:良品圖檔 312:不良品訓練圖檔 4:分類裝置 5:輸入裝置 51:判定結果資訊 100: Classification system 1: Automatic optical inspection device 11: Image grabber 111: Image to be tested 2: Processing device 21: Preset grayscale rules 22, 22A, 22B, 22C: machine learning model 23: Information 3: storage device 31: Training Atlas 311: Good product image file 312: Bad product training image file 4: Sorting device 5: Input device 51: Judgment result information
圖1為本發明的分類系統的方塊示意圖。Figure 1 is a block diagram of the classification system of the present invention.
圖2為本發明的分類方法的自動光學檢測裝置分類步驟的流程示意圖。2 is a schematic flow chart of the classification steps of the automatic optical inspection device of the classification method of the present invention.
圖3為本發明的分類方法的其中一個實際例子的說明示意圖。Fig. 3 is an explanatory diagram of an actual example of the classification method of the present invention.
圖4為通過二值化處理後的待測影像的其中一個實際例的示意圖。FIG. 4 is a schematic diagram of an actual example of the image to be measured after the binarization process.
圖5為通過二值化處理的待測影像的其中一個實施例的示意圖。FIG. 5 is a schematic diagram of one embodiment of the image to be measured through binarization processing.
圖6為本發明的分類方法的機器學習分類步驟的流程示意圖。FIG. 6 is a schematic flowchart of the machine learning classification step of the classification method of the present invention.
圖7為本發明的分類系統的儲存裝置的其中一個實施例的方塊示意圖。FIG. 7 is a block diagram of one embodiment of the storage device of the classification system of the present invention.
圖8為本發明的分類方法的其中一個實際例子的說明示意圖。Fig. 8 is an explanatory diagram of an actual example of the classification method of the present invention.
圖9為發明的分類方法的機器學習分類步驟的另一實施例的流程示意圖。FIG. 9 is a schematic flowchart of another embodiment of the machine learning classification step of the inventive classification method.
圖10為本發明的分類方法的其中一個實際例子的說明示意圖。Fig. 10 is an explanatory diagram of an actual example of the classification method of the present invention.
圖11為通過二值化處理的待測影像的其中一個實施例的示意圖。FIG. 11 is a schematic diagram of one embodiment of the image to be measured through binarization processing.
圖12為待測影像的其中一個實施例的示意圖。FIG. 12 is a schematic diagram of one embodiment of the image to be measured.
100:分類系統 100: Classification system
1:自動光學檢測裝置 1: Automatic optical inspection device
11:影像擷取器 11: Image grabber
111:待測影像 111: Image to be tested
2:處理裝置 2: Processing device
21:預設灰階規則 21: Preset grayscale rules
22:機器學習模型 22: Machine learning model
23:提示資訊 23: Information
3:儲存裝置 3: storage device
31:訓練圖集 31: Training Atlas
311:良品圖檔 311: Good product image file
312:不良品訓練圖檔 312: Bad product training image file
4:分類裝置 4: Sorting device
5:輸入裝置 5: Input device
51:判定結果資訊 51: Judgment result information
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109111742A TWI722861B (en) | 2020-04-08 | 2020-04-08 | Classification method and a classification system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109111742A TWI722861B (en) | 2020-04-08 | 2020-04-08 | Classification method and a classification system |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI722861B true TWI722861B (en) | 2021-03-21 |
TW202138785A TW202138785A (en) | 2021-10-16 |
Family
ID=76036146
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109111742A TWI722861B (en) | 2020-04-08 | 2020-04-08 | Classification method and a classification system |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI722861B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114002225A (en) * | 2021-10-19 | 2022-02-01 | 业成科技(成都)有限公司 | Optical detection system and method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101210889A (en) * | 2006-12-30 | 2008-07-02 | 大元科技股份有限公司 | Holographic type automatic optical detection system and method |
TW201930908A (en) * | 2018-01-05 | 2019-08-01 | 財團法人工業技術研究院 | Board defect filtering method and device thereof and computer-readabel recording medium |
TWI692700B (en) * | 2017-10-05 | 2020-05-01 | 敖翔科技股份有限公司 | Smart defect calibration system and the method thereof |
-
2020
- 2020-04-08 TW TW109111742A patent/TWI722861B/en active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101210889A (en) * | 2006-12-30 | 2008-07-02 | 大元科技股份有限公司 | Holographic type automatic optical detection system and method |
TWI692700B (en) * | 2017-10-05 | 2020-05-01 | 敖翔科技股份有限公司 | Smart defect calibration system and the method thereof |
TW201930908A (en) * | 2018-01-05 | 2019-08-01 | 財團法人工業技術研究院 | Board defect filtering method and device thereof and computer-readabel recording medium |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114002225A (en) * | 2021-10-19 | 2022-02-01 | 业成科技(成都)有限公司 | Optical detection system and method |
CN114002225B (en) * | 2021-10-19 | 2023-05-12 | 业成科技(成都)有限公司 | Optical detection system and method |
Also Published As
Publication number | Publication date |
---|---|
TW202138785A (en) | 2021-10-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109934814B (en) | Surface defect detection system and method thereof | |
US11017259B2 (en) | Defect inspection method, defect inspection device and defect inspection system | |
EP3502966B1 (en) | Data generation apparatus, data generation method, and data generation program | |
JP4616864B2 (en) | Appearance inspection method and apparatus, and image processing evaluation system | |
TWI557650B (en) | System and method for identifying defects in a material | |
KR102058427B1 (en) | Apparatus and method for inspection | |
US11313806B2 (en) | Defect inspection method and defect inspection device | |
KR100598381B1 (en) | in-line typed apparatus for auto wafer-defect classification and control method thereof | |
JP2018036241A (en) | Inspection method, inspection device, inspection program and recording medium | |
CN114266743A (en) | FPC defect detection method, system and storage medium based on HSV and CNN | |
TWI722861B (en) | Classification method and a classification system | |
JP2021143884A (en) | Inspection device, inspection method, program, learning device, learning method, and trained dataset | |
TWI694250B (en) | Surface defect detection system and method thereof | |
CN116542984A (en) | Hardware defect detection method, device, computer equipment and storage medium | |
JP2007285880A (en) | Sample image registration method in board inspection, and sample image producing system | |
JP7298176B2 (en) | Defect inspection device and trained model | |
JP5405245B2 (en) | Image inspection method and image inspection apparatus | |
US11176419B1 (en) | Method for labeling image | |
CN114226262A (en) | Flaw detection method, flaw classification method and flaw detection system | |
JP2981434B2 (en) | Pattern defect detection method and apparatus | |
Mansano et al. | Inspection of metallic surfaces using local binary patterns | |
KR20190119801A (en) | Vehicle Headlight Alignment Calibration and Classification, Inspection of Vehicle Headlight Defects | |
CN105277569B (en) | Route board detecting method based on three-dimensional feature | |
KR20230036650A (en) | Defect detection method and system based on image patch | |
JP3652589B2 (en) | Defect inspection equipment |