TW202030544A - Recognition method of pattern feature - Google Patents
Recognition method of pattern feature Download PDFInfo
- Publication number
- TW202030544A TW202030544A TW108104043A TW108104043A TW202030544A TW 202030544 A TW202030544 A TW 202030544A TW 108104043 A TW108104043 A TW 108104043A TW 108104043 A TW108104043 A TW 108104043A TW 202030544 A TW202030544 A TW 202030544A
- Authority
- TW
- Taiwan
- Prior art keywords
- image
- pattern
- feature
- pattern features
- actual
- Prior art date
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
Description
本發明是有關於一種識別結果可應用於光學鄰近效應校正的圖案特徵的識別方法。The present invention relates to a method for identifying pattern features whose identification results can be applied to optical proximity effect correction.
半導體元件製程中,通常稱最小線寬為關鍵尺寸(critical dimension,CD)。隨著設計法則(design rule)及關鍵尺寸的微縮,在佈局上有時需要特別的斜角度(tilt)或彎曲(wiggle shape)之圖案設計。此外,受限於微影製程與蝕刻製程的限制,通常會使用光學鄰近效應校正(optical proximity correction, OPC)來修正光罩的圖案,以形成精準的圖案。In the semiconductor device manufacturing process, the minimum line width is usually referred to as the critical dimension (CD). With the reduction of design rules and key dimensions, a special tilt or wiggle shape pattern design is sometimes required in the layout. In addition, due to the limitations of the lithography process and the etching process, optical proximity correction (OPC) is usually used to correct the pattern of the photomask to form a precise pattern.
目前,在進行光學鄰近效應校正之前,通常會藉由人工的方式針對由掃瞄式電子顯微鏡(Scanning Electron Microscope, SEM)所獲得的圖案影像來量測圖案的特徵值(例如圖案彎曲的角度、相鄰圖案之間的距離等)。之後,將所量測的特徵值應用至光學鄰近效應校正中作為補償值,以製作可形成精準圖案的光罩。At present, before the optical proximity effect correction is performed, the pattern image obtained by the Scanning Electron Microscope (SEM) is usually manually measured to measure the characteristic value of the pattern (such as the angle of pattern bending, The distance between adjacent patterns, etc.). After that, the measured characteristic value is applied to the optical proximity effect correction as a compensation value to produce a mask that can form a precise pattern.
然而,利用人工方式來量測圖案的特徵值十分耗時且容易存在人為判斷誤差,因而影響最終所形成的圖案的精準度。However, using manual methods to measure the characteristic values of patterns is very time-consuming and prone to human judgment errors, which affects the accuracy of the final pattern formed.
本發明提供一種圖案特徵的識別方法,其利用影像辨識裝置來得到圖案特徵的識別結果。The invention provides a pattern feature recognition method, which uses an image recognition device to obtain a pattern feature recognition result.
本發明的一種圖案特徵的識別方法,其識別結果應用於光學鄰近效應校正,所述圖案特徵的識別方法包括提供多個具有參考圖案特徵的參考影像,再藉由影像辨識裝置對參考影像進行辨識與分類,並儲存辨識結果。然後,藉由影像辨識裝置將具有實際圖案特徵的影像與儲存的辨識結果進行比對,以將具有實際圖案特徵的影像進行辨識與分類。並且,藉由影像辨識裝置根據分類的結果來計算實際圖案特徵的角度特徵值及/或距離特徵值,以得到圖案特徵的識別結果。A pattern feature recognition method of the present invention, the recognition result of which is applied to optical proximity effect correction. The pattern feature recognition method includes providing a plurality of reference images with reference pattern characteristics, and then identifying the reference image by an image recognition device And classification, and save the identification results. Then, the image with the actual pattern feature is compared with the stored recognition result by the image recognition device to identify and classify the image with the actual pattern feature. In addition, the image recognition device calculates the angle feature value and/or the distance feature value of the actual pattern feature according to the classification result to obtain the recognition result of the pattern feature.
基於上述,在本發明中,利用影像辨識裝置來得到圖案特徵的識別結果,可避免人為判斷誤差的發生。並且,藉由影像辨識裝置對具有實際圖案特徵的影像進行比對及分類,可一次性的計算影像中多個角度特徵值及/或距離特徵值,進而有效提升半導體元件製程的效率。Based on the above, in the present invention, the image recognition device is used to obtain the recognition result of the pattern feature, which can avoid the occurrence of human judgment errors. In addition, by comparing and classifying images with actual pattern features by the image recognition device, multiple angle feature values and/or distance feature values in the image can be calculated at one time, thereby effectively improving the efficiency of the semiconductor device manufacturing process.
為讓本發明的上述特徵和優點能更明顯易懂,下文特舉實施例,並配合所附圖式作詳細說明如下。In order to make the above-mentioned features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail in conjunction with the accompanying drawings.
在本文中,所謂「圖案特徵」是指彎曲圖案所具有的角度及/或相鄰圖案之間的距離等。舉例來說,彎曲圖案所具有的角度為彎曲圖案的轉折處(頂點)所呈現的角度,其可為鈍角、直角或銳角。並且,圖案特徵的識別結果例如可應用於計算光學鄰近效應校正時所需的補償值。In this context, the so-called "pattern feature" refers to the angle of the curved pattern and/or the distance between adjacent patterns. For example, the angle of the curved pattern is the angle presented by the turning point (vertex) of the curved pattern, and it may be an obtuse angle, a right angle, or an acute angle. In addition, the recognition result of the pattern feature can be used to calculate the compensation value required for the correction of the optical proximity effect, for example.
圖1是依照本發明一實施例的圖案特徵的識別方法的流程圖。FIG. 1 is a flowchart of a method for identifying pattern features according to an embodiment of the invention.
請參照圖1,首先,進行步驟S100,提供多個具有參考圖案特徵的參考影像。在本實施例中,所謂「參考圖案特徵」為現有的元件的淺溝渠隔離(shallow trench isolation,STI)圖案、形成接觸窗所需的開孔圖案或是線路設計所需的導線圖案等圖案,然而本發明不以此為限。在本實施例中,參考影像為由掃描式電子顯微鏡針對現有的元件進行拍攝而得的影像,其中掃描式電子顯微鏡例如為關鍵尺寸掃描式電子顯微鏡(critical dimension scanning electron microscope,CD-SEM)。Please refer to FIG. 1, first, step S100 is performed to provide a plurality of reference images with the characteristics of reference patterns. In this embodiment, the so-called "reference pattern feature" is the shallow trench isolation (STI) pattern of the existing device, the opening pattern required to form the contact window, or the pattern of the wire pattern required for circuit design. However, the present invention is not limited to this. In this embodiment, the reference image is an image captured by a scanning electron microscope for existing components, where the scanning electron microscope is, for example, a critical dimension scanning electron microscope (CD-SEM).
然後,進行步驟S102,將所述多個參考影像提供至影像辨識裝置。在影像辨識的過程中,影像辨識裝置先將每一個參考影像分割為多個次影像。一般來說,掃描式電子顯微鏡照片的尺寸例如為960×960畫素(pixel),因此,在本實施例中,以960×960畫素的參考影像200為例,影像辨識裝置將參考影像200以10×10畫素為單位進行分割,可得到96×96個次影像210,如圖2所示。藉此,後續可藉由影像辨識裝置對其中一個次影像210進行辨識與分類,以進行後續的辨識步驟。Then, step S102 is performed to provide the multiple reference images to the image recognition device. In the image recognition process, the image recognition device first divides each reference image into multiple secondary images. Generally speaking, the size of a scanning electron microscope photograph is, for example, 960×960 pixels. Therefore, in this embodiment, taking the
一般而言,掃描式電子顯微鏡照片由於半導體元件的表面結構的不同,使得掃描式電子顯微鏡接收到的二次電子訊號改變,進而於二次電子訊號不平整處產生如圖2所示的白邊(white wall)。在本實施例中,如圖2所示,參考影像200的白邊216呈現彎曲波浪狀圖案,且白邊216包含邊界212及頂點214,其中頂點214為彎曲波浪狀圖案的轉折處,且兩相鄰的頂點214之間為邊界212。經分割後,參考影像200包括含有邊界212的次影像210a、含有頂點214的次影像210b、與其餘的次影像210c。Generally speaking, due to the difference in the surface structure of the semiconductor components, the scanning electron microscope photo changes the secondary electron signal received by the scanning electron microscope, and the white edge shown in Figure 2 is generated at the unevenness of the secondary electron signal. (White wall). In this embodiment, as shown in FIG. 2, the
接著,進行步驟S104,藉由影像辨識裝置將包含有參考圖案特徵的邊界或頂點的次影像分類為第一類,以及將其餘的次影像分類為第二類。在本實施例中,藉由影像辨識裝置將次影像210a與次影像210b分類為第一類,以及將次影像210c分類為第二類。在本實施例中,第二類被視為影像的雜訊而不予以參考。換句話說,在後續的辨識步驟中,主要以第一類作為辨識圖案特徵的分析依據。在本實施例中,影像辨識裝置例如藉由K均值群聚演算法(K-Means cluster)進行上述的影像辨識與分類。Then, step S104 is performed to classify the secondary image including the boundary or vertex of the reference pattern feature as the first type by the image recognition device, and classify the remaining secondary images as the second type. In this embodiment, the
然後,進行步驟S106,儲存辨識結果。具體來說,經上述步驟對參考影像200進行辨識與分類後,將辨識結果(包括分類結果)進行儲存。據此,可藉由上述第一類與第二類的次影像210進行後續的辨識步驟,以代替工程人員的主觀判斷,進而避免人為判斷誤差的發生。Then, step S106 is performed to store the identification result. Specifically, after the
接著,進行步驟S108,將具有實際圖案特徵的影像與儲存的辨識結果進行比對與辨識。在本實施例中,所謂「實際圖案特徵」類似於上述參考圖案特徵,可為實際的元件的淺溝渠隔離圖案、形成接觸窗所需的開孔圖案或是線路設計所需的導線圖案等圖案,然而本發明不以此為限。在本實施例中,具有實際圖案特徵的影像例如包括由掃描式電子顯微鏡對實際的元件進行拍攝而得的影像,其中掃描式電子顯微鏡例如為關鍵尺寸掃描式電子顯微鏡(CD-SEM)。Then, step S108 is performed to compare and recognize the image with the actual pattern characteristics and the stored recognition result. In this embodiment, the so-called "actual pattern feature" is similar to the above-mentioned reference pattern feature, which can be the shallow trench isolation pattern of the actual device, the opening pattern required to form the contact window, or the pattern of the wire pattern required for circuit design. However, the present invention is not limited to this. In this embodiment, the image with actual pattern features includes, for example, an image obtained by a scanning electron microscope photographing an actual element, where the scanning electron microscope is, for example, a critical dimension scanning electron microscope (CD-SEM).
在此步驟中,藉由影像辨識裝置將具有實際圖案特徵的影像與第一類的次影像進行比對,即例如利用步驟S106所儲存的辨識結果中第一類的次影像的邊界或頂點擬合(fitting)具有實際圖案特徵的影像。In this step, the image with the actual pattern characteristics is compared with the first type of secondary image by the image recognition device, that is, for example, using the boundary or vertex of the first type of secondary image in the recognition result stored in step S106 Fitting images with actual pattern characteristics.
然後,根據具有實際圖案特徵的影像的擬合結果,辨識具有實際圖案特徵的影像,將具有封閉式圖案特徵的具有實際圖案特徵的影像分類為第一類影像,以及將具有開放式圖案特徵的具有實際圖案特徵的影像分類為第二類影像。舉例來說,若具有實際圖案特徵的影像呈現方形、圓形等封閉式圖案,則此實際圖案特徵視為封閉式圖案特徵;相反地,則此實際圖案特徵視為開放式圖案特徵。在本實施例中,封閉式圖案特徵為開孔圖案或開口圖案,開放式圖案特徵為導線圖案。之後,即可藉由影像辨識裝置根據分類的結果來計算實際圖案特徵的角度特徵值及/或距離特徵值,以得到圖案特徵的識別結果。下文將對角度特徵值與距離特徵值作詳細的定義。Then, according to the fitting result of the image with the actual pattern feature, the image with the actual pattern feature is identified, the image with the closed pattern feature and the actual pattern feature is classified as the first type of image, and the image with the open pattern feature is classified Images with actual pattern characteristics are classified as the second type of images. For example, if an image with actual pattern features presents a closed pattern such as a square or a circle, the actual pattern feature is regarded as a closed pattern feature; on the contrary, the actual pattern feature is regarded as an open pattern feature. In this embodiment, the closed pattern feature is an opening pattern or an opening pattern, and the open pattern feature is a wire pattern. After that, the image recognition device can be used to calculate the angle feature value and/or the distance feature value of the actual pattern feature according to the classification result to obtain the recognition result of the pattern feature. The following will give a detailed definition of the angle characteristic value and the distance characteristic value.
以下,將分別針對計算第一類影像或第二類影像中的實際圖案特徵的角度特徵值及/或距離特徵值作說明。Hereinafter, the calculation of the angle feature value and/or the distance feature value of the actual pattern feature in the first type image or the second type image will be described respectively.
若具有實際圖案特徵的影像被分類為第一類影像,則進行下述步驟,來計算實際圖案特徵的角度特徵值及距離特徵值。If the image with the actual pattern feature is classified as the first type of image, the following steps are performed to calculate the angle feature value and the distance feature value of the actual pattern feature.
請同時參照圖1與圖3A,進行步驟S110,找出各個封閉式圖案特徵的重心。舉例來說,可利用影像辨識裝置中的計算單元、或外接於影像辨識裝置的計算單元來找出第一類影像300中各個封閉式圖案特徵的重心310,然而本發明不以此為限。在本實施例中,第一類影像300的封閉式圖案特徵以呈現橢圓形圖案為例,且各個橢圓形圖案例如以彼此交錯的方式排列。在其他實施例中,也可以呈現圓形圖案、方形圖案等,或是以不同的方式排列,然本發明不以此為限。1 and 3A at the same time, proceed to step S110 to find the center of gravity of each closed pattern feature. For example, the calculation unit in the image recognition device or the calculation unit external to the image recognition device can be used to find the center of
請同時參照圖1與圖3B,進行步驟S112,計算相鄰的兩個封閉式圖案特徵的重心之間的連線的斜率。在本實施例中,如圖3B所示將彼此交錯且相鄰的重心312與重心314相連而得到連線316,並利用上述計算單元計算連線316的斜率。並且,藉由計算而得的連線316的斜率對封閉式圖案特徵進行分類。舉例來說,若連線316的斜率大於0,則具有重心312的封閉式圖案特徵與具有重心314的封閉式圖案特徵被分類為第一群;若連線316的斜率小於或等於0,則具有重心312的封閉式圖案特徵與具有重心314的封閉式圖案特徵被分類為第二群。也就是說,將斜率大於0的相鄰的兩個封閉式圖案特徵分類為第一群,以及將斜率小於或等於0的相鄰的兩個封閉式圖案特徵分類為第二群。1 and 3B at the same time, proceed to step S112 to calculate the slope of the line between the centers of gravity of two adjacent closed pattern features. In this embodiment, as shown in FIG. 3B, the center of
接著,挑選第一群或第二群來計算後續步驟中的特徵值,以避免重複計算。舉例來說,在同一群斜率的情況下,藉由挑選任兩個斜率不超過一定的偏差值(threshold)來計算後續步驟中的特徵值,而可降低計算的誤差。在一實施例中,一定的偏差值為0.01,然而本發明不以此為限。在本實施例中,如圖3B所示例如是挑選斜率小於0的相鄰的兩個封閉式圖案特徵,即第二群,來進行計算。Then, select the first group or the second group to calculate the feature values in the subsequent steps to avoid repeated calculations. For example, in the case of the same group of slopes, by selecting any two slopes not to exceed a certain deviation value (threshold) to calculate the characteristic value in the subsequent steps, the calculation error can be reduced. In one embodiment, a certain deviation value is 0.01, but the present invention is not limited to this. In this embodiment, as shown in FIG. 3B, for example, two adjacent closed pattern features with a slope less than 0, that is, the second group, are selected for calculation.
之後,進行步驟S114,計算相鄰的兩個封閉式圖案特徵的重心之間的距離。在本實施例中,如圖3B所示,藉由計算單元來計算連線316的長度,即重心312與重心314之間的距離D1。After that, step S114 is performed to calculate the distance between the centers of gravity of two adjacent closed pattern features. In this embodiment, as shown in FIG. 3B, the length of the
並進行步驟S116,根據距離D1來計算角度特徵值θ1與距離特徵值D2、D3。在本實施例中,利用計算單元計算相鄰的兩個封閉式圖案特徵的角度特徵值θ1,並藉由上述計算而得的重心312與重心314之間的距離D1以及角度特徵值θ1,根據反三角函數法來獲得距離特徵值D2、D3。在本實施例中,距離特徵值D2實質上等於重心312與重心314之間的水平距離,距離特徵值D3實質上等於重心312與重心314之間的垂直距離。換句話說,距離D1與距離特徵值D2、D3大致上為構成直角三角形的三邊的邊長,而角度特徵值θ1例如為直角三角形中的其中一個夾角。在本實施例中,角度特徵值θ1與距離特徵值D2、D3即為可應用於光學鄰近效應校正的圖案特徵的識別結果。And proceed to step S116 to calculate the angle feature value θ1 and the distance feature values D2, D3 according to the distance D1. In this embodiment, the calculation unit is used to calculate the angle feature value θ1 of two adjacent closed pattern features, and the distance D1 between the center of
以上為方便說明,是以計算一組角度特徵值與距離特徵值為例。在其他實施例中,可以藉由影像辨識裝置同時對多組封閉式圖案特徵進行計算,便可以一次性的獲得第一類影像中的實際圖案特徵中多個角度特徵值及/或距離特徵值,進而有效提升半導體元件製程的效率。For the convenience of description, the above is an example of calculating a set of angle characteristic values and distance characteristic values. In other embodiments, multiple sets of closed pattern features can be calculated simultaneously by the image recognition device, and multiple angle feature values and/or distance feature values of the actual pattern features in the first type of image can be obtained at one time , Thereby effectively improving the efficiency of the semiconductor device manufacturing process.
在另一實施例中,若是計算第二類影像中的實際圖案特徵的特徵值,則如圖1、圖4A與圖4B所示進行步驟S118,計算實際圖案特徵的角度特徵值。In another embodiment, if the feature value of the actual pattern feature in the second type of image is calculated, step S118 is performed as shown in FIGS. 1, 4A and 4B to calculate the angle feature value of the actual pattern feature.
請同時參照圖1與圖4A,在本實施例中,第二類影像400的開放式圖案特徵以呈現彎曲波浪狀圖案為例,且各個彎曲波浪狀圖案以彼此平行的方式排列。在其他實施例中,也可以呈現其他的導線圖案,或是以不同的方式排列,然而本發明不以此為限。Please refer to FIGS. 1 and 4A at the same time. In this embodiment, the open pattern feature of the second-
舉例來說,藉由影像辨識裝置將第二類影像400與第一類的次影像進行比對,即例如利用步驟S106所儲存的辨識結果中第一類的次影像的邊界或頂點擬合第二類影像400,以更明顯地標示出第二類影像400的開放式圖案特徵的邊界或頂點,而可代替工程人員的主觀判斷,進而避免人為判斷誤差的發生。For example, the second-
請同時參照圖1與圖4B,藉由影像辨識裝置中的計算單元、或外接於影像辨識裝置的計算單元來計算相鄰的兩個邊界以及使兩個邊界相連的頂點之間所呈現的角度,以獲得第二類影像400的開放式圖案特徵的角度特徵值θ2。在其他實施例中,可以藉由影像辨識裝置同時對多組開放式圖案特徵進行計算,便可一次性的計算開放式圖案特徵的多個角度特徵值,進而有效提升半導體元件製程的效率。在本實施例中,角度特徵值θ2即為可應用於光學鄰近效應校正方法的圖案特徵的識別結果。Please refer to FIG. 1 and FIG. 4B at the same time, the calculation unit in the image recognition device or the calculation unit external to the image recognition device is used to calculate the angle between the two adjacent borders and the vertices connecting the two borders. , To obtain the angle feature value θ2 of the open pattern feature of the
在一實施例中,可藉由影像辨識裝置同時對第二類影像中的開放式圖案特徵的多組角度特徵值進行計算,並可如圖5所示自動標示於影像中。In one embodiment, the image recognition device can be used to simultaneously calculate multiple sets of angular feature values of the open pattern features in the second type of image, and can be automatically marked in the image as shown in FIG. 5.
綜上所述,藉由影像辨識裝置根據分類的結果來計算多組角度特徵值及/或距離特徵值,可避免人為判斷誤差的發生。另外,將多組角度特徵值及/或距離特徵值應用於光學鄰近效應校正,並藉由反三角函數法等方法推得光學鄰近效應校正所需的補償值,以校正光罩的圖案,進而形成精準的圖案。如此一來,可避免人為判斷誤差的發生,且有效提升半導體元件製程的效率。In summary, by using the image recognition device to calculate multiple sets of angle feature values and/or distance feature values according to the classification results, the occurrence of human judgment errors can be avoided. In addition, multiple sets of angle feature values and/or distance feature values are applied to the optical proximity effect correction, and the compensation value required for the optical proximity effect correction is derived by methods such as inverse trigonometric function method to correct the pattern of the mask, and then Form a precise pattern. In this way, human judgment errors can be avoided, and the efficiency of the semiconductor device manufacturing process can be effectively improved.
雖然本發明已以實施例揭露如上,然其並非用以限定本發明,任何所屬技術領域中具有通常知識者,在不脫離本發明的精神和範圍內,當可作些許的更動與潤飾,故本發明的保護範圍當視後附的申請專利範圍所界定者為準。Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Anyone with ordinary knowledge in the technical field can make some changes and modifications without departing from the spirit and scope of the present invention. The scope of protection of the present invention shall be determined by the scope of the attached patent application.
200:參考影像
210、210a、210b、210c:次影像
212:邊界
214:頂點
216:白邊
300:第一類影像
310、312、314:重心
316:連線
400:第二類影像
S100、S102、S104、S106、S108、S110、S112、S114、S116、S118:步驟
θ1、θ2:角度特徵值
D1:距離
D2、D3:距離特徵值200:
圖1是依照本發明一實施例的圖案特徵的識別方法的流程圖。 圖2是經分割的參考影像的掃瞄式電子顯微鏡(SEM)照片。 圖3A是第一類影像的掃瞄式電子顯微鏡(SEM)照片。 圖3B是表示第一類影像的示意圖。 圖4A是第二類影像的掃瞄式電子顯微鏡(SEM)照片。 圖4B是表示第二類影像的示意圖。 圖5是表示圖案特徵的識別結果的掃瞄式電子顯微鏡(SEM)照片。FIG. 1 is a flowchart of a method for identifying pattern features according to an embodiment of the invention. Figure 2 is a scanning electron microscope (SEM) photograph of the segmented reference image. Figure 3A is a scanning electron microscope (SEM) photograph of the first type of image. Fig. 3B is a schematic diagram showing the first type of image. Figure 4A is a scanning electron microscope (SEM) photo of the second type of image. Fig. 4B is a schematic diagram showing the second type of image. Fig. 5 is a scanning electron microscope (SEM) photograph showing the recognition result of pattern features.
S100、S102、S104、S106、S108、S110、S112、S114、S116、S118:步驟 S100, S102, S104, S106, S108, S110, S112, S114, S116, S118: steps
Claims (9)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW108104043A TWI695221B (en) | 2019-02-01 | 2019-02-01 | Recognition method of pattern feature |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW108104043A TWI695221B (en) | 2019-02-01 | 2019-02-01 | Recognition method of pattern feature |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI695221B TWI695221B (en) | 2020-06-01 |
TW202030544A true TW202030544A (en) | 2020-08-16 |
Family
ID=72176074
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW108104043A TWI695221B (en) | 2019-02-01 | 2019-02-01 | Recognition method of pattern feature |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI695221B (en) |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7014955B2 (en) * | 2001-08-28 | 2006-03-21 | Synopsys, Inc. | System and method for indentifying dummy features on a mask layer |
US9401016B2 (en) * | 2014-05-12 | 2016-07-26 | Kla-Tencor Corp. | Using high resolution full die image data for inspection |
US10074036B2 (en) * | 2014-10-21 | 2018-09-11 | Kla-Tencor Corporation | Critical dimension uniformity enhancement techniques and apparatus |
KR102048918B1 (en) * | 2014-12-18 | 2020-01-08 | 에이에스엠엘 네델란즈 비.브이. | Feature search by machine learning |
-
2019
- 2019-02-01 TW TW108104043A patent/TWI695221B/en active
Also Published As
Publication number | Publication date |
---|---|
TWI695221B (en) | 2020-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115147414B (en) | Surface breakdown defect detection method for bipolar power transistor | |
JP6227466B2 (en) | Charged particle beam apparatus and inspection apparatus | |
JP6004956B2 (en) | Pattern evaluation apparatus and appearance inspection apparatus provided with pattern evaluation apparatus | |
US7090949B2 (en) | Method of manufacturing a photo mask and method of manufacturing a semiconductor device | |
JP5500858B2 (en) | Pattern measuring device | |
JP5543984B2 (en) | CD measurement system and method for classifying similar structural elements | |
TW201921167A (en) | Methods of determining corrections for a patterning process, device manufacturing method, control system for a lithographic apparatus and lithographic apparatus | |
JP5081276B2 (en) | Pattern measuring device, pattern measuring method, and program | |
US20120198404A1 (en) | Defect inspection supporting apparatus and defect inspection supporting method | |
JP5677356B2 (en) | Generation method of mask pattern | |
CN116402808B (en) | Intelligent detection method for manufacturing cable clamp plate die | |
TW202017069A (en) | Method, system and non-transitory ccomputer readable medium for wafer-to-design image analysis | |
EP2663998B1 (en) | Method and system of object based metrology for advanced wafer surface nanotopography | |
US10916006B2 (en) | Recognition method of pattern feature | |
WO2022058264A1 (en) | Defect detection for semiconductor structures on a wafer | |
CN116503316A (en) | Chip defect measurement method and system based on image processing | |
JP5810031B2 (en) | Semiconductor circuit pattern measuring apparatus and method | |
US20150268177A1 (en) | Defect detection method | |
TWI695221B (en) | Recognition method of pattern feature | |
CN113192045A (en) | Defect size analysis method for weld image | |
CN111580338B (en) | Pattern feature recognition method | |
TWI736843B (en) | Contour extraction method, contour extraction device and non-volatile recording medium | |
TWI697972B (en) | Method for monitoring fin removal | |
CN115829951A (en) | Scanning electron microscope image defect classification method and device based on design layout | |
JPS63147281A (en) | Pattern detecting method |