CN115908532A - Line width identification method, line width identification device, medium and electronic device - Google Patents
Line width identification method, line width identification device, medium and electronic device Download PDFInfo
- Publication number
- CN115908532A CN115908532A CN202110949034.5A CN202110949034A CN115908532A CN 115908532 A CN115908532 A CN 115908532A CN 202110949034 A CN202110949034 A CN 202110949034A CN 115908532 A CN115908532 A CN 115908532A
- Authority
- CN
- China
- Prior art keywords
- picture
- boundary
- determining
- recognized
- pixel
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The application discloses a line width identification method, a line width identification device, a medium and an electronic device, wherein the line width identification method comprises the following steps: acquiring a picture to be identified; determining a first physical size corresponding to a single pixel in the picture to be recognized and a first pixel number of a distance between boundaries of the circuit pattern in the picture to be recognized; and taking the product of the first physical size and the first pixel number as the line width of the circuit pattern in the picture to be identified. The line width identification method can improve the line width identification accuracy of the line pattern.
Description
Technical Field
The application belongs to the technical field of quantum computing, and particularly relates to a line width identification method, a line width identification device, a medium and an electronic device.
Background
With the development of semiconductor manufacturing processes, integrated circuit devices are becoming more and more precise. Therefore, in semiconductor manufacturing, the control of Critical Dimension (CD) such as the line width of fine circuit patterns on a mask or a wafer is an important link. When an integrated circuit element is prepared, line width detection needs to be carried out on a circuit pattern to judge whether the circuit pattern is accurate or not and whether deviation exists or not. As semiconductor dimensions shrink, the process-tolerant line width errors become smaller and smaller, and the current main way to identify line widths is still manual identification. The manual identification mode greatly depends on human subjectivity, so that results obtained by different people are different for the line width of the same line pattern, the error is large, and the method is not tolerable for the nanometer-level semiconductor manufacturing process. Therefore, how to accurately identify the line width of the circuit pattern is an urgent problem to be solved.
Content of application
The application aims to provide a line identification method, a line identification device, a medium and an electronic device, and aims to improve the line width identification accuracy of a line pattern.
One embodiment of the present application provides a line width identification method, including:
acquiring a picture to be identified;
determining a first physical size corresponding to a single pixel in the picture to be recognized and a first pixel number of a distance between boundaries of the circuit pattern in the picture to be recognized;
and taking the product of the first physical size and the first pixel number as the line width of the circuit pattern in the picture to be identified.
Optionally, the determining a first physical size corresponding to a single pixel in the picture to be recognized includes:
determining a scale in the picture to be identified, wherein the length of the scale is the second pixel number;
and taking the quotient of the second physical size corresponding to the scale and the second pixel number as the first physical size corresponding to a single pixel in the picture to be identified.
Optionally, the determining a scale in the picture to be recognized includes:
if the type of the picture to be recognized is a first type, determining a first line segment of which the pixel value is greater than or equal to a first preset threshold and the pixel number is greater than or equal to a second preset threshold in the picture to be recognized, and determining the first line segment as a ruler in the picture to be recognized;
if the type of the picture to be recognized is a second type, determining a first rectangle of which the size is larger than or equal to a third preset threshold and the pixel value is larger than or equal to a fourth preset threshold in the picture to be recognized; if the first number of the first rectangles is larger than or equal to a fifth preset threshold value and is uniformly distributed along a first direction, determining the first number of the first rectangles as scales in the picture to be identified.
Optionally, the boundary includes a left boundary, a right boundary, an upper boundary, and a lower boundary, and the first pixel number includes a first sub-pixel number and a second sub-pixel number; the determining a first pixel number of a distance between boundaries of the line pattern in the picture to be recognized includes:
performing normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture;
determining a vertical line formed by pixels of which the pixel values are first target values in the intermediate process picture, and determining a horizontal line formed by pixels of which the pixel values are second target values in the intermediate process picture;
determining a left boundary and a right boundary based on the vertical lines, and determining an upper boundary and a lower boundary based on the horizontal lines;
a first sub-pixel number of a distance between the left and right boundaries is determined, and a second sub-pixel number of a distance between the upper and lower boundaries is determined.
Optionally, the determining the left boundary and the right boundary based on the vertical line includes:
pairing every two vertical lines to obtain vertical line pairs;
and if a first vertical line pair exists in the vertical line pair, wherein the distance between the vertical lines meets a first preset range, one of the first vertical line pair is used as a left boundary, and the other vertical line pair is used as a right boundary.
Optionally, the determining the upper boundary and the lower boundary based on the horizontal line includes:
pairing every two transverse lines to obtain a transverse line pair;
and if a first transverse line pair with the distance between the transverse lines meeting a second preset range exists in the transverse line pair, taking one of the first transverse line pair as an upper boundary and taking the other one as a lower boundary.
Optionally, the method further includes:
and if no first vertical line pair with the distance between the vertical lines meeting a first preset range exists in the vertical line pair, reducing a detection threshold value in the edge detection operation, and then executing the normalization, gaussian filtering and edge detection operation on the picture to be identified to obtain an intermediate process picture.
Optionally, the method further includes:
if no first vertical line pair with the distance between the vertical lines meeting a first preset range exists in the vertical line pair, reducing the width and the height of a Gaussian kernel in the Gaussian filtering operation, and then executing the normalization, the Gaussian filtering and the edge detection operation on the picture to be recognized to obtain an intermediate process picture.
Optionally, after determining the left boundary and the right boundary based on the vertical line and determining the upper boundary and the lower boundary based on the horizontal line, the method further includes:
translating the left boundary leftwards by a first preset distance to obtain a new left boundary, translating the right boundary rightwards by a second preset distance to obtain a new right boundary, translating the upper boundary upwards by a third preset distance to obtain a new upper boundary, and translating the lower boundary downwards by a fourth preset distance to obtain a new lower boundary;
extending a rectangular frame surrounded by the left boundary, the right boundary, the upper boundary and the lower boundary outwards by a fifth preset distance to obtain a new rectangular frame;
and taking the selected part of the rectangular frame on the picture to be identified as a new picture to be identified, and then executing normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture.
Another embodiment of the present application provides a line width recognition apparatus, including:
the acquisition unit is used for acquiring a picture to be identified;
the determining unit is used for determining a first physical size corresponding to a single pixel in the picture to be recognized and a first pixel number of a distance between boundaries of the circuit pattern in the picture to be recognized;
and the identification unit is used for taking the product of the first physical size and the first pixel number as the line width of the line pattern in the picture to be identified.
Optionally, in the aspect of determining the first physical size corresponding to a single pixel in the picture to be recognized, the determining unit is specifically configured to:
determining a scale in the picture to be identified, wherein the length of the scale is a second pixel number;
and taking the quotient of the second physical size corresponding to the scale and the second pixel number as the first physical size corresponding to a single pixel in the picture to be identified.
Optionally, in the aspect of determining the scale in the picture to be recognized, the determining unit is specifically configured to:
if the type of the picture to be recognized is a first type, determining a first line segment of which the pixel value is greater than or equal to a first preset threshold and the pixel number is greater than or equal to a second preset threshold in the picture to be recognized, and determining the first line segment as a ruler in the picture to be recognized;
if the type of the picture to be recognized is a second type, determining a first rectangle of which the size is larger than or equal to a third preset threshold and the pixel value is larger than or equal to a fourth preset threshold in the picture to be recognized; if the first number of the first rectangles is larger than or equal to a fifth preset threshold value and are uniformly distributed along a first direction, determining the first number of the first rectangles as scales in the picture to be identified.
Optionally, the boundary includes a left boundary, a right boundary, an upper boundary, and a lower boundary, and the first pixel number includes a first sub-pixel number and a second sub-pixel number; in the aspect of determining the first pixel number of the distance between the boundaries of the line pattern in the picture to be recognized, the determining unit is specifically configured to:
performing normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture;
determining a vertical line formed by pixels of which the pixel values are first target values in the intermediate process picture, and determining a horizontal line formed by pixels of which the pixel values are second target values in the intermediate process picture;
determining a left boundary and a right boundary based on the vertical lines, and determining an upper boundary and a lower boundary based on the horizontal lines;
a first sub-pixel number of a distance between the left and right boundaries is determined, and a second sub-pixel number of a distance between the upper and lower boundaries is determined.
Optionally, in the aspect of determining the left boundary and the right boundary based on the vertical line, the determining unit is specifically configured to:
pairing every two vertical lines to obtain vertical line pairs;
and if a first vertical line pair exists in the vertical line pair, wherein the distance between the vertical lines meets a first preset range, one of the first vertical line pair is used as a left boundary, and the other vertical line pair is used as a right boundary.
Optionally, in the aspect of determining the upper boundary and the lower boundary based on the horizontal line, the determining unit is specifically configured to:
pairing every two transverse lines to obtain a transverse line pair;
and if a first transverse line pair with the distance between the transverse lines meeting a second preset range exists in the transverse line pair, taking one of the first transverse line pair as an upper boundary and taking the other one as a lower boundary.
Optionally, the determining unit is further configured to:
and if the first vertical line pair with the distance between the vertical lines meeting a first preset range does not exist in the vertical line pair, reducing a detection threshold value in the edge detection operation, and then executing the normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture.
Optionally, the determining unit is further configured to:
if the first vertical line pair with the distance between the vertical lines meeting a first preset range does not exist in the vertical line pair, reducing the width and the height of a Gaussian kernel in the Gaussian filtering operation, and then executing the normalization, the Gaussian filtering and the edge detection operation on the picture to be identified to obtain an intermediate process picture.
Optionally, after the determining the left boundary and the right boundary based on the vertical line and the determining the upper boundary and the lower boundary based on the horizontal line, the determining unit is further configured to:
translating the left boundary leftwards by a first preset distance to obtain a new left boundary, translating the right boundary rightwards by a second preset distance to obtain a new right boundary, translating the upper boundary upwards by a third preset distance to obtain a new upper boundary, and translating the lower boundary downwards by a fourth preset distance to obtain a new lower boundary;
extending a rectangular frame surrounded by the left boundary, the right boundary, the upper boundary and the lower boundary outwards by a fifth preset distance to obtain a new rectangular frame;
and taking the selected part of the rectangular frame on the picture to be identified as a new picture to be identified, and then executing normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture.
A further embodiment of the application provides a storage medium having a computer program stored thereon, wherein the computer program is arranged to perform the method as described in any of the above when executed.
Yet another embodiment of the present application provides an electronic device, comprising a memory having a computer program stored therein and a processor configured to execute the computer program to perform the method described in any of the above.
Compared with the prior art, the line width identification method provided by the application takes the product of the first physical dimension corresponding to a single pixel in the picture to be identified and the first pixel number of the distance between the boundaries of the line pattern in the picture to be identified as the line width of the line pattern in the picture to be identified, the pixel is the minimum unit which can not be cut in the picture, and the pixel exists in a small cell with a single color, so that the line width of the line pattern is more accurately determined by taking the pixel as a unit for measuring the length; meanwhile, a machine is adopted to determine the number of pixels, so that manual errors caused by inconsistent quantity of manual statistics can be avoided.
Drawings
Fig. 1 is a block diagram of a hardware structure of a computer terminal of a line width identification method according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a line width identification method according to an embodiment of the present application;
fig. 3 is a first type of picture to be recognized according to an embodiment of the present disclosure;
fig. 4 is a second type of picture to be recognized according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a line width identification device according to an embodiment of the present application.
Detailed Description
The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
The embodiment of the application firstly provides a line width identification method, which can be applied to electronic devices, such as computer terminals, specifically ordinary computers, quantum computers and the like.
This will be described in detail below by way of example as it would run on a computer terminal. Fig. 1 is a block diagram of a hardware structure of a computer terminal of a line width identification method according to an embodiment of the present application. As shown in fig. 1, the computer terminal may include one or more processors 102 (only one is shown in fig. 1) (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing the line width recognition method, and optionally, the computer terminal may further include a transmission device 106 for communication function and an input/output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the computer terminal. For example, the computer terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used to store software programs and modules of application software, such as program instructions/modules corresponding to the line width recognition method in the embodiment of the present application, and the processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 104, so as to implement the above-mentioned method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to a computer terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 106 can be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
Referring to fig. 2, fig. 2 is a schematic flowchart of a line width identification method provided in the embodiment of the present application. The method comprises the following steps:
step 201: acquiring a picture to be identified;
specifically, the acquiring of the picture to be recognized includes acquiring a size, a type, and the like of the picture to be recognized uploaded by the user. The size includes a length and a width, and for example, the length of the size of the picture to be recognized is denoted as h, and the width is denoted as w.
Step 202: determining a first physical size corresponding to a single pixel in the picture to be recognized and a first pixel number of a distance between boundaries of the circuit pattern in the picture to be recognized;
specifically, in the aspect of determining the first physical size corresponding to a single pixel in the picture to be recognized, the method includes: determining a scale in the picture to be identified, wherein the length of the scale is a second pixel number; and taking the quotient of the second physical size corresponding to the scale and the second pixel number as the first physical size corresponding to a single pixel in the picture to be identified.
The length of the scale is represented by a second number of pixels, which may be, for example, 1, 5, or 10 or other values, and the length of the scale is 1 pixel long, 5 pixels long, 10 pixels long, or other values. The scale position in the image may be, for example, top, bottom, left, bottom, or middle; the scale may be a line segment, a series of dots or a pattern uniformly distributed along a certain direction, or others, all of which are not limited herein.
The scales can be classified according to the type of the picture to be recognized. For example, a picture to be recognized, which is shot by a first instrument, is taken as a picture of a first type, and a picture to be recognized, which is shot by a second instrument, is taken as a picture of a second type; the scales of the first type of picture to be recognized are consistent, the scales of the second type of picture to be recognized are consistent, and the scales of the first type of picture to be recognized and the second type of picture to be recognized are different.
Specifically, in the aspect of determining the scale in the picture to be recognized, the method includes: if the type of the picture to be recognized is a first type, determining a first line segment of which the pixel value is greater than or equal to a first preset threshold and the pixel number is greater than or equal to a second preset threshold in the picture to be recognized, and determining the first line segment as a ruler in the picture to be recognized; if the type of the picture to be recognized is a second type, determining a first rectangle of which the size is larger than or equal to a third preset threshold value and the pixel value is larger than or equal to a fourth preset threshold value in the picture to be recognized; if the first number of the first rectangles is larger than or equal to a fifth preset threshold value and is uniformly distributed along a first direction, determining the first number of the first rectangles as scales in the picture to be identified.
The first preset threshold or the third preset threshold may be, for example, 200, 250, 300, or other values, and the first preset threshold may be equal to or different from the third preset threshold; the second preset threshold or the fourth preset threshold may be, for example, 10, 30, 50, 70, 90, or other values, the second preset threshold may be equal to the fourth preset threshold, or may not be equal to the fourth preset threshold, and the fifth preset threshold may be, for example, 10, 30, 50, 70, 90, or other values, which are not limited herein.
For example, referring to fig. 3 and fig. 4, fig. 3 is a first type of picture to be recognized provided in an embodiment of the present application, and fig. 4 is a second type of picture to be recognized provided in an embodiment of the present application. The scale in fig. 3 is located in the area of the bottom 10% (i.e., height 0.9h to h) of the picture, and is a line segment, the length of which (i.e., the second physical size) is 2 μm, and the line segment is composed of 50 pixels having a pixel value of 250 or more. The first physical dimension in fig. 3 is therefore 40nm. The scale in fig. 4, which is also located in the area at the bottom 10% of the picture (i.e. with a height of 0.9h to h), is 11 small rectangles distributed uniformly in the lateral direction, each of which is composed of 4 × 10 pixels, each having a pixel value greater than or equal to 250. The length of the 11 small rectangles (i.e. the second physical dimension) is 500nm, and if the length of the scale is 100 pixels, the first physical dimension in fig. 4 is 5nm.
Specifically, the boundary includes a left boundary, a right boundary, an upper boundary and a lower boundary, and the first pixel number includes a first sub-pixel number and a second sub-pixel number; in the aspect of determining the first pixel number of the distance between the boundaries of the circuit patterns in the picture to be recognized, the method comprises the following steps: performing normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture; determining a vertical line formed by pixels of which the pixel values are first target values in the intermediate process picture, and determining a horizontal line formed by pixels of which the pixel values are second target values in the intermediate process picture; determining a left boundary and a right boundary based on the vertical lines, and determining an upper boundary and a lower boundary based on the horizontal lines; a first sub-pixel number of a distance between the left and right boundaries is determined, and a second sub-pixel number of a distance between the upper and lower boundaries is determined.
The picture normalization refers to a process of performing a series of standard processing transformations on a picture to transform the picture into a fixed standard form, and the standard picture is called a normalized picture. For example, the normalization can be performed for each pixel according to the following formula:
wherein x is norm,i Normalizing the pixel value, x, of the ith pixel in the picture i And the pixel value before normalization of the ith pixel in the picture is shown, min (x) is the minimum pixel value in the picture, and max (x) is the maximum pixel value in the picture.
The gaussian filtering is a linear smoothing filtering, is suitable for eliminating gaussian noise, and is widely applied to a noise reduction process of image processing. Generally speaking, gaussian filtering is a process of performing weighted average on the whole image, and the value of each pixel is obtained by performing weighted average on the value of each pixel and other pixel values in the neighborhood. The specific operation of gaussian filtering is: each pixel in the image is scanned using a gaussian kernel (or template, convolution, mask), and the value of the template center pixel is replaced by the weighted average of the pixels in the neighborhood determined by the gaussian kernel. The size of the gaussian kernel and may be preset, each element in the gaussian kernel is generated according to a gaussian formula.
The Edge Detection operation may be implemented by corresponding algorithms, such as a canny algorithm, a whole-Nested-Edge Detection (HED) algorithm, and a structure forest Edge Detection (Fast Edge Detection Using Structured forms) algorithm.
In the embodiment of the present application, a canny algorithm is preferred, and the specific implementation steps of the canny algorithm are as follows: denoising a picture to be recognized first, wherein the step can be omitted, and the denoising is performed for one round through Gaussian filtering; then calculating the amplitude and the direction of the pixel gradient of the denoised image to be recognized, and carrying out non-maximum suppression according to the calculated amplitude and direction to obtain target data; then, judging strong edge points, weak edge points and inhibition points by adopting a double-threshold method, judging the strong edge points as the strong edge points if the strong edge points are larger than a high threshold, judging the inhibition points as the inhibition points if the weak edge points are smaller than a low threshold, and judging the weak edge points as the weak edge points if the weak edge points are between the high threshold and the low threshold; and finally, performing lagging edge tracking, reserving the strong edge points, discarding the inhibition points, judging whether the weak edge points are continuous with the strong edge points or not for the weak edge points, discarding the weak edge points when the weak edge points are discontinuous, and reserving the weak edge points when the weak edge points are continuous.
If the intermediate process picture obtained through normalization, gaussian filtering and edge detection operations is not a binarized picture, binarizing the intermediate process picture; and if the intermediate process picture obtained through normalization, gaussian filtering and edge detection operations is a binarized picture, determining a horizontal line and a vertical line according to the binarized picture. The binarized picture pixel value may be, for example, 0 or 1, and a plurality of consecutive pixels having a pixel value of 1 in the horizontal direction may be determined as a horizontal line, or a plurality of consecutive pixels having a pixel value of 0 in the horizontal direction may be determined as a horizontal line; similarly, a plurality of consecutive pixels having a pixel value of 1 in the vertical direction may be determined as vertical lines, or a plurality of consecutive pixels having a pixel value of 0 in the vertical direction may be determined as vertical lines.
The pixel value of the binarized picture may be two other values, and the first target value and the second target value may be one of the two values, and may be equal to or different from each other. Besides the horizontal lines and the vertical lines in the embodiment of the present application, the line patterns may also be oblique lines and curved lines, and the method for identifying the boundaries thereof is the same as the method for identifying the boundaries of the horizontal lines and the vertical lines, which is not described in detail.
Specifically, in the aspect of determining the left boundary and the right boundary based on the vertical line, the method includes:
pairing every two vertical lines to obtain vertical line pairs;
and if a first vertical line pair exists in the vertical line pair, wherein the distance between the vertical lines meets a first preset range, one of the first vertical line pair is used as a left boundary, and the other vertical line pair is used as a right boundary.
Specifically, in the aspect of determining the upper boundary and the lower boundary based on the transverse line, the method includes:
pairing every two transverse lines to obtain a transverse line pair;
and if a first transverse line pair with the distance between the transverse lines meeting a second preset range exists in the transverse line pair, taking one of the first transverse line pair as an upper boundary and the other one as a lower boundary.
The first preset range and the second preset range may be equal or different. If the two horizontal lines or the two vertical lines are not within the first preset range or the second preset range, the two horizontal lines or the two vertical lines can be considered to belong to two boundaries of different line patterns. For example, the first predetermined range or the second predetermined range may be not less than 100nm and not more than 500nm.
Further, the method further comprises: and if no first vertical line pair with the distance between the vertical lines meeting a first preset range exists in the vertical line pair, reducing a detection threshold value in the edge detection operation, and then executing the normalization, gaussian filtering and edge detection operation on the picture to be identified to obtain an intermediate process picture.
If the edge detection operation adopts the canny algorithm, the detection threshold value here includes a high threshold value and a low threshold value, and the high threshold value may be only reduced, or only the low threshold value may be reduced, or both the high threshold value and the low threshold value may be reduced. By lowering the detection threshold, the search range is expanded, and further searching is possible.
Further, the method further comprises: if the first vertical line pair with the distance between the vertical lines meeting a first preset range does not exist in the vertical line pair, reducing the width and the height of a Gaussian kernel in the Gaussian filtering operation, and then executing the normalization, the Gaussian filtering and the edge detection operation on the picture to be identified to obtain an intermediate process picture.
Similarly, the width and height of the Gaussian kernel are reduced, and excessive denoising can be prevented. It should be noted that the above method for reducing the detection threshold in the edge detection operation or reducing the width and height of the gaussian kernel in the gaussian filtering operation may be used only one, or may be used in combination of two. The number of times of reduction is not limited to one, and the first vertical line pair with the distance meeting the first preset range cannot be found and is reduced until the first vertical line pair is found.
It should be further noted that, if there is no first cross line pair in the cross line pair whose distance between the cross lines satisfies a second preset range, the above method for reducing the detection threshold in the edge detection operation and/or reducing the width and height of the gaussian kernel in the gaussian filtering operation may also be used, and then the normalization, gaussian filtering, and edge detection operations are performed on the to-be-identified picture, so as to obtain an intermediate process picture.
Further, after the determining the left boundary and the right boundary based on the vertical line and the determining the upper boundary and the lower boundary based on the horizontal line, the method further comprises: translating the left boundary leftwards by a first preset distance to obtain a new left boundary, translating the right boundary rightwards by a second preset distance to obtain a new right boundary, translating the upper boundary upwards by a third preset distance to obtain a new upper boundary, and translating the lower boundary downwards by a fourth preset distance to obtain a new lower boundary; extending a rectangular frame surrounded by the left boundary, the right boundary, the upper boundary and the lower boundary outwards by a fifth preset distance to obtain a new rectangular frame; and taking the part of the rectangular frame framed and selected on the picture to be identified as a new picture to be identified, and then executing normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture.
The first preset distance, the second preset distance, the third preset distance, the fourth preset distance and the fifth preset distance may be equal or different. The preferred implementation manner of the embodiment of the application is as follows: the first preset distance, the second preset distance, the third preset distance and the fourth preset distance are equal and are all 300nm. The fifth predetermined distance is 20nm. The search area is further refined by readjusting the left, right, upper and lower boundaries and the rectangular frame determined based on the left, right, upper and lower boundaries, so that the determined left, right, upper and lower boundaries are more accurate.
Step 203: and taking the product of the first physical size and the first pixel number as the line width of the circuit pattern in the picture to be identified.
Compared with the prior art, the line width identification method provided by the application takes the product of the first physical dimension corresponding to a single pixel in the picture to be identified and the first pixel number of the distance between the boundaries of the line pattern in the picture to be identified as the line width of the line pattern in the picture to be identified, the pixel is the minimum unit which can not be cut in the picture, and the pixel exists in a small cell with a single color, so that the line width of the line pattern is more accurately determined by taking the pixel as a unit for measuring the length; meanwhile, a machine is adopted to determine the number of pixels, so that manual errors caused by inconsistent quantity of manual statistics can be avoided.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a line width identification apparatus provided in an embodiment of the present application, corresponding to the flow illustrated in fig. 2, the apparatus includes:
an obtaining unit 501, configured to obtain a picture to be identified;
a determining unit 502, configured to determine a first physical size corresponding to a single pixel in the picture to be recognized, and a first pixel number of a distance between boundaries of a line pattern in the picture to be recognized;
the identifying unit 503 is configured to use a product of the first physical size and the first pixel count as a line width of the line pattern in the picture to be identified.
Optionally, in terms of determining the first physical size corresponding to a single pixel in the picture to be recognized, the determining unit 502 is specifically configured to:
determining a scale in the picture to be identified, wherein the length of the scale is the second pixel number;
and taking the quotient of the second physical size corresponding to the scale and the second pixel number as the first physical size corresponding to a single pixel in the picture to be identified.
Optionally, in the aspect of determining the scale in the picture to be recognized, the determining unit 502 is specifically configured to:
if the type of the picture to be recognized is a first type, determining a first line segment of which the pixel value is greater than or equal to a first preset threshold and the pixel number is greater than or equal to a second preset threshold in the picture to be recognized, and determining the first line segment as a ruler in the picture to be recognized;
if the type of the picture to be recognized is a second type, determining a first rectangle of which the size is larger than or equal to a third preset threshold and the pixel value is larger than or equal to a fourth preset threshold in the picture to be recognized; if the first number of the first rectangles is larger than or equal to a fifth preset threshold value and is uniformly distributed along a first direction, determining the first number of the first rectangles as scales in the picture to be identified.
Optionally, the boundary includes a left boundary, a right boundary, an upper boundary, and a lower boundary, and the first pixel number includes a first sub-pixel number and a second sub-pixel number; in the aspect of determining the first pixel number of the distance between the boundaries of the line pattern in the picture to be recognized, the determining unit 502 is specifically configured to:
performing normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture;
determining a vertical line formed by pixels of which the pixel values are first target values in the intermediate process picture, and determining a horizontal line formed by pixels of which the pixel values are second target values in the intermediate process picture;
determining a left boundary and a right boundary based on the vertical lines, and determining an upper boundary and a lower boundary based on the horizontal lines;
a first sub-pixel count of a distance between the left and right boundaries is determined, and a second sub-pixel count of the distance between the upper and lower boundaries is determined.
Optionally, in the aspect of determining the left boundary and the right boundary based on the vertical line, the determining unit 502 is specifically configured to:
pairing every two vertical lines to obtain vertical line pairs;
and if a first vertical line pair exists in the vertical line pair, wherein the distance between the vertical lines meets a first preset range, one of the first vertical line pair is used as a left boundary, and the other vertical line pair is used as a right boundary.
Optionally, in the aspect of determining the upper boundary and the lower boundary based on the horizontal line, the determining unit 502 is specifically configured to:
pairing every two transverse lines to obtain transverse line pairs;
and if a first transverse line pair with the distance between the transverse lines meeting a second preset range exists in the transverse line pair, taking one of the first transverse line pair as an upper boundary and taking the other one as a lower boundary.
Optionally, the determining unit 502 is further configured to:
and if the first vertical line pair with the distance between the vertical lines meeting a first preset range does not exist in the vertical line pair, reducing a detection threshold value in the edge detection operation, and then executing the normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture.
Optionally, the determining unit 502 is further configured to:
if no first vertical line pair with the distance between the vertical lines meeting a first preset range exists in the vertical line pair, reducing the width and the height of a Gaussian kernel in the Gaussian filtering operation, and then executing the normalization, the Gaussian filtering and the edge detection operation on the picture to be recognized to obtain an intermediate process picture.
Optionally, after determining the left boundary and the right boundary based on the vertical line and determining the upper boundary and the lower boundary based on the horizontal line, the determining unit 502 is further configured to:
translating the left boundary leftwards by a first preset distance to obtain a new left boundary, translating the right boundary rightwards by a second preset distance to obtain a new right boundary, translating the upper boundary upwards by a third preset distance to obtain a new upper boundary, and translating the lower boundary downwards by a fourth preset distance to obtain a new lower boundary;
extending a rectangular frame surrounded by the left boundary, the right boundary, the upper boundary and the lower boundary outwards by a fifth preset distance to obtain a new rectangular frame;
and taking the selected part of the rectangular frame on the picture to be identified as a new picture to be identified, and then executing normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture.
Compared with the prior art, the line width recognition device provided by the application takes the product of the first physical dimension corresponding to a single pixel in the picture to be recognized and the first pixel number of the distance between the boundaries of the line pattern in the picture to be recognized as the line width of the line pattern in the picture to be recognized, the pixel is the minimum unit which can not be cut in the picture, and the pixel exists in a small cell with a single color, so that the line width of the line pattern is determined more accurately by taking the pixel as a unit for measuring the length; meanwhile, a machine is adopted to determine the number of pixels, so that manual errors caused by inconsistent quantity of manual statistics can be avoided.
A further embodiment of the invention provides a storage medium having a computer program stored thereon, wherein the computer program is arranged to perform the steps in any of the above method embodiments when executed.
Specifically, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:
acquiring a picture to be identified;
determining a first physical size corresponding to a single pixel in the picture to be recognized and a first pixel number of a distance between boundaries of the circuit pattern in the picture to be recognized;
and taking the product of the first physical size and the first pixel number as the line width of the line pattern in the picture to be identified.
Specifically, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Yet another embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to perform the steps in any one of the above method embodiments.
Specifically, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Specifically, in this embodiment, the processor may be configured to execute the following steps by a computer program:
acquiring a picture to be identified;
determining a first physical size corresponding to a single pixel in the picture to be recognized and a first pixel number of a distance between boundaries of the circuit pattern in the picture to be recognized;
and taking the product of the first physical size and the first pixel number as the line width of the circuit pattern in the picture to be identified.
The construction, features and functions of the present application are described in detail in the embodiments illustrated in the drawings, which are only preferred embodiments of the present application, but the present application is not limited by the drawings, and all equivalent embodiments that can be modified or changed according to the idea of the present application are within the scope of the present application without departing from the spirit of the present application.
Claims (12)
1. A method for line width identification, the method comprising:
acquiring a picture to be identified;
determining a first physical size corresponding to a single pixel in the picture to be recognized and a first pixel number of a distance between boundaries of the circuit pattern in the picture to be recognized;
and taking the product of the first physical size and the first pixel number as the line width of the line pattern in the picture to be identified.
2. The method of claim 1, wherein the determining a first physical size corresponding to a single pixel in the picture to be recognized comprises:
determining a scale in the picture to be identified, wherein the length of the scale is a second pixel number;
and taking the quotient of the second physical size corresponding to the scale and the second pixel number as the first physical size corresponding to a single pixel in the picture to be identified.
3. The method as claimed in claim 2, wherein the determining the scale in the picture to be recognized comprises:
if the type of the picture to be recognized is a first type, determining a first line segment of which the pixel value is greater than or equal to a first preset threshold value and the pixel number is greater than or equal to a second preset threshold value in the picture to be recognized, and determining the first line segment as a scale in the picture to be recognized;
if the type of the picture to be recognized is a second type, determining a first rectangle of which the size is larger than or equal to a third preset threshold and the pixel value is larger than or equal to a fourth preset threshold in the picture to be recognized; if the first number of the first rectangles is larger than or equal to a fifth preset threshold value and is uniformly distributed along a first direction, determining the first number of the first rectangles as scales in the picture to be identified.
4. The method of any of claims 1-3, wherein the boundary comprises a left boundary, a right boundary, an upper boundary, and a lower boundary, the first number of pixels comprises a first number of sub-pixels and a second number of sub-pixels; the determining a first pixel number of a distance between boundaries of the line pattern in the picture to be recognized includes:
performing normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture;
determining a vertical line formed by pixels of which the pixel values are first target values in the intermediate process picture, and determining a horizontal line formed by pixels of which the pixel values are second target values in the intermediate process picture;
determining a left boundary and a right boundary based on the vertical lines, and determining an upper boundary and a lower boundary based on the horizontal lines;
a first sub-pixel count of a distance between the left boundary and the right boundary is determined, and a second sub-pixel count of the distance between the upper boundary and the lower boundary is determined.
5. The method of claim 4, wherein the determining a left boundary and a right boundary based on the vertical line comprises:
pairing every two vertical lines to obtain vertical line pairs;
and if a first vertical line pair exists in the vertical line pair, wherein the distance between the vertical lines meets a first preset range, one of the first vertical line pair is used as a left boundary, and the other vertical line pair is used as a right boundary.
6. The method of claim 4, wherein said determining an upper boundary and a lower boundary based on said cross-line comprises:
pairing every two transverse lines to obtain a transverse line pair;
and if a first transverse line pair with the distance between the transverse lines meeting a second preset range exists in the transverse line pair, taking one of the first transverse line pair as an upper boundary and taking the other one as a lower boundary.
7. The method of claim 5, wherein the method further comprises:
and if the first vertical line pair with the distance between the vertical lines meeting a first preset range does not exist in the vertical line pair, reducing a detection threshold value in the edge detection operation, and then executing the normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture.
8. The method of claim 7, wherein the method further comprises:
if no first vertical line pair with the distance between the vertical lines meeting a first preset range exists in the vertical line pair, reducing the width and the height of a Gaussian kernel in the Gaussian filtering operation, and then executing the normalization, the Gaussian filtering and the edge detection operation on the picture to be recognized to obtain an intermediate process picture.
9. The method of claim 8, wherein after determining the left and right boundaries based on the vertical lines and determining the upper and lower boundaries based on the horizontal lines, the method further comprises:
translating the left boundary leftwards by a first preset distance to obtain a new left boundary, translating the right boundary rightwards by a second preset distance to obtain a new right boundary, translating the upper boundary upwards by a third preset distance to obtain a new upper boundary, and translating the lower boundary downwards by a fourth preset distance to obtain a new lower boundary;
extending a rectangular frame defined by the left boundary, the right boundary, the upper boundary and the lower boundary outwards by a fifth preset distance to obtain a new rectangular frame;
and taking the selected part of the rectangular frame on the picture to be identified as a new picture to be identified, and then executing normalization, gaussian filtering and edge detection operations on the picture to be identified to obtain an intermediate process picture.
10. A line width identifying device, the device comprising:
the acquisition unit is used for acquiring a picture to be identified;
the determining unit is used for determining a first physical size corresponding to a single pixel in the picture to be recognized and a first pixel number of a distance between boundaries of the circuit pattern in the picture to be recognized;
and the identification unit is used for taking the product of the first physical size and the first pixel number as the line width of the line pattern in the picture to be identified.
11. A storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 9 when executed.
12. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110949034.5A CN115908532A (en) | 2021-08-18 | 2021-08-18 | Line width identification method, line width identification device, medium and electronic device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110949034.5A CN115908532A (en) | 2021-08-18 | 2021-08-18 | Line width identification method, line width identification device, medium and electronic device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115908532A true CN115908532A (en) | 2023-04-04 |
Family
ID=86484374
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110949034.5A Pending CN115908532A (en) | 2021-08-18 | 2021-08-18 | Line width identification method, line width identification device, medium and electronic device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115908532A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117179744A (en) * | 2023-08-30 | 2023-12-08 | 武汉星巡智能科技有限公司 | Non-contact infant height measurement method, device, equipment and storage medium |
-
2021
- 2021-08-18 CN CN202110949034.5A patent/CN115908532A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117179744A (en) * | 2023-08-30 | 2023-12-08 | 武汉星巡智能科技有限公司 | Non-contact infant height measurement method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108171104B (en) | Character detection method and device | |
CN108805023B (en) | Image detection method, device, computer equipment and storage medium | |
EA004910B1 (en) | Method and apparatus for determining regions of interest in images and for image transmission | |
CN109977949B (en) | Frame fine adjustment text positioning method and device, computer equipment and storage medium | |
CN112085682B (en) | Image noise reduction method and device, electronic equipment and storage medium | |
US11107202B2 (en) | Contrast enhancement and reduction of noise in images from cameras | |
CN103119609B (en) | A kind of method and apparatus determining video foreground main image area | |
CN113781406B (en) | Scratch detection method and device for electronic component and computer equipment | |
CN110414649B (en) | DM code positioning method, device, terminal and storage medium | |
US8913836B1 (en) | Method and system for correcting projective distortions using eigenpoints | |
US20170178341A1 (en) | Single Parameter Segmentation of Images | |
US20150220804A1 (en) | Image processor with edge selection functionality | |
CN113609984A (en) | Pointer instrument reading identification method and device and electronic equipment | |
CN114494017A (en) | Method, device, equipment and medium for adjusting DPI (deep packet inspection) image according to scale | |
CN111489389A (en) | Light spot center detection method | |
CN111079793A (en) | Icon similarity determining method and electronic equipment | |
US20140003703A1 (en) | Semiconductor circuit pattern measuring apparatus and method | |
CN110084818B (en) | Dynamic down-sampling image segmentation method | |
CN115908532A (en) | Line width identification method, line width identification device, medium and electronic device | |
CN111862040A (en) | Portrait picture quality evaluation method, device, equipment and storage medium | |
CN110751156A (en) | Method, system, device and medium for table line bulk interference removal | |
CN114581331A (en) | Point cloud noise reduction method and device suitable for multiple scenes | |
CN112465707A (en) | Method and device for processing infrared image stripe noise, medium and electronic equipment | |
CN117115774A (en) | Lawn boundary identification method, device, equipment and storage medium | |
US20170352170A1 (en) | Nearsighted camera object detection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 230088 6th floor, E2 building, phase II, innovation industrial park, 2800 innovation Avenue, Hefei high tech Zone, Hefei City, Anhui Province Applicant after: Benyuan Quantum Computing Technology (Hefei) Co.,Ltd. Address before: 230088 6th floor, E2 building, phase II, innovation industrial park, 2800 innovation Avenue, Hefei high tech Zone, Hefei City, Anhui Province Applicant before: ORIGIN QUANTUM COMPUTING COMPANY, LIMITED, HEFEI |
|
CB02 | Change of applicant information |