Cell detection method for semiconductor crystal growth furnace in low-resolution scene

Abstract

The invention discloses a unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scene, and relates to the technical field of semiconductor crystal growth furnaces, and the method comprises the following steps: collecting an original crystal seeding image through a global industrial camera in advance, and calibrating a double-aperture part of the original crystal seeding image as a target feature for cutting, obtaining a target image containing the double-aperture part; respectively and synchronously carrying out hollow detection and unit cell forming detection on the target image; and outputting detection results of hollow detection and unit cell forming detection, and determining whether unit cells are generated in the current seeding stage or not. According to the invention, the state of the unit cell can be more accurately judged, the unit cell can be automatically detected, the labor burden is reduced, and the accuracy, efficiency and reliability of detection are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of semiconductor crystal growth furnaces, and in particular to a unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario. Background Art

[0002] Unit cells are a phenomenon that occurs during the seeding stage. Small crystals similar to the lattice structure grow on the finished crystal. This involves the production process. When unit cells appear, the temperature, pan rotation speed and pulling speed need to be controlled to further control the growth of the crystal. The generation of unit cells is also related to the subsequent formation of crystal columns, so it is necessary to observe the moment when the unit cells appear.

[0003] At present, the crystal cell appears in the seeding stage. At this time, the diameter of the crystal column is very small, about 10 to 20 mm. The traditional manual observation method is that workers use an optical microscope to observe whether the crystal cell appears through the filter of the flange observation port. However, there are the following main disadvantages:

[0004] 1. Limited resolution: The resolution of an optical microscope is limited by the wavelength of light. The resolution limit of a general optical microscope is about 0.2 microns. For a microstructure such as a unit cell, the size of many unit cells is at the nanometer level. For example, the unit cell side length of a common metal crystal may be between a few nanometers and tens of nanometers. In this case, it is difficult for an optical microscope to clearly distinguish the shape and structural details of a single unit cell, which may lead to inaccurate observation results and inability to accurately determine whether the unit cell appears. At the same time, the depth of field of an optical microscope is relatively shallow. If the sample where the unit cell is located has a certain thickness, or the unit cells are distributed at different depth levels, it is difficult to focus on and observe all the unit cells at the same time, which can easily miss the information of some unit cells.

[0005] 2. Limited observation angle: The observation angle is relatively fixed when observing through the flange observation port. This makes it difficult to observe the unit cell from multiple angles. For some unit cells with complex three-dimensional structures, observation from a single angle may not fully understand the true shape and distribution of the unit cell. Just like observing a three-dimensional sculpture, if you only look at it from one direction, you may ignore some important features on the back or side of the sculpture, which will lead to deviations in the judgment of whether the unit cell appears and its state.

[0006] 3. Highly subjective: Visual observation relies on the worker’s vision and experience. Different workers may make different judgments on whether unit cells appear due to differences in vision and perception of unit cell morphology. For example, an inexperienced worker may misjudge some impurities or other microstructures as unit cells, or conversely, ignore some tiny unit cells that have just formed. This highly subjective judgment method is not conducive to accurately and consistently determining the appearance of unit cells.

[0007] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0008] In view of the problems in the related art, the present invention proposes a unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario to overcome the above-mentioned technical problems existing in the existing related art.

[0009] The technical solution of the present invention is achieved in this way:

[0010] A unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario comprises the following steps:

[0011] The crystal seeding original image is collected in advance by a global industrial camera, and the double aperture part of the crystal seeding original image is calibrated as a target feature for cropping to obtain a target image including the double aperture part;

[0012] The target image is subjected to a hollow detection and a cell forming detection respectively and synchronously, wherein: the hollow detection is used to detect whether the current target image is a hollow polygon, and the cell forming detection is used to detect whether the current target image is a plurality of lines;

[0013] Output the detection results of hollow detection and cell forming detection to determine whether a cell is generated in the current seeding stage, including: if the hollow detection output is a hollow polygon and the cell forming detection output is a plurality of lines, it indicates that a cell is generated in the current seeding stage.

[0014] Further, the acquiring of the target image including the dual aperture portion comprises the following steps:

[0015] The target image containing the double aperture part is converted into a binary image.

[0016] Furthermore, hollow detection is performed on the target image, including the following steps:

[0017] Read and process binary images: Load and process the input binary image to ensure that the image contains only two grayscale values: black and white;

[0018] Find contours in the image: Get all external contours through the findContours function, including: Use the cv::findContours function to find all contours in the image;

[0019] Traversing each found contour, including: for each contour, checking whether its point set size is greater than the point set threshold, filtering contours whose point set size is less than the point set threshold, so as to filter out contours that are too small;

[0020] Check the number of corner points of the filtered contour to determine whether the number of points of the contour is greater than the point threshold, and remove the contours with points less than the point threshold;

[0021] Perform convex hull detection on the contour after elimination, calculate the convex hull through the convexHull function, and obtain the minimum convex polygon that can enclose the contour point set;

[0022] Obtaining hollow detection results, including: comparing the number of points of the external contour obtained with the number of points of the convex hull, including the following steps:

[0023] If the number of points of the outer contour is equal to the number of points of the convex hull, it means that the current contour is not a hollow polygon, and the output hollow detection result is no;

[0024] If the number of points of the outer contour is not equal to the number of points of the convex hull, it means that the current contour is a hollow polygon, and the contour containing the hollow polygon is drawn as the hollow detection output, which means that the target image has unit cells.

[0025] Further, the target image is subjected to a cell forming detection, including the following steps:

[0026] Read and process binary images: Load and process the input binary image to ensure that the image contains only two grayscale values: black and white;

[0027] Find contours in the image: Get all external contours through the findContours function, including: Use the cv::findContours function to find all contours in the image;

[0028] Traversing each found contour, including: for each contour, checking whether its point set size is greater than the point set threshold, filtering contours whose point set size is less than the point set threshold, so as to filter out contours that are too small;

[0029] Calculate the perimeter of each contour, including: obtaining the complete length of the contour through the arcLength function,

[0030] Judging whether the contour satisfies the continuous line condition according to the set line threshold, which includes: setting the image segmentation number to segment the contour, and taking the contour perimeter after segmentation greater than the set line threshold as a satisfying line, and obtaining the number of satisfying lines;

[0031] The number of lines that meet the line condition is compared with a preset line threshold to determine whether the current unsegmented contour meets multiple lines, including: if the number of lines that meet the line condition is greater than the line threshold, the current unsegmented contour meets multiple lines.

[0032] Beneficial effects of the present invention:

[0033] The present invention has high detection accuracy and fast detection speed. It collects the original image of crystal seeding through a global industrial camera, and synchronously performs hollow detection and cell forming detection on the target image, outputs the detection results of hollow detection and cell forming detection, and determines whether a cell is generated in the current seeding stage, which helps to more accurately judge the state of the cell, can automatically detect the cell, reduce manual burden, and achieve detection accuracy, efficiency and reliability. At the same time, the present invention is applicable to a wide range of scenarios, and synchronously performs hollow detection and cell forming detection on the target image to identify the state of the cell. It can adapt to low-resolution global industrial cameras, further reduce the production cost of the enterprise, and meet the low-cost production configuration needs of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 is a schematic flow chart of a unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario according to an embodiment of the present invention;

[0036] Figure 2 is a schematic diagram of target image cutting according to a unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario according to an embodiment of the present invention;

[0037] Figure 3 is a schematic diagram of a binary image of a unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario according to an embodiment of the present invention;

[0038] Figure 4 is a schematic diagram of a hollow polygonal scene according to a method for detecting a unit cell of a semiconductor crystal growth furnace in a low-resolution scene according to an embodiment of the present invention;

[0039] Figure 5 It is a schematic diagram of multiple line scenes of a method for detecting a unit cell of a semiconductor crystal growth furnace in a low-resolution scene according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0041] According to an embodiment of the present invention, a unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario is provided.

[0042] like Figure 1 As shown, according to an embodiment of the present invention, a unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario includes the following steps:

[0043] Step S1, pre-collect the original image of crystal seeding by global industrial camera, and cut the double aperture part of the original image of crystal seeding as the target feature to obtain the target image including the double aperture part, such as Figure 2 shown.

[0044] This technical solution, such as Figure 3 As shown, the target image containing the dual aperture portion is converted into a binary image.

[0045] Step S2, performing hollow detection and cell forming detection on the target image simultaneously, wherein: the hollow detection is used to detect whether the current target image is a hollow polygon, and the cell forming detection is used to detect whether the current target image is a plurality of lines;

[0046] The hollow detection of the target image includes the following steps:

[0047] Read and process binary images: Load and process the input binary image to ensure that the image contains only two grayscale values: black (0) and white (255).

[0048] Find contours in the image: Get all external contours through the findContours function, including: Use the cv::findContours function to find all contours in the image.

[0049] Specifically, when applied, the findContours function is a function in OpenCV (a library for computer vision tasks) that is used to find contours in a binary image. The parameter RETR_EXTERNAL specifies that only the external contour is extracted, and CHAIN_APPROX_SIMPLE indicates that the contour is simplified, and redundant points are merged into a line segment.

[0050] Traversing each found contour, including: for each contour, checking whether its point set size is greater than the point set threshold, taking the value 4, filtering contours with point set sizes less than 4, so as to filter out contours that are too small;

[0051] This technical solution, when applied, for a contour in OpenCV, its point set size refers to the number of points contained in the contour, each point is represented by (x, y) coordinates, and for a contour, it is composed of a series of points. By checking whether the number of points contained in the contour is greater than 4, the contour that is too small is filtered out. Make sure the contour is large enough.

[0052] Check the number of corner points of the filtered contour to determine whether the number of points of the contour is greater than the point threshold, take a value of 4, and remove the contours with points less than the point threshold to ensure that there are enough vertices for subsequent analysis.

[0053] Perform convex hull detection on the contour after elimination, calculate the convex hull through the convexHull function, and obtain the minimum convex polygon that can enclose the contour point set.

[0054] Specifically, the convex hull is a polygon whose vertices are composed of the points in the contour, enclosing the entire contour, and any two points are inside the convex hull. The cv::convexHull function in OpenCV is used to calculate the convex hull of a given set of points.

[0055] like Figure 4 As shown, obtaining the hollow detection result, which includes: comparing the number of points of the external contour with the number of points of the convex hull, including the following steps:

[0056] If the number of points of the outer contour is equal to the number of points of the convex hull, it means that the current contour is not a hollow polygon, and the output hollow detection result is no;

[0057] If the number of points of the outer contour is not equal to the number of points of the convex hull, it means that the current contour is a hollow polygon, and the contour containing the hollow polygon is drawn as the hollow detection output, which means that the target image has a unit cell;

[0058] Among them, performing cell forming detection on the target image includes the following steps:

[0059] Read and process binary images: Load and process the input binary image to ensure that the image contains only two grayscale values: black (0) and white (255).

[0060] Find contours in the image: Get all external contours through the findContours function, including: Use the cv::findContours function to find all contours in the image.

[0061] Traversing each found contour, including: for each contour, checking whether its point set size is greater than the point set threshold, taking the value 4, filtering contours with point set sizes less than 4, so as to filter out contours that are too small;

[0062] Calculate the perimeter of each contour, including: obtaining the complete length of the contour through the arcLength function,

[0063] In this technical solution, cv::arclength is a function in the OpenCV library, which is used to calculate the arc length of a curve. The arcLength function returns the complete length of a closed contour, that is, the perimeter of the area enclosed by the contour.

[0064] Judging whether the contour satisfies the continuous line condition according to the set line threshold, which includes: setting the image segmentation number to segment the contour, and taking the contour perimeter after segmentation greater than the set line threshold as a satisfying line, and obtaining the number of satisfying lines;

[0065] Specifically, in application, according to production requirements, the number of image segmentation is set to 9, and the calibration image is 1000x1000 pixel size, that is, each segmented image has 333x333. According to experiments in production, when a halo appears, the length of the lines in the image after binarization and segmentation is generally more than 100, so the line threshold is set to 100 here. When the perimeter is greater than the line threshold of 100, it is considered a line.

[0066] Compare the number of lines that meet the line requirement with the preset line threshold to determine whether the current unsegmented contour meets multiple white continuous lines, including:

[0067] If the number of lines that currently meet the line requirement is greater than the line threshold, the current unsegmented contour meets multiple white continuous lines, indicating that the target image has a unit cell, that is, the target image has a double aperture, such as Figure 5 shown.

[0068] Specifically, according to actual production, the line threshold can be 14. When the number of lines is 14, that is, at least 7 of the 9 segmentation images have two lines, it means that multiple white continuous lines (greater than or equal to 2) are detected in the complete contour (unsegmented contour), indicating that double apertures appear, indicating that the target image has unit cells.

[0069] In addition, for the above-mentioned acquisition of the number of lines that meet the conditions, when applied, if the contour meets the conditions, the line count is increased, and at the same time, it is determined whether there are any unchecked contours.

[0070] Step S3, output the detection results of hollow detection and cell forming detection, and determine whether a cell is generated in the current crystal seeding stage, which includes: if the hollow detection output is a hollow polygon and the cell forming detection output is multiple lines, it means that a cell is generated in the current crystal seeding stage.

[0071] In the present technical solution, when the hollow detection output is a hollow polygon and the unit cell forming detection output is a plurality of lines, the unit cell is determined to exist; otherwise, the unit cell cannot be determined to exist.

[0072] In summary, with the help of the above technical solution of the present invention, the following benefits can be achieved:

[0073] The present invention has high detection accuracy and fast detection speed. It collects the original image of crystal seeding through a global industrial camera, and synchronously performs hollow detection and cell forming detection on the target image, outputs the detection results of hollow detection and cell forming detection, and determines whether a cell is generated in the current seeding stage, which helps to more accurately judge the state of the cell, can automatically detect the cell, reduce manual burden, and achieve detection accuracy, efficiency and reliability. At the same time, the present invention is applicable to a wide range of scenarios, and synchronously performs hollow detection and cell forming detection on the target image to identify the state of the cell. It can adapt to low-resolution global industrial cameras, further reduce the production cost of the enterprise, and meet the low-cost production configuration needs of the enterprise.

[0074] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. After considering the disclosure of the specification and the examples, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and the examples are only regarded as exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

[0075] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario, characterized in that: The following steps are involved: The crystal seeding original image is collected in advance by a global industrial camera, and the double aperture part of the crystal seeding original image is calibrated as a target feature for cropping to obtain a target image including the double aperture part; The target image is subjected to a hollow detection and a cell forming detection respectively and synchronously, wherein: the hollow detection is used to detect whether the current target image is a hollow polygon, and the cell forming detection is used to detect whether the current target image is a plurality of lines; Output the detection results of hollow detection and cell forming detection to determine whether a cell is generated in the current seeding stage, including: if the hollow detection output is a hollow polygon and the cell forming detection output is a plurality of lines, it indicates that a cell is generated in the current seeding stage.

2. The unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario according to claim 1, characterized in that: The step of acquiring the target image including the dual aperture portion comprises the following steps: The target image containing the double aperture part is converted into a binary image.

3. The unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario according to claim 2, characterized in that: Hollow detection of the target image includes the following steps: Read and process binary images: Load and process the input binary image to ensure that the image contains only two grayscale values: black and white; Find contours in the image: Get all external contours through the findContours function, including: Use the cv::findContours function to find all contours in the image; Traversing each found contour, including: for each contour, checking whether its point set size is greater than the point set threshold, filtering contours whose point set size is less than the point set threshold, so as to filter out contours that are too small; Check the number of corner points of the filtered contour to determine whether the number of points of the contour is greater than the point threshold, and remove the contours with points less than the point threshold; Perform convex hull detection on the contour after elimination, calculate the convex hull through the convexHull function, and obtain the minimum convex polygon that can enclose the contour point set; Obtaining hollow detection results, including: comparing the number of points of the external contour obtained with the number of points of the convex hull, including the following steps: If the number of points of the outer contour is equal to the number of points of the convex hull, it means that the current contour is not a hollow polygon, and the output hollow detection result is no; If the number of points of the outer contour is not equal to the number of points of the convex hull, it means that the current contour is a hollow polygon, and the contour containing the hollow polygon is drawn as the hollow detection output, which means that the target image has unit cells.

4. The unit cell detection method for a semiconductor crystal growth furnace in a low-resolution scenario according to claim 2, characterized in that: Performing cell forming detection on the target image includes the following steps: Read and process binary images: Load and process the input binary image to ensure that the image contains only two grayscale values: black and white; Find contours in the image: Get all external contours through the findContours function, including: Use the cv::findContours function to find all contours in the image; Traversing each found contour, including: for each contour, checking whether its point set size is greater than the point set threshold, filtering contours whose point set size is less than the point set threshold, so as to filter out contours that are too small; Calculate the perimeter of each contour, including: obtaining the complete length of the contour through the arcLength function, Judging whether the contour satisfies the continuous line condition according to the set line threshold, which includes: setting the image segmentation number to segment the contour, and taking the contour perimeter after segmentation greater than the set line threshold as a satisfying line, and obtaining the number of satisfying lines; The number of lines that meet the line condition is compared with a preset line threshold to determine whether the current unsegmented contour meets multiple lines, including: if the number of lines that meet the line condition is greater than the line threshold, the current unsegmented contour meets multiple lines.

Images