Geometric position-based abnormal droplet determination method, system, and electronic device

Abstract

The application provides a geometric position-based abnormal droplet determination method and system and electronic equipment, and relates to the field of droplet identification. First, a chip support column image and a to-be-determined image are determined. The chip support column image includes a first support column region, and the to-be-determined image includes a plurality of to-be-determined droplets. Then, the chip support column image and the to-be-determined image are matched. The first support column region is projected into the to-be-determined image to obtain a second support column region corresponding to the to-be-determined image. Finally, the to-be-determined droplets with a distance less than a preset threshold from the second support column region are determined as abnormal droplets. The method uses the chip support column image and the to-be-determined image for registration and marks the position of the chip support column, and determines the droplets around the support column as abnormal droplets, thereby avoiding the misjudgment of free droplets outside the support column as abnormal droplets, and solving the problem of poor droplet identification accuracy caused by the misjudgment of free droplets in the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of microdroplet recognition, and in particular to a geometric position-based abnormal microdroplet determination method and system and electronic device. BACKGROUND

[0002] Digital PCR (Polymerase Chain Reaction, PCR) is a nucleic acid molecule absolute quantification technology, which mainly adopts microfluidic or microdroplet method to disperse a large amount of diluted nucleic acid solution into micro-reaction chambers or microdroplets of a chip, and the number of nucleic acid templates in each micro-reaction chamber or microdroplet is not more than 1. After PCR cycle, the micro-reaction chamber or microdroplet with one nucleic acid molecule template will emit a fluorescence signal, and the micro-reaction chamber or microdroplet without nucleic acid molecule template will not emit a fluorescence signal. Therefore, how to quickly and accurately identify the positive point microdroplet in the fluorescence image is very important to ensure the accuracy of detection.

[0003] In the prior art, when determining the effectiveness of the microdroplets, the chip support column region usually does not contain microdroplets, so in the actual scene, the region without microdroplets in a larger range is usually marked as a support column region, and the microdroplets around the region are determined as abnormal microdroplets. However, this method may also misjudge the free microdroplets in the chip as abnormal microdroplets, resulting in a decrease in the number of effective microdroplets and affecting the recognition accuracy of the microdroplets. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a geometric position-based abnormal microdroplet determination method and system and electronic device, which registers the chip support column image and the image to be determined, marks the position of the chip support column in the image to be determined, and then determines the microdroplets around the support column as abnormal microdroplets, thereby avoiding misjudging the free microdroplets in the region outside the support column as abnormal microdroplets, and solving the problem of poor microdroplet recognition accuracy caused by misjudgment of free microdroplets in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a geometric position-based abnormal microdroplet determination method, which comprises:

[0006] determining a chip support column image and an image to be determined; wherein the chip support column image comprises a first support column region; and the image to be determined comprises a plurality of microdroplets to be determined;

[0007] performing image matching on the chip support column image and the image to be determined;

[0008] projecting the first support column region in the chip support column image to the image to be determined to obtain a second support column region corresponding to the image to be determined;

[0009] The microdroplet to be judged is determined as an abnormal microdroplet if the distance between the microdroplet to be judged and the second support column region is less than a preset threshold.

[0010] In some embodiments, the image matching of the chip support column image and the image to be judged comprises:

[0011] The first support column contained in the first support column region in the chip support column image is acquired.

[0012] The second support column corresponding to the first support column is determined from the image to be judged.

[0013] A scaling factor is determined by using the size data of the first support column and the second support column.

[0014] The chip support column image and the image to be judged are image size matched based on the scaling factor.

[0015] In some embodiments, the step of image matching of the chip support column image and the image to be judged comprises:

[0016] The first support column contained in the first support column region in the chip support column image is acquired.

[0017] The second support column corresponding to the first support column is determined from the image to be judged.

[0018] An angle transformation factor is determined by using the position data of the first support column and the second support column.

[0019] The chip support column image and the image to be judged are image angle matched based on the angle transformation factor.

[0020] In some embodiments, the step of determining the angle transformation factor by using the position data of the first support column and the second support column comprises:

[0021] According to the position data of the first support column and the second support column, it is determined whether the first support column and the second support column are in the same plane.

[0022] If not, a rotation transformation factor and a first translation transformation factor between the first support column and the second support column are determined; wherein the rotation transformation factor is used to rotate the chip support column image and the image to be judged to the same plane; and the first translation transformation factor is used to translate the chip support column image and the image to be judged to the same position.

[0023] The rotation transformation factor and the first translation transformation factor are determined as the angle transformation factor.

[0024] In some embodiments, the step of determining the angle transformation factor by using the position data of the first support column and the second support column comprises:

[0025] determining whether the first support column and the second support column are in the same plane according to the position data of the first support column and the second support column;

[0026] If yes, determining a second translation transformation factor between the first support column and the second support column; wherein the second translation transformation factor is used to translate the chip support column image and the image to be determined to the same position;

[0027] determining the second translation transformation factor as the angle transformation factor.

[0028] In some embodiments, the step of projecting the first support column region in the chip support column image into the image to be determined to obtain the second support column region corresponding to the image to be determined includes:

[0029] superimposing the chip support column image and the image to be determined, and translating the chip support column image on the image to be determined according to a preset step length;

[0030] traversing all the translation transformations, and calculating the sum of pixel values of the first support column region and the superimposed region corresponding to the image to be determined in all the translation transformations;

[0031] selecting the translation transformation with the smallest sum of pixel values, and projecting the first support column region into the image to be determined according to the translation transformation to obtain the second support column region.

[0032] In some embodiments, before superimposing the support column image and the image to be determined, the method further includes:

[0033] performing binaryzation processing on the chip support column image;

[0034] determining whether the pixel value of the first support column region in the chip support column image is 0;

[0035] If no, performing inversion processing on the chip support column image.

[0036] In a second aspect, an embodiment of the present application provides an abnormal microdroplet determination system based on geometric position, which comprises:

[0037] an initialization module configured to determine a chip support column image and an image to be determined; wherein the chip support column image comprises a first support column region; and the image to be determined comprises a plurality of microdroplets to be determined;

[0038] an image matching module configured to perform image matching on the chip support column image and the image to be determined;

[0039] an image projection module configured to project the first support column region in the chip support column image into the image to be determined to obtain a second support column region corresponding to the image to be determined;

[0040] The determination execution module is configured to determine the droplet to be determined as an abnormal droplet if the distance between the second support column region and the droplet to be determined is less than a preset threshold.

[0041] In a third aspect, an electronic device is provided, which comprises a processor and a memory, and the memory stores a computer program which, when executed by the processor, implements the steps of the abnormal droplet determination method based on geometric positions mentioned in the first aspect.

[0042] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the abnormal droplet determination method based on geometric positions mentioned in the first aspect.

[0043] The embodiments of the present application have the following beneficial effects:

[0044] The present application provides an abnormal droplet determination method and system based on geometric positions and an electronic device. In the process of determining abnormal droplets, a chip support column image and a to-be-determined image are first determined. The chip support column image includes a first support column region, and the to-be-determined image includes a plurality of to-be-determined droplets. Then, the chip support column image and the to-be-determined image are matched. The first support column region in the chip support column image is projected into the to-be-determined image to obtain a second support column region corresponding to the to-be-determined image. Finally, the to-be-determined droplets with a distance less than a preset threshold from the second support column region are determined as abnormal droplets. This method uses the chip support column image and the to-be-determined image for registration, marks the position of the chip support column in the to-be-determined image, and then determines the droplets around the support column as abnormal droplets, thereby avoiding the misjudgment of free droplets outside the support column as abnormal droplets, and solving the problem of poor droplet recognition accuracy caused by misjudgment of free droplets in the prior art.

[0045] Other features and advantages of the present application will be illustrated in the following description, or can be known or determined without any doubt from the description, or can be known by implementing the above-mentioned technologies of the present application.

[0046] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described in detail below, and the accompanying drawings are referred to. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor based on these drawings.

[0048] Figure 1 A flow chart of a geometric position-based abnormal microdroplet determination method provided for an embodiment of the present application;

[0049] Figure 2 A flow chart of image matching of a chip support column image and a to-be-determined image using a scaling factor provided for an embodiment of the present application;

[0050] Figure 3 A flow chart of image matching of a chip support column image and a to-be-determined image using an angle transformation factor provided for an embodiment of the present application;

[0051] Figure 4 A flow chart of determining an angle transformation factor using position data of a first support column and a second support column provided for an embodiment of the present application;

[0052] Figure 5 A flow chart of another method of determining an angle transformation factor using position data of a first support column and a second support column provided for an embodiment of the present application;

[0053] Figure 6 A flow chart of projecting a first support column region in a chip support column image to a to-be-determined image to obtain a second support column region corresponding to the to-be-determined image provided for an embodiment of the present application;

[0054] Figure 7 A flow chart of a geometric position-based abnormal microdroplet determination method provided for an embodiment of the present application, before superimposing a support column image and a to-be-determined image;

[0055] Figure 8 An effect diagram of a chip support column image provided for an embodiment of the present application;

[0056] Figure 9 An effect diagram of a to-be-determined image provided for an embodiment of the present application;

[0057] Figure 10 An effect diagram of a to-be-determined image containing a support column region provided for an embodiment of the present application;

[0058] Figure 11 A structural schematic diagram of a geometric position-based abnormal microdroplet determination method system provided for an embodiment of the present application;

[0059] Figure 12 A structural schematic diagram of an electronic device provided by an embodiment of the present application.

[0060] Icon:

[0061] 1110 - initialization module; 1120 - image matching module; 1130 - image projection module; 1140 - determination execution module;

[0062] 101 - processor; 102 - memory; 103 - bus; 104 - communication interface. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the present application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0064] Digital PCR (Polymerase Chain Reaction, PCR) is a nucleic acid absolute quantification technology. Digital PCR is a nucleic acid quantification method based on single molecule PCR counting, which mainly uses microfluidic or microdroplet methods to disperse a large amount of diluted nucleic acid solution into micro-reaction chambers or microdroplets of a chip, and the number of nucleic acid templates in each micro-reaction chamber or microdroplet is not more than 1. After PCR cycles, a micro-reaction chamber or microdroplet with a nucleic acid molecule template will emit a fluorescence signal, and a micro-reaction chamber or microdroplet without a nucleic acid molecule template will not emit a fluorescence signal. Therefore, how to quickly and accurately identify the positive point microdroplets in the fluorescence image is very important to ensure the accuracy of detection.

[0065] In the prior art, when determining the effectiveness of the microdroplets, the chip support column region usually does not contain microdroplets, so in actual scenarios, a region without microdroplets in a larger range is usually marked as a support column region, and the microdroplets around the region are determined as abnormal microdroplets. However, this method also misjudges the free microdroplets in the chip as abnormal microdroplets, resulting in a decrease in the number of effective microdroplets and affecting the recognition accuracy of the microdroplets. Based on this, the embodiments of the present application provide a geometric position-based abnormal microdroplet determination method and system and an electronic device. By using the chip support column image and the image to be determined for registration, the positions of the chip support columns in the image to be determined are marked, and then the microdroplets around the support columns are determined as abnormal microdroplets, so that the free microdroplets in the region outside the support columns are avoided from being misjudged as abnormal microdroplets, and the problem of poor microdroplet recognition accuracy caused by misjudgment of free microdroplets in the prior art is solved.

[0066] For the convenience of understanding the present embodiment, first, a kind of geometric position-based abnormal micro droplet determination method disclosed in the present embodiment is introduced in detail, specifically, the method as shown in Figure 1 As shown in

[0067] Step S101, determine chip support column image and image to be determined;Wherein, chip support column image includes first support column region;Image to be determined includes a plurality of micro droplets to be determined.

[0068] Image to be determined is digital PCR (Polymerase Chain Reaction, Polymerase Chain Reaction) image, and a plurality of micro droplets are contained in PCR image, and a micro-reaction chamber or micro droplet with a nucleic acid molecule template will emit a fluorescent signal, and the micro-reaction chamber or micro droplet without nucleic acid molecule template will not emit fluorescent signal.Therefore, how to quickly and accurately identify positive points in PCR image is very important to ensure the accuracy of detection.

[0069] In actual detection, image to be determined is obtained by shooting the chip containing micro droplets, and relevant support column is contained in the chip to support the relevant structural components of the chip.In simple terms, chip can be understood as a container, which contains a plurality of micro droplets, including micro droplets to be determined.The support column in the chip is used to support the container, and its structure is usually fixed and unchangeable.Therefore, the image of the support column can be obtained by its corresponding engineering image and data, or can be obtained directly by shooting.

[0070] Step S102, image matching is carried out between chip support column image and image to be determined.

[0071] Since the acquisition approach of chip support column image and the acquisition approach of image to be determined are not necessarily the same, the two need to be matched for subsequent determination of abnormal micro droplets.The implementation process of image matching can be realized by related matching algorithm of digital image processing, or chip support column image and image to be determined can be processed by related translation, rotation, mirror image, etc.

[0072] Step S103, project the first support column region in the chip support column image into the image to be determined, to obtain the second support column region corresponding to the image to be determined.

[0073] Generally, after image matching, the size of chip support column image and image to be determined can be ensured in the same plane, or completely the same.At this time, the first support column region in the chip support column image can be projected into the image to be determined, so that the second support column region corresponding to the support column in the image to be determined is marked.

[0074] Step S104: Determine droplets whose distance from the second support column region is less than a preset threshold as abnormal droplets.

[0075] The second support pillar area is the actual support pillar area of ​​the chip. The reason for projecting the chip support pillar image is that the image of the second support pillar area in the image to be judged may be very similar to the ambient light during the illumination and imaging process, and directly using the image to be judged would result in a large error. By projecting the first support pillar area in the chip support pillar image onto the image to be judged, the support pillars in the image to be judged are determined, thereby avoiding the misjudgment of free droplets outside the support pillars as abnormal droplets, and solving the problem of poor droplet recognition accuracy caused by misjudgment of free droplets in the existing technology.

[0076] As can be seen from the description in the above embodiments, image matching plays a crucial role in the processing of the chip support pillar image and the image to be determined. In some embodiments, the step S102 of performing image matching between the chip support pillar image and the image to be determined is as follows: Figure 2 As shown, it includes:

[0077] Step S201: Obtain the first support pillar contained in the first support pillar region of the chip support pillar image.

[0078] In the chip support pillar image, the first support pillar region contains various types of support pillars, whose cross-sections are usually circular, and some are rounded rectangles. Select one of these support pillars and designate it as the first support pillar.

[0079] Step S202: Determine the second support column corresponding to the first support column from the image to be determined.

[0080] Since the same support column is used, the second support column corresponding to the first support column can be directly identified from the image to be judged. Specifically, it can be found by using the corresponding shape and position parameters.

[0081] Step S203: Determine the scaling factor using the size data of the first support column and the second support column.

[0082] After obtaining the first and second support columns, their scaling factors are calculated based on their dimensions. Generally, the scaling factor is the ratio of their dimensions, but it can also be obtained through the ratio of their areas.

[0083] Step S204: Match the chip support pillar image with the image to be judged based on the scaling factor.

[0084] After the scaling factor is determined, the chip support pillar image and the image to be judged are size matched to ensure that they are consistent.

[0085] The scaling factor in the above embodiment is determined by the size parameter, and in an actual scene, the scaling factor also needs to include the related angle parameter. In some embodiments, the step S102 of performing image matching between the chip support column image and the image to be judged, as shown in Figure 3 includes the following steps:

[0086] In step S301, a first support column contained in a first support column region in the chip support column image is obtained.

[0087] Similarly, in the chip support column image, the first support column region contains various types of support columns, and the cross section is usually circular or round rectangular. The support column is selected and used as the first support column.

[0088] In step S302, a second support column corresponding to the first support column is determined from the image to be judged.

[0089] Similarly, since the same support column is used, the second support column corresponding to the first support column can be directly determined from the image to be judged. Specifically, the corresponding shape and position parameters can be used to find and obtain.

[0090] In step S303, an angle transformation factor is determined using the position data of the first support column and the second support column.

[0091] After the first support column and the second support column are obtained, the scaling factor of the two is calculated according to their shapes and positions. Generally, the scaling factor is the related rotation angle of the two, and it can also be measured by the related projection of the two.

[0092] In step S304, the chip support column image and the image to be judged are image angle matched based on the angle transformation factor.

[0093] After the scaling factor is determined, the chip support column image and the image to be judged are size matched to keep them consistent.

[0094] In the process of determining the angle transformation factor using the position data of the first support column and the second support column, the first support column and the second support column need to be finally matched through related matching transformation, which includes rigid body matching, and is composed of rotation transformation and translation transformation. Specifically, in some embodiments, the step S303 of determining the angle transformation factor using the position data of the first support column and the second support column, as shown in Figure 4 includes the following steps:

[0095] In step S401, whether the first support column and the second support column are in the same plane is judged according to the position data of the first support column and the second support column.

[0096] Step S402, if no, determining a rotation transformation factor and a first translation transformation factor between the first support column and the second support column; wherein the rotation transformation factor is used to rotate the chip support column image and the image to be judged to the same plane; and the first translation transformation factor is used to translate the chip support column image and the image to be judged to the same position.

[0097] Step S403, determining the rotation transformation factor and the first translation transformation factor as the angle transformation factor.

[0098] Generally, the premise of the rotation transformation is that the first support column and the second support column are not in the same plane, and at this time, the rotation transformation is needed to keep them in the same plane, and thus the rotation transformation factor can be calculated according to the position data of the first support column and the second support column.

[0099] After the transformation, the first support column and the second support column are in the same plane, and at this time, the translation transformation is needed to match them. Thus the first translation transformation factor can be calculated according to the position data of the first support column and the second support column, and finally the rotation transformation factor and the first translation transformation factor are determined as the angle transformation factor.

[0100] In some scenarios, the first support column and the second support column are in the same plane, and at this time, in some embodiments, the step S303 of determining the angle transformation factor by using the position data of the first support column and the second support column, as shown in Figure 5 , includes:

[0101] Step S501, determining whether the first support column and the second support column are in the same plane according to the position data of the first support column and the second support column;

[0102] Step S502, if yes, determining a second translation transformation factor between the first support column and the second support column; wherein the second translation transformation factor is used to translate the chip support column image and the image to be judged to the same position;

[0103] Step S503, determining the second translation transformation factor as the angle transformation factor.

[0104] The first support column and the second support column are found to be in the same plane after being obtained, and thus in the process of determining the angle transformation factor, the related rotation transformation process can no longer be considered, and the second translation transformation factor is directly determined by using the position data of the first support column and the second support column, and finally the second translation transformation factor is determined as the angle transformation factor.

[0105] After image matching, the size of the chip support column image and the to-be-judged image can be ensured to be in the same plane, or completely the same. At this time, the first support column region in the chip support column image can be projected into the to-be-judged image, so that the second support column region corresponding to the support column in the to-be-judged image is marked. In the specific implementation process, the two can be directly superimposed, but the direction of the two cannot be guaranteed to remain consistent, so in the actual scene, the two can also be superimposed by using the translation superposition method. Therefore, in some embodiments, the step of projecting the first support column region in the chip support column image into the to-be-judged image to obtain the second support column region corresponding to the to-be-judged image, as shown in Figure 6 , includes:

[0106] In step S601, the chip support column image is superimposed with the to-be-judged image, and the chip support column image is translated on the to-be-judged image according to a preset step length.

[0107] The support column image and the to-be-judged image are superimposed from one direction, and are translated according to a preset step length until all possible translation transformations of the two are completed.

[0108] In step S602, all translation transformations are traversed, and the sum of pixel values of the first support column region and the superimposed region corresponding to the to-be-judged image in all translation transformations is calculated.

[0109] All translation transformations are traversed, and the sum of pixel values of the first support column region and the superimposed region corresponding to the to-be-judged image in all translation transformations is calculated. Since the image brightness of the support column position in the to-be-judged image is relatively low, the pixel values of the two after superimposing the first support column region are the smallest, so the translation transformation process can be determined according to this determination condition.

[0110] In step S603, the translation transformation with the smallest sum of pixel values is selected, and the first support column region is projected into the to-be-judged image according to the translation transformation to obtain the second support column region.

[0111] There is a premise in the process of obtaining the second support column region by such a method, that is, the pixel value of the support column position in the to-be-judged image is the lowest, so it is necessary to process the to-be-judged image to ensure that the pixel value of the support column region is 0. In some embodiments, before the chip support column image is superimposed with the to-be-judged image, as shown in Figure 7 , the method further includes:

[0112] In step S701, the chip support column image is binarized.

[0113] After the binarization processing, the target pixel value of the first support column region in the chip support column image is 0, and the pixel value of other regions is 255. However, in the actual scene, it cannot be guaranteed that the pixel value of the first support column region is 0, and it needs to be determined.

[0114] Step S702, judging whether the pixel value of the first support column region in the chip support column image is 0;

[0115] Step S703, if not, performing the NOT operation on the chip support column image.

[0116] Because in some scenes, the binarization result obtained may be reversed, that is, the pixel value of the first support column region is 255, and the pixel value of other regions is 0, in this case, the NOT operation needs to be performed on the chip support column image.

[0117] In the process of determining the abnormal microdroplets, the chip support column image and the image to be determined obtained after step S101 are respectively as Figure 8 As Figure 9 It can be seen from Figure 8 that the support column in the chip support column image is a white region; the pixel value in the corresponding support column region of the image to be determined is also relatively low, but since other environmental colors are close to the support region, if the image to be determined is directly used to determine the abnormal microdroplets, a large error will be generated. Figure 9

[0118] In the image matching process of the chip support column image and the image to be determined, this process can be divided into two steps, first, the scaling factor of the chip support column image and the image to be determined is determined through the size of the support column, so as to match in unification; finally, the matching transformation of the two images is determined through the positions of all the support columns (the two images can be matched through a rigid body transformation, which is composed of a rotation transformation and a translation transformation, but the directions of the two images are basically the same, and the transformation can be approximated through a translation transformation).

[0119] Then, the first support column region in the chip support column image is projected into the image to be determined, and the second support column region corresponding to the image to be determined is obtained. It can be seen from Figure 9 that the brightness of the support column position in the image to be determined is obviously lower than that of the microdroplet region, so all possible translation transformations can be traversed, and the sum of all pixel values corresponding to the support column position is calculated as the evaluation index of the current transformation, and the transformation corresponding to the minimum sum of pixel values in the index is selected as the matching transformation of the two images, and the second support column region is projected in the image to be determined, as shown in Figure 10 .

[0120] ​Finally, the to-be-judged microdroplet with a distance to the second support column region in the to-be-judged image less than the preset threshold is determined as an abnormal microdroplet.

[0121] It can be known from the above-mentioned abnormal microdroplet judgment method based on geometric positions in the embodiments that, by using the chip support column image and the to-be-judged image for registration, marking the positions of the chip support columns in the to-be-judged image, and determining the microdroplets around the support columns as abnormal microdroplets, the method avoids misjudging the free microdroplets in the region outside the support columns as abnormal microdroplets, and solves the problem of poor microdroplet recognition accuracy caused by misjudgment of free microdroplets in the prior art.

[0122] Corresponding to the above-mentioned abnormal microdroplet judgment method based on geometric positions, the embodiments of the present application provide an abnormal microdroplet judgment system based on geometric positions, as shown in Figure 11 The system comprises:

[0123] The initialization module 1110 is configured to determine a chip support column image and a to-be-judged image; wherein the chip support column image comprises a first support column region; and the to-be-judged image comprises a plurality of to-be-judged microdroplets.

[0124] The image matching module 1120 is configured to perform image matching on the chip support column image and the to-be-judged image.

[0125] The image projection module 1130 is configured to project the first support column region in the chip support column image into the to-be-judged image to obtain a second support column region corresponding to the to-be-judged image.

[0126] The judgment execution module 1140 is configured to determine the to-be-judged microdroplet with a distance to the second support column region less than a preset threshold as an abnormal microdroplet.

[0127] In some embodiments, the image matching module 1120 is further configured to: acquire a first support column contained in the first support column region in the chip support column image; determine a second support column corresponding to the first support column from the to-be-judged image; determine a scaling factor by using size data of the first support column and the second support column; and perform image size matching on the chip support column image and the to-be-judged image based on the scaling factor.

[0128] In some embodiments, the image matching module 1120 is further configured to: acquire a first support column contained in the first support column region in the chip support column image; determine a second support column corresponding to the first support column from the to-be-judged image; determine an angle transformation factor by using position data of the first support column and the second support column; and perform image angle matching on the chip support column image and the to-be-judged image based on the angle transformation factor.

[0129] In some embodiments, the image matching module 1120, in the process of determining the angle transformation factor using the position data of the first support column and the second support column, is further configured to: determine, according to the position data of the first support column and the second support column, whether the first support column and the second support column are in the same plane; if not, determine a rotation transformation factor and a first translation transformation factor between the first support column and the second support column; wherein the rotation transformation factor is used to rotate the chip support column image and the image to be determined to the same plane, and the first translation transformation factor is used to translate the chip support column image and the image to be determined to the same position; and determine the rotation transformation factor and the first translation transformation factor as the angle transformation factor.

[0130] In some embodiments, the image matching module 1120, in the process of determining the angle transformation factor using the position data of the first support column and the second support column, is further configured to: determine, according to the position data of the first support column and the second support column, whether the first support column and the second support column are in the same plane; if yes, determine a second translation transformation factor between the first support column and the second support column; wherein the second translation transformation factor is used to translate the chip support column image and the image to be determined to the same position; and determine the second translation transformation factor as the angle transformation factor.

[0131] In some embodiments, the image projection module 1130 is further configured to: superimpose the support column image and the image to be determined, and perform a translation transformation on the support column image on the image to be determined according to a preset step size; traverse all translation transformations, and calculate the sum of pixel values of the superimposed region corresponding to the first support column region in the image to be determined in all translation transformations; select a translation transformation with the smallest sum of pixel values, and project the first support column region to the image to be determined according to the translation transformation to obtain a second support column region.

[0132] In some embodiments, before superimposing the support column image and the image to be determined, the image projection module 1130 is further configured to: perform a binaryzation processing on the support column image; determine whether the pixel value of the first support column region in the chip support column image is 0; and if not, perform an inversion processing on the support column image.

[0133] It can be known from the above-mentioned abnormal microdroplet determination system based on geometric position that the system determines the effectiveness of the microdroplet by using the half-peak parameters of the gray scale distribution curves of the microdroplet to be determined in multiple directions, reduces the influence of image noise on the determination of the effectiveness of the microdroplet, and improves the accuracy of the determination of the microdroplet.

[0134] The abnormal microdroplet judgment system based on geometric position provided by the embodiments of the present application has the same technical features as the abnormal microdroplet judgment method based on geometric position provided by the above embodiments, and can solve the same technical problems and achieve the same technical effects. For brevity, the part of the embodiments not mentioned can refer to the corresponding content in the above embodiments.

[0135] The present embodiment also provides an electronic device, and a schematic structural diagram of the electronic device is shown in FIG. 10. Figure 12 As shown in FIG. 10, the device includes a processor 101 and a memory 102; wherein the memory 102 is configured to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the steps of the above abnormal microdroplet judgment method based on geometric position.

[0136] Figure 12 As shown in FIG. 10, the electronic device also includes a bus 103 and a communication interface 104, and the processor 101, the communication interface 104 and the memory 102 are connected through the bus 103.

[0137] The memory 102 can include a high-speed random access memory (RAM), and can also include a non-volatile memory, for example, at least one disk memory. The bus 103 can be an ISA bus, a PCI bus or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 12 only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0138] The communication interface 104 is configured to connect with at least one user terminal and other network units through a network interface, and send the encapsulated IPv4 packet or IPv4 packet to the user terminal through the network interface.

[0139] The processor 101 can be an integrated circuit chip having a processing capability of signals. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the processor 101 or the instruction in the form of software. The processor 101 described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. Each method, step and logic block diagram disclosed in the embodiment of the present disclosure can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiment of the present disclosure can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory or an electrically erasable programmable memory, a register or other mature storage medium in the art. The storage medium is located in the memory 102, and the processor 101 reads the information in the memory 102, and combines the hardware to complete the steps of the method of the above embodiment.

[0140] The embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program is run by a processor, the steps of the method of the above embodiment are executed.

[0141] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented by other ways. The above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and other division manners can be used in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0142] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0143] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0144] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various program code storage media.

[0145] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the present application, used to illustrate the technical solutions of the present application, and not to limit them, the protection scope of the present application is not limited thereto, although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand: any skilled person in the art within the technical range disclosed by the present application, they can still modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and all should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for determining anomalous droplets based on geometric location, characterized in that, The method comprises: determining a chip support column image and a to-be-judged image; wherein the chip support column image comprises a first support column region; the to-be-judged image comprises a plurality of to-be-judged microdroplets; image matching the chip support column image and the to-be-judged image; projecting the first support column region in the chip support column image into the to-be-judged image to obtain a second support column region corresponding to the to-be-judged image; judging the to-be-judged microdroplets with a distance less than a preset threshold from the second support column region as abnormal microdroplets; The step of projecting the first support column region in the chip support column image into the to-be-judged image to obtain a second support column region corresponding to the to-be-judged image comprises: superimpose the chip support column image and the to-be-judged image, and translate the chip support column image on the to-be-judged image according to a preset step length; traverse all the translation transformations, and calculate the sum of pixel values of the first support column region and the superimposed region corresponding to the to-be-judged image in all the translation transformations; select the translation transformation with the smallest sum of pixel values, and project the first support column region into the to-be-judged image according to the translation transformation to obtain the second support column region; Before superimposing the chip support column image and the to-be-judged image, the method further comprises: binaryzation processing the chip support column image; determine whether the pixel value of the first support column region in the chip support column image is 0; if not, then perform the NOT operation on the chip support column image.

2. The geometric position-based abnormal droplet determination method according to claim 1, wherein The image matching the chip support column image and the to-be-judged image comprises: obtaining a first support column contained in the first support column region in the chip support column image; determining a second support column corresponding to the first support column from the to-be-judged image; determining a scaling factor using the size data of the first support column and the second support column; image size matching the chip support column image and the to-be-judged image based on the scaling factor.

3. The geometric position-based abnormal droplet determination method according to claim 1, wherein The step of image matching the chip support column image and the to-be-judged image comprises: obtaining a first support column contained in the first support column region in the chip support column image; determining a second support column corresponding to the first support column from the to-be-judged image; determining an angle transformation factor using the position data of the first support column and the second support column; image angle matching the chip support column image and the to-be-judged image based on the angle transformation factor.

4. The geometric position-based abnormal droplet determination method according to claim 3, characterized by, The step of determining an angle transformation factor using the position data of the first support column and the second support column comprises: determining whether the first support column and the second support column are in the same plane according to the position data of the first support column and the second support column; If no, a rotation transformation factor and a first translation transformation factor between the first support column and the second support column are determined; wherein the rotation transformation factor is used to rotate the chip support column image and the image to be judged to the same plane; and the first translation transformation factor is used to translate the chip support column image and the image to be judged to the same position. The rotation transformation factor and the first translation transformation factor are determined as the angle transformation factor.

5. The geometric position-based abnormal droplet determination method according to claim 3, wherein, The step of determining the angle transformation factor by using the position data of the first support column and the second support column comprises: According to the position data of the first support column and the second support column, it is determined whether the first support column and the second support column are in the same plane; If yes, a second translation transformation factor between the first support column and the second support column is determined; wherein the second translation transformation factor is used to translate the chip support column image and the image to be judged to the same position; The second translation transformation factor is determined as the angle transformation factor.

6. A geometric position-based anomalous droplet determination system, comprising: The system comprises: An initialization module is configured to determine a chip support column image and an image to be judged; wherein the chip support column image comprises a first support column region; and the image to be judged comprises a plurality of microdroplets to be judged; An image matching module is configured to perform image matching on the chip support column image and the image to be judged; An image projection module is configured to project the first support column region in the chip support column image to the image to be judged to obtain a second support column region corresponding to the image to be judged; A judgment execution module is configured to judge the microdroplets to be judged, which are less than a preset threshold from the second support column region, as abnormal microdroplets; The image projection module is further configured to: superimpose the chip support column image and the image to be judged, and perform translation transformation on the chip support column image on the image to be judged according to a preset step; traverse all the translation transformations, and calculate the sum of pixel values of the first support column region and the superimposed region corresponding to the image to be judged in all the translation transformations; select the translation transformation with the smallest sum of pixel values, and project the first support column region to the image to be judged according to the translation transformation to obtain the second support column region; Before superimposing the chip support column image and the image to be judged, the image projection module is further configured to: perform binaryzation processing on the chip support column image; determine whether the pixel value of the first support column region in the chip support column image is 0; and if no, perform inversion processing on the chip support column image.

7. An electronic device, comprising: Comprise: A processor and a storage device; The storage device stores a computer program, which, when executed by the processor, implements the steps of the geometric position-based abnormal microdroplet judgment method of any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that The computer program, when executed by the processor, implements the steps of the geometric position-based abnormal microdroplet judgment method of any one of claims 1 to 5.

Images