Meibomian gland deletion detection method, system and device and medium

Abstract

The invention relates to a meibomian gland deletion detection method, a meibomian gland deletion detection system, a meibomian gland deletion detection device and a medium, and relates to the technical field of image processing. The meibomian gland deletion detection method comprises the steps of image acquisition, image processing, first gray value segmentation point acquisition, first image segmentation, nth gray value segmentation point acquisition, nth image segmentation, gray value judgment, area calculation, deletion rate calculation, output and the like. The meibomian gland deletion detection system comprises an acquisition module, a processing module, a calculation module I, a segmentation module I, a calculation module II, a segmentation module II, a judgment module, a calculation module III and an output module. According to the meibomian gland deletion detection method and device, intervention of human factors can be reduced in the meibomian gland deletion detection process, then errors of meibomian gland deletion detection are reduced, and then the precision of meibomian gland deletion detection is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method, system, device and medium for detecting meibomian gland deficiency. Background Art

[0002] Meibomian glands are enlarged and abnormal sebaceous glands, which are composed of two independent functional structural units, the alveoli and the ducts, and have the functions of synthesizing, storing and secreting lipids. The lipids secreted by the meibomian glands are called meibomians, which participate in the formation of the lipid layer of the tear film. The lipid layer of the tear film plays an important role in maintaining the stability of the tear film, reducing the evaporation rate of the aqueous layer of the tear film, preventing the outflow of tears, and resisting microorganisms.

[0003] Currently, doctors are trying to use image processing algorithms or software to obtain information about the meibomian glands more accurately and conveniently, increase the contrast of the meibomian gland images and highlight the glands, so that doctors can observe the meibomian glands more easily. The images are analyzed, the areas where the meibomian glands are present and absent are manually drawn, and then the areas where the meibomian glands are present and absent are calculated.

[0004] However, when obtaining the missing area of ​​the meibomian glands, the process of drawing the meibomian glands is relatively cumbersome and time-consuming, and the accuracy of manual drawing is low, and the detection process is prone to human errors. Therefore, a high-precision meibomian gland missing detection method is urgently needed to detect the missing area of ​​the meibomian glands. Summary of the invention

[0005] In order to improve the accuracy of meibomian gland detection, the present invention provides a method, system, device and medium for detecting meibomian gland deficiency.

[0006] In a first aspect, the present invention provides a method for detecting meibomian gland deficiency, which adopts the following technical solution:

[0007] A method for detecting meibomian gland deficiency, comprising:

[0008] Image acquisition: open the upper and lower eyelids, take a picture of the eyes, and obtain the eye picture;

[0009] Image processing: grayscale processing is performed on the eye photo so that each pixel in the eye photo corresponds to a grayscale value K, and the total number of grayscale values ​​m, the maximum grayscale value Nmax, and the minimum grayscale value Nmin are obtained;

[0010] First gray value segmentation point acquisition: Get the first gray value segmentation point M1. The acquisition model of the first gray value segmentation point M1 is as follows:

[0011]

[0012] First image segmentation: Taking the first gray value segmentation point M1 as a reference, the m gray values ​​in the eye photo are distinguished to form a set A1 and a set B1. The elements in the set A1 are gray values ​​whose gray value K is less than M1, and the elements in the set B1 are gray values ​​whose gray value K is greater than M1.

[0013] Get the nth grayscale segmentation point: Get the nth grayscale segmentation point M n , the nth gray value segmentation point M n The acquisition model is as follows:

[0014]

[0015] In the formula, i is the set A n-1 The number of elements in K i The gray value is less than the n-1th gray value segmentation point M n-1 The gray value of j is the set B n-1 The number of elements in K j The gray value is greater than the n-1th gray value segmentation point M n-1 Gray value of

[0016] The nth image segmentation: segmentation point M with the nth gray value n As a benchmark, and make M n Replace Mn-1, distinguish the m grayscale values ​​in the eye photo and form a set A n and set B n , set A n The elements in the grayscale value K are less than M n Gray value of set B n The elements in the grayscale value K are greater than M n Gray value, and make the set An replace the set A n-1 , set B n Replaces Bn-1;

[0017] Gray value judgment: Set the gray value threshold ΔM. If M n -M n-1 ≥ΔM, then execute the nth gray value segmentation point acquisition step and the nth image segmentation step. If M n -M n-1 <ΔM, then execute the area calculation step;

[0018] Area calculation: Calculate the area S of the meibomian glands. The calculation model of the meibomian gland area S is as follows:

[0019]

[0020] Where X is the width of the eye photo, Y is the length of the eye photo, m is the total number of grayscale values, and Z is the number of grayscale values ​​in the meibomian gland area;

[0021] The calculation model of the number of gray values ​​Z in the meibomian gland area is as follows:

[0022] Z = ∑ R[K]:

[0023]

[0024] Output: Output the processed eye photo and the value of the area S of the meibomian gland.

[0025] When testing the meibomian glands, the eyelids of the person being tested are turned up, the eyes are photographed, and the eye photograph is gray-processed so that each pixel in the eye photograph corresponds to a gray value K, and the total number of gray values ​​m, the maximum gray value Nmax, and the minimum gray value Nmin are obtained. The first gray value segmentation point M1 is calculated by the maximum gray value Nmax and the minimum gray value Nmin. Based on M1, the m gray values ​​in the eye photograph are distinguished to form a set A1 and a set B1. The elements in set A1 are gray values ​​whose gray value K is less than M1, and the elements in set B1 are gray values ​​whose gray value K is greater than M1. After n calculations, M is obtained. n -M n-1 ≥ΔM when M n The value of proves that the area of ​​the meibomian gland has been separated from the eye photo. By obtaining the proportion of the number of gray values ​​greater than Mn in the total number of gray values, the area occupied by the meibomian gland in the eye image is obtained.

[0026] The above technical solutions in the embodiments of the present application have at least the following technical effects:

[0027] By processing the eye photo, the meibomian glands are highlighted, thereby achieving clearer observation of the meibomian glands. When the meibomian glands are highlighted, the area of ​​the meibomian glands is obtained by calculating the ratio of the number of grayscale values ​​in the meibomian gland area to the number of grayscale values ​​in the entire eye photo. In the process of meibomian gland loss detection, the intervention of human factors is reduced, thereby reducing the error of meibomian gland loss detection, thereby improving the accuracy of meibomian gland loss detection.

[0028] Optionally, a missing rate calculation step is further provided after the area calculation step;

[0029] Calculation of missing rate: Calculate the missing rate V of the meibomian glands. The calculation model of the missing rate V of the meibomian glands is as follows:

[0030] Where S1 is the area of ​​the standard meibomian gland.

[0031] Optionally, the output step also outputs the loss rate V of the meibomian glands.

[0032] In a second aspect, the present invention provides a meibomian gland deficiency detection system, which adopts the following technical solution:

[0033] A meibomian gland deficiency detection system comprises an acquisition module, a processing module, a calculation module I, a segmentation module I, a calculation module II, a segmentation module II, a judgment module, a calculation module III and an output module;

[0034] Acquisition module: the output end is electrically connected to the input end of the processing module, and is used to take a picture of the eye and acquire the eye picture;

[0035] Processing module: the input end is electrically connected to the output end of the acquisition module, and the output end is electrically connected to the input end of the calculation module I, and is used to perform grayscale processing on the eye photo acquired by the acquisition module, so that each pixel in the eye photo corresponds to a grayscale value K, and obtain the total number of grayscale values ​​m, the maximum grayscale value Nmax and the minimum grayscale value Nmin;

[0036] Calculation module I: The output end is electrically connected to the input end of segmentation module I, and is used to calculate the first gray value segmentation point M1. The acquisition model of the first gray value segmentation point M1 is as follows:

[0037]

[0038] Segmentation module I: the output end is electrically connected to the input end of the calculation module II, and the m gray values ​​in the eye photo are distinguished based on the first gray value segmentation point M1, and a set A1 and a set B1 are formed, wherein the elements in the set A1 are gray values ​​whose gray value K is less than M1, and the elements in the set B1 are gray values ​​whose gray value K is greater than M1;

[0039] Calculation module II: The output end is connected to the input end of the segmentation module for calculating the nth gray value segmentation point M n , the nth gray value segmentation point M n The acquisition model is as follows:

[0040]

[0041] In the formula, i is the set A n-1 The number of elements in K i The gray value is less than the n-1th gray value segmentation point M n-1 The gray value of j is the set B n-1 The number of elements in K j The gray value is greater than the n-1th gray value segmentation point M n-1 Gray value of

[0042] Segmentation module II: The output terminal is connected to the input terminal of the judgment module, and the nth gray value is used to segment the point M. n As a benchmark, and make M n Replace Mn-1, distinguish the m grayscale values ​​in the eye photo and form a set A n and set B n , set A n The elements in the grayscale value K are less than M n Gray value of set B n The elements in the grayscale value K are greater than M n Gray value, and make the set An replace the set A n-1 , set B n Replaces Bn-1;

[0043] Judgment module: The output end is connected to the input end of the calculation module III and the input end of the calculation module II. The gray value threshold ΔM is set in the judgment module. If M n -M n-1 ≥ΔM, then calculate module II and execute segmentation module II. If M n -M n-1 <ΔM, then execute calculation module III;

[0044] Calculation module III: The output end is connected to the input end of the output module for electrical signal calculation of the area S of the meibomian gland. The calculation model of the meibomian gland area S is as follows:

[0045]

[0046] Where X is the width of the eye photo, Y is the length of the eye photo, m is the total number of grayscale values, and Z is the number of grayscale values ​​in the meibomian gland area;

[0047] The calculation model of the number of gray values ​​Z in the meibomian gland area is as follows:

[0048] Z = ∑ R[K]:

[0049]

[0050] Output module: Outputs processed eye photos and the value of the area S of the meibomian glands.

[0051] Optionally, a calculation module IV is further provided after the calculation module III;

[0052] Calculation module IV: the input end is electrically connected to the output end of calculation module III, and the output end is electrically connected to the input end of the output module, and is used to calculate the meibomian gland deficiency rate V. The calculation model of the meibomian gland deficiency rate V is as follows:

[0053] Where S1 is the area of ​​the standard meibomian gland.

[0054] Optionally, the output module also outputs the loss rate V of the meibomian glands.

[0055] In a third aspect, the present invention provides a device for detecting meibomian gland deficiency, which adopts the following technical solution:

[0056] A device comprises a processor and a storage, wherein the storage is used to store a computer program, and the processor is used to execute the computer program stored in the storage, so that the device executes the method as described in the first aspect.

[0057] In a fourth aspect, the present invention provides a computer storage medium for detecting meibomian gland deficiency, which adopts the following technical solution:

[0058] A medium having a computer program stored thereon; when the computer program is executed by a processor, the method described in the first aspect is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is a flow chart of Example 1 of the present application;

[0060] Figure 2 is a schematic diagram of the system structure of Example 2 of the present application;

[0061] Figure 3 This is a device diagram of Example 3 of the present application. DETAILED DESCRIPTION

[0062] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0064] It should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.

[0065] It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0066] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0067] In this application, "and / or" is only a description of the association relationship of associated objects, indicating that there can be three relationships; for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0068] It should be noted that, in the present application, words such as "in some embodiments", "exemplarily", "for example", etc. are used to indicate examples, illustrations or descriptions. Any embodiment or design described in the present application as "in some embodiments", "exemplarily", "for example" should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "in some embodiments", "exemplarily", "for example", etc. is intended to present related concepts in a concrete way, meaning that specific features, structures or characteristics described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the above words in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0069] The following combination Figure 1 to Figure 2 The present invention is described in further detail.

[0070] Example 1: This example discloses a method for detecting meibomian gland deficiency, referring to Figure 1 , a method for detecting meibomian gland deficiency comprises the following steps:

[0071] S1: Image acquisition: Open the upper and lower eyelids, take a picture of the eyes, and obtain the eye picture.

[0072] S2: Image processing: grayscale processing is performed on the eye photo so that each pixel in the eye photo corresponds to a grayscale value K, and the total number of grayscale values ​​m, the maximum grayscale value Nmax and the minimum grayscale value Nmin are obtained. (For example: the number of grayscale values ​​in the obtained eye photo is 10, namely 200, 300, 800, 700, 450, 650, 750, 430, 550, 610, the maximum grayscale value is 800, and the minimum grayscale value is 200).

[0073] S3: Acquisition of the first grayscale segmentation point: Acquisition of the first grayscale segmentation point M1. The acquisition model of the first grayscale segmentation point M1 is as follows:

[0074] (For example, the maximum grayscale value is 800, the minimum grayscale value is 200, and M1 is calculated to be 500).

[0075] S4: First image segmentation: Based on the first grayscale value segmentation point M1, the m grayscale values ​​in the eye photo are distinguished and formed into a set A1 and a set B1. The elements in the set A1 are grayscale values ​​whose grayscale value K is less than M1, and the elements in the set B1 are grayscale values ​​whose grayscale value K is greater than M1. (For example: with the grayscale value M1=500 as the segmentation point, the points with grayscale values ​​less than 500 form the A1 set, and the points with grayscale values ​​greater than 500 form the B1 set).

[0076] S5: Obtaining the nth grayscale value segmentation point: Obtaining the nth grayscale value segmentation point M n , the nth gray value segmentation point M n The acquisition model is as follows:

[0077]

[0078] In the formula, i is the set A n-1 The number of elements in K i The gray value is less than the n-1th gray value segmentation point M n-1 The gray value of j is the set B n-1 The number of elements in K j The gray value is greater than the n-1th gray value segmentation point M n-1 Grayscale value. (For example: the elements in set A2 are 200, 300, 450, 430, the elements in set B2 are 800, 700, 650, 750, 550, 610, and the output of M2 is 511).

[0079] S6: nth image segmentation: segmentation point M with nth gray value n As a benchmark, and make M n Replace Mn-1, distinguish the m grayscale values ​​in the eye photo and form a set A n and set Bn , set A n The elements in the grayscale value K are less than M n Gray value of set B n The elements in the grayscale value K are greater than M n Gray value, and make the set An replace the set A n-1 , set B n Replace Bn-1. (For example: after calculating M2, use M2 as the segmentation point to segment the M grayscale values ​​K, and then calculate M3, through step S5; after calculating M3, use M3 as the segmentation point to segment the M grayscale values ​​K, and then calculate M4, through step S5; and so on, calculate M n-1 and M n ).

[0080] S7: Gray value judgment: Set the gray value threshold ΔM. If M n -M n-1 ≥ΔM, then execute the nth gray value segmentation point acquisition step and the nth image segmentation step. If M n -M n-1 <ΔM, then the area calculation step is performed. (For example: the gray value threshold ΔM is 10, by looping step S5, M4=491, M5=498, M5-M4=7<10 is calculated, then the gray values ​​greater than M5 are the gray values ​​of the meibomian glands after the eye photo is processed, and the area calculation step is performed. If M4=491, M5=520, M5-M4=29>10, then continue to loop step S5 and step S6).

[0081] S8: Area calculation: Calculate the area S of the meibomian glands. The calculation model of the meibomian gland area S is as follows:

[0082]

[0083] Where X is the width of the eye photo, Y is the length of the eye photo, m is the total number of grayscale values, and Z is the number of grayscale values ​​in the meibomian gland area;

[0084] The calculation model of the number of gray values ​​Z in the meibomian gland area is as follows:

[0085] Z = ∑ R[K]:

[0086]

[0087] S9: Calculation of missing rate: Calculate the missing rate V of the meibomian glands. The calculation model of the missing rate V of the meibomian glands is as follows:

[0088] Where S1 is the area of ​​the standard meibomian gland.

[0089] S10: Output: Output the processed eye photo, the value of the area S of the meibomian gland, and the loss rate V of the meibomian gland.

[0090] The implementation principle of a method for detecting meibomian gland deficiency in the present embodiment is as follows: when detecting the meibomian glands, the eyelids of the person being detected are turned up, the eyes are photographed, and the eye photograph is gray-processed so that each pixel in the eye photograph corresponds to a gray value K, and the total number of gray values ​​m, the maximum gray value Nmax, and the minimum gray value Nmin are obtained. The first gray value segmentation point M1 is calculated by the maximum gray value Nmax and the minimum gray value Nmin. Based on M1, the m gray values ​​in the eye photograph are distinguished to form a set A1 and a set B1. The elements in set A1 are gray values ​​whose gray value K is less than M1, and the elements in set B1 are gray values ​​whose gray value K is greater than M1. After n calculations, M1 is obtained. n -M n-1 ≥ΔM when M n The value of proves that the area of ​​the meibomian gland has been separated from the eye photo. By obtaining the proportion of the number of gray values ​​greater than Mn in the total number of gray values, the area occupied by the meibomian gland in the eye image is obtained.

[0091] Embodiment 2: This embodiment discloses a system for detecting meibomian gland deficiency, referring to Figure 2 , a meibomian gland absence detection system includes: an acquisition module, a processing module, a calculation module I, a segmentation module I, a calculation module II, a segmentation module II, a judgment module, a calculation module III, a calculation module IV and an output module;

[0092] Acquisition module: The output end is electrically connected to the input end of the processing module, and is used to take pictures of the eyes and obtain the pictures of the eyes.

[0093] Processing module: the input end is electrically connected to the output end of the acquisition module, and the output end is electrically connected to the input end of the calculation module I, and is used to perform grayscale processing on the eye photo acquired by the acquisition module, so that each pixel in the eye photo corresponds to a grayscale value K, and obtain the total number of grayscale values ​​m, the maximum grayscale value Nmax and the minimum grayscale value Nmin.

[0094] Calculation module I: The output end is electrically connected to the input end of segmentation module I, and is used to calculate the first gray value segmentation point M1. The acquisition model of the first gray value segmentation point M1 is as follows:

[0095]

[0096] Segmentation module I: The output end is electrically connected to the input end of the calculation module II. Based on the first gray value segmentation point M1, the m gray values ​​in the eye photo are distinguished to form a set A1 and a set B1. The elements in set A1 are gray values ​​whose gray value K is less than M1, and the elements in set B1 are gray values ​​whose gray value K is greater than M1.

[0097] Calculation module II: The output end is connected to the input end of the segmentation module for calculating the nth gray value segmentation point M n , the nth gray value segmentation point M n The acquisition model is as follows:

[0098]

[0099] In the formula, i is the set A n-1 The number of elements in K i The gray value is less than the n-1th gray value segmentation point M n-1 The gray value of j is the set B n-1 The number of elements in K j The gray value is greater than the n-1th gray value segmentation point M n-1 The gray value of .

[0100] Segmentation module II: The output terminal is connected to the input terminal of the judgment module, and the nth gray value is used to segment the point M. n As a benchmark, and make M n Replace Mn-1, distinguish the m grayscale values ​​in the eye photo and form a set A n and set B n , set A n The elements in the grayscale value K are less than M n Gray value of set B n The elements in the grayscale value K are greater than M n Gray value, and make the set An replace the set A n-1 , set B n Replaces Bn-1.

[0101] Judgment module: The output end is connected to the input end of the calculation module III and the input end of the calculation module II. The gray value threshold ΔM is set in the judgment module. If M n -M n-1 ≥ΔM, then calculate module II and execute segmentation module II. If M n -M n-1 <ΔM, then execute calculation module III.

[0102] Calculation module III: The output end is connected to the input end of the output module for electrical signal calculation of the area S of the meibomian gland. The calculation model of the meibomian gland area S is as follows:

[0103]

[0104] Where X is the width of the eye photo, Y is the length of the eye photo, m is the total number of grayscale values, and Z is the number of grayscale values ​​in the meibomian gland area;

[0105] The calculation model of the number of gray values ​​Z in the meibomian gland area is as follows:

[0106] Z = ∑ R[K]:

[0107]

[0108] Calculation module IV: The input end is electrically connected to the output end of calculation module III, and the output end is electrically connected to the input end of the output module, and is used to calculate the meibomian gland deficiency rate V. The calculation model of the meibomian gland deficiency rate V is as follows:

[0109] Where S1 is the area of ​​the standard meibomian gland.

[0110] Output module: Outputs processed eye photos and the value of the area S of the meibomian glands.

[0111] The implementation principle of the meibomian gland deficiency detection system of this embodiment is as follows: the acquisition module acquires an eye photo, the processing module performs grayscale processing on the eye photo acquired by the acquisition module, so that each pixel in the eye photo corresponds to a grayscale value K, and obtains the total number of grayscale values ​​m, the maximum grayscale value Nmax and the minimum grayscale value Nmin; the calculation module I calculates the first grayscale value segmentation point M1, and the segmentation module I distinguishes the m grayscale values ​​in the eye photo based on the first grayscale value segmentation point M1, and forms a set A1 and a set B1, the elements in the set A1 are grayscale values ​​whose grayscale value K is less than M1, and the elements in the set B1 are grayscale values ​​whose grayscale value K is greater than M1. The calculation module II calculates the nth grayscale value segmentation point M1. n , segmentation module II segments point M with the nth gray value n As a benchmark, and make M n Replace Mn-1, distinguish the m grayscale values ​​in the eye photo and form a set A n and set B n , set A n The elements in the gray value K are less than M n Gray value of set B n The elements in the grayscale value K are greater than M n Gray value, and make the set An replace the set A n-1 , set B n Replace Bn-1. Set the gray value threshold ΔM in the judgment module. If M n-M n-1 ≥ΔM, then calculate module II and execute segmentation module II. If M n -M n-1 <ΔM, the calculation module III is executed. The calculation module III calculates the area S of the meibomian glands, the calculation module IV calculates the loss rate V of the meibomian glands, and the output module outputs the processed eye photo, as well as the value of the area S of the meibomian glands and the loss rate V of the meibomian glands.

[0112] Embodiment 3: This embodiment discloses a device for detecting meibomian gland deficiency, referring to Figure 3 , a meibomian gland absence detection device comprises:

[0113] Storage for storing computer programs;

[0114] The processor is used to execute the computer program stored in the memory, thereby implementing the method described in Example 1.

[0115] The storage may include a large capacity storage for storing data or instructions. By way of example and not limitation, the storage may include a hard disk, a floppy disk, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a combination of two or more of these. Where appropriate, the storage may include a removable or non-removable (or fixed) medium. Where appropriate, the storage may be inside or outside the data processing device. In a particular embodiment, the storage is a non-volatile solid-state storage. In a particular embodiment, the storage includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EBROM), or a combination of two or more of these.

[0116] Embodiment 4: This embodiment discloses a computer storage medium for detecting meibomian gland deficiency, wherein the computer storage medium stores a program, and when the program is executed, part or all of the steps of the method described in Embodiment 1 can be implemented.

[0117] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting meibomian gland deficiency, characterized in that: Image acquisition: open the upper and lower eyelids, take a picture of the eyes, and obtain the eye picture; Image processing: grayscale processing is performed on the eye photo so that each pixel in the eye photo corresponds to a grayscale value K, and the total number of grayscale values ​​m, the maximum grayscale value Nmax, and the minimum grayscale value Nmin are obtained; First gray value segmentation point acquisition: Get the first gray value segmentation point M1. The acquisition model of the first gray value segmentation point M1 is as follows: First image segmentation: Taking the first gray value segmentation point M1 as a reference, the m gray values ​​in the eye photo are distinguished to form a set A1 and a set B1. The elements in the set A1 are gray values ​​whose gray value K is less than M1, and the elements in the set B1 are gray values ​​whose gray value K is greater than M1. Get the nth grayscale segmentation point: Get the nth grayscale segmentation point M n , the nth gray value segmentation point M n The acquisition model is as follows: In the formula, i is the set A n-1 The number of elements in K i The gray value is less than the n-1th gray value segmentation point M n-1 The gray value of j is the set B n-1 The number of elements in K j The gray value is greater than the n-1th gray value segmentation point M n-1 Gray value of The nth image segmentation: segmentation point M with the nth gray value n As a benchmark, and make M n Replace Mn-1, distinguish the m grayscale values ​​in the eye photo and form a set A n and set B n , set A n The elements in the grayscale value K are less than M n Gray value of set B n The elements in the grayscale value K are greater than M n Gray value, and make the set An replace the set A n-1 , set B n Replace B n-1 ; Gray value judgment: Set the gray value threshold ΔM. If M n -M n-1 ≥ΔM, then execute the nth gray value segmentation point acquisition step and the nth image segmentation step. If M n -M n-1 <ΔM, then execute the area calculation step; Area calculation: Calculate the area S of the meibomian glands. The calculation model of the meibomian gland area S is as follows: Where X is the width of the eye photo, Y is the length of the eye photo, m is the total number of grayscale values, and Z is the number of grayscale values ​​in the meibomian gland area; The calculation model of the number of gray values ​​Z in the meibomian gland area is as follows: Z = ∑ R[K]: Output: Output the processed eye photo and the value of the area S of the meibomian gland.

2. A method for detecting meibomian gland deficiency according to claim 1, characterized in that: A missing rate calculation step is also provided after the area calculation step; Calculation of missing rate: Calculate the missing rate V of the meibomian glands. The calculation model of the missing rate V of the meibomian glands is as follows: Where S1 is the area of ​​the standard meibomian gland.

3. A method for detecting meibomian gland deficiency according to claim 2, characterized in that: In the output step, the loss rate V of the meibomian glands is also output.

4. A meibomian gland deficiency detection system, using a meibomian gland deficiency detection method according to any one of claims 1 to 3, characterized in that: It includes an acquisition module, a processing module, a calculation module I, a segmentation module I, a calculation module II, a segmentation module II, a judgment module, a calculation module III and an output module; Acquisition module: the output end is electrically connected to the input end of the processing module, and is used to take a picture of the eye and acquire the eye picture; Processing module: the input end is electrically connected to the output end of the acquisition module, and the output end is electrically connected to the input end of the calculation module I, and is used to perform grayscale processing on the eye photo acquired by the acquisition module, so that each pixel in the eye photo corresponds to a grayscale value K, and obtain the total number of grayscale values ​​m, the maximum grayscale value Nmax and the minimum grayscale value Nmin; Calculation module I: The output end is electrically connected to the input end of segmentation module I, and is used to calculate the first gray value segmentation point M1. The acquisition model of the first gray value segmentation point M1 is as follows: Segmentation module I: the output end is electrically connected to the input end of the calculation module II, and the m gray values ​​in the eye photo are distinguished based on the first gray value segmentation point M1, and a set A1 and a set B1 are formed, wherein the elements in the set A1 are gray values ​​whose gray value K is less than M1, and the elements in the set B1 are gray values ​​whose gray value K is greater than M1; Calculation module II: The output end is connected to the input end of the segmentation module for calculating the nth gray value segmentation point M n , the nth gray value segmentation point M n The acquisition model is as follows: In the formula, i is the set A n-1 The number of elements in K i The gray value is less than the n-1th gray value segmentation point M n-1 The gray value of j is the set B n-1 The number of elements in K j The gray value is greater than the n-1th gray value segmentation point M n-1 Gray value of Segmentation module II: The output terminal is connected to the input terminal of the judgment module, and the nth gray value is used to segment the point M. n As a benchmark, and make M n Replace Mn-1, distinguish the m grayscale values ​​in the eye photo and form a set A n and set B n , set A n The elements in the grayscale value K are less than M n Gray value of set B n The elements in the grayscale value K are greater than M n Gray value, and make the set An replace the set A n-1 , set B n Replaces Bn-1; Judgment module: The output end is connected to the input end of the calculation module III and the input end of the calculation module II. The gray value threshold ΔM is set in the judgment module. If M n -M n-1 ≥ΔM, then calculate module II and execute segmentation module II. If M n -M n-1 <ΔM, then execute calculation module III; Calculation module III: The output end is connected to the input end of the output module for electrical signal calculation of the area S of the meibomian gland. The calculation model of the meibomian gland area S is as follows: Where X is the width of the eye photo, Y is the length of the eye photo, m is the total number of grayscale values, and Z is the number of grayscale values ​​in the meibomian gland area; The calculation model of the number of gray values ​​Z in the meibomian gland area is as follows: Z = ∑ R[K]: Output module: Outputs processed eye photos and the value of the area S of the meibomian glands.

5. A meibomian gland absence detection system according to claim 4, characterized in that: A computing module IV is also provided after the computing module III; Calculation module IV: the input end is electrically connected to the output end of calculation module III, and the output end is electrically connected to the input end of the output module, and is used to calculate the meibomian gland deficiency rate V. The calculation model of the meibomian gland deficiency rate V is as follows: Where S1 is the area of ​​the standard meibomian gland.

6. A meibomian gland absence detection system according to claim 5, characterized in that: The output module also outputs the loss rate V of the meibomian glands.

7. A device for detecting meibomian gland deficiency, characterized in that: The device comprises a processor and a storage, wherein the storage is used to store a computer program, and the processor is used to execute the computer program stored in the storage, so that the device executes the method according to any one of claims 1 to 3.

8. A computer storage medium for detecting meibomian gland deficiency, having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images