A method, device, medium and product for determining corneal curvature radius

Abstract

According to an exemplary embodiment of the present disclosure, a method, device, medium and product for determining the radius of corneal curvature are provided. The method includes: determining the minimum pixel number range and the maximum pixel number range occupied by the outer diameter of the backlight ring based on multiple first keratometer images with the minimum corneal curvature radius and multiple second keratometer images with the maximum corneal curvature radius; determining the backlight ring area range based on the maximum pixel number range and the preset offset; collecting human eye images; performing circular detection and fitting on the human eye images based on the maximum pixel number range and the minimum pixel number range to obtain the number of pixels occupied by the outer diameter of the backlight ring in the human eye image; and determining the corneal curvature radius of the human eye image based on the number of pixels occupied by the outer diameter of the backlight ring obtained by the preset formula. In this way, the calculation accuracy of the corneal curvature radius can be improved.

Description

Technical Field

[0001] Embodiments of the present disclosure generally relate to the field of information processing, and more particularly to a method for determining a corneal curvature radius, an electronic device, a computer-readable medium, and a computer program product. Background Art

[0002] In the application of measuring the corneal curvature radius (diopter) of the human eye using a biometer, the captured image will have a relatively optimally focused backlight circle at the cornea. The curvature radius and diopter can be calculated by determining the diameter pixel value of the backlight circle.

[0003] The traditional solution is to determine the number of pixels occupied by the diameter by framing the left and right boundary points of the backlight ring. However, the biggest disadvantage of determining the number of pixels occupied by the diameter by framing the left and right boundary points of the backlight ring is that the external environment has a great influence. If the shooting environment is very bright, there will be different degrees of interference bright spots at the corneal backlight ring. If these bright spots appear at the edge, they will greatly affect the calibration of the backlight ring edge, thereby greatly affecting the calculation results of the number of pixels and the radius of curvature. Summary of the invention

[0004] The embodiments of the present disclosure provide a method, electronic device, computer-readable medium and computer program product for determining the radius of corneal curvature, thereby being able to exclude interference circles outside the conditions by determining the range of the number of pixels occupied by the back aperture diameter, thereby improving the accuracy of detecting the fitting circle and thus improving the calculation accuracy of the radius of corneal curvature.

[0005] In a first aspect of the present disclosure, a method for determining the radius of corneal curvature is provided. The method includes: determining the minimum pixel number range and the maximum pixel number range occupied by the outer diameter of the backlight ring based on a plurality of first keratometer images with the minimum corneal curvature radius and a plurality of second keratometer images with the maximum corneal curvature radius; determining the backlight ring area range based on the maximum pixel number range and a preset offset; collecting a human eye image, wherein the distance between the corneal center point in the human eye image and the image center point is less than or equal to the preset offset, and the backlight ring in the human eye image is located within the backlight ring area range; performing circular detection and fitting on the human eye image based on the maximum pixel number range and the minimum pixel number range to obtain the number of pixels occupied by the outer diameter of the backlight ring in the human eye image; and determining the corneal curvature radius of the human eye image through a preset formula based on the number of pixels occupied by the outer diameter of the backlight ring obtained.

[0006] In a second aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect of the present disclosure.

[0007] In a third aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the method according to the first aspect of the present disclosure.

[0008] In a fourth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method according to the first aspect of the present disclosure when executed by a processor.

[0009] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the present disclosure, nor is it intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other objects, features and advantages of the present disclosure will become more apparent through a more detailed description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components throughout the exemplary embodiments of the present disclosure.

[0011] Figure 1 A schematic diagram of an example environment 100 is shown according to an embodiment of the present disclosure;

[0012] Figure 2 A schematic diagram of a method 200 for determining a corneal curvature radius according to an embodiment of the present disclosure is shown;

[0013] Figure 3 A schematic diagram showing calculation 300 of circular area diameter pixels after the keratometer original image is filled with a circle according to an embodiment of the present disclosure;

[0014] Figure 4 A schematic diagram showing a backlight area range 400 according to an embodiment of the present disclosure is shown;

[0015] Figure 5 A schematic diagram of a human eye image 500 according to an embodiment of the present disclosure is shown;

[0016] Figure 6 A schematic diagram showing a comparison 600 of an image before smooth filtering and an image after smooth filtering according to an embodiment of the present disclosure;

[0017] Figure 7 A schematic diagram showing a circular fitting result 700 according to an embodiment of the present disclosure is shown;

[0018] Figure 8 A schematic diagram showing a method 800 for determining a corneal curvature radius of a human eye image according to an embodiment of the present disclosure is shown;

[0019] Fig. 9 shows a schematic diagram of a standard resolution board image 900 according to an embodiment of the present disclosure;

[0020] Fig.10 shows a schematic diagram of a populated line pair 1000 according to an embodiment of the present disclosure;

[0021] Fig.11 A schematic diagram showing a relationship 1100 between the imaged size of a backlight circle and the actual backlight circle size according to an embodiment of the present disclosure; and

[0022] Fig.12 A block diagram of an electronic device 1200 suitable for implementing the embodiments of the present disclosure is schematically shown.

[0023] In the various drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0024] The preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0025] As mentioned above, the biggest shortcoming of the traditional solution of determining the pixel value occupied by the diameter by framing the left and right boundary points of the backlight ring is that it is greatly affected by the external environment. If the shooting environment is very bright, interfering bright spots of varying degrees will appear at the corneal backlight ring. If these bright spots appear at the edge, they will greatly affect the calibration of the backlight ring edge, thereby greatly affecting the calculation results of the pixel value and the radius of curvature.

[0026] In order to solve the above problems or other problems not described, the present disclosure provides a scheme for determining the radius of corneal curvature. In the scheme, based on a plurality of first keratometer images with a minimum radius of corneal curvature and a plurality of second keratometer images with a maximum radius of corneal curvature, the minimum pixel number range and the maximum pixel number range occupied by the outer diameter of the backlight ring are determined; based on the maximum pixel number range and the preset offset, the backlight ring area range is determined; a human eye image is collected, wherein the distance between the corneal center point in the human eye image and the image center point is less than or equal to the preset offset, and the backlight ring in the human eye image is located within the backlight ring area range; based on the maximum pixel number range and the minimum pixel number range, the human eye image is detected and fitted with a circle to obtain the number of pixels occupied by the outer diameter of the backlight ring in the human eye image; and based on the obtained number of pixels occupied by the outer diameter of the backlight ring, the corneal curvature radius of the human eye image is determined via a preset formula.

[0027] Therefore, by determining the range of the number of pixels occupied by the back aperture diameter, all interference circles outside the conditions are excluded, thereby improving the accuracy of detecting the fitting circle and improving the calculation accuracy of the corneal curvature radius.

[0028] The following is a detailed description with reference to the accompanying drawings.

[0029] Figure 1 1 shows a schematic diagram of an example environment 100 according to an embodiment of the present disclosure. Figure 1 As shown, the example environment 100 includes a computing device 110 , a plurality of first keratometer images 120 having a minimum corneal curvature radius, a plurality of second keratometer images 130 having a maximum corneal curvature radius, a human eye image 140 , and a corneal curvature radius 150 of the human eye image 140 .

[0030] The computing device 110 may include, but is not limited to, an ophthalmic medical device, a personal computer, a personal digital assistant, a wearable device, a tablet computer, a smart phone, etc. In some embodiments, the computing device 110 may have or be coupled to an image acquisition device for acquiring images of human eyes.

[0031] The actual corneal curvature radius of the human eye is between 5 mm and 11 mm. The minimum corneal curvature radius here is 5 mm, and the maximum corneal curvature radius is 11 mm. The number of the plurality of first keratometer images 120 and the plurality of second keratometer images 130 is, for example, 200 each, but it should be understood that this number is only an example, the number can be other numbers, the number of the first keratometer images and the number of the second keratometer images can also be different, and the scope of the present disclosure is not limited thereto.

[0032] The computing device 110 can be used to determine the minimum pixel number range and the maximum pixel number range occupied by the outer circle diameter of the backlight circle based on multiple first keratometer images 120 with the minimum corneal curvature radius and multiple second keratometer images 130 with the maximum corneal curvature radius; determine the backlight circle area range based on the maximum pixel number range and the preset offset; collect the human eye image 140, wherein the distance between the corneal center point and the image center point in the human eye image 140 is less than or equal to the preset offset, and the backlight circle in the human eye image 140 is located within the backlight circle area range; perform circle detection and fitting on the human eye image 140 based on the maximum pixel number range and the minimum pixel number range to obtain the number of pixels occupied by the outer circle diameter of the backlight circle in the human eye image 140; and determine the corneal curvature radius 150 of the human eye image 140 based on the obtained number of pixels occupied by the outer circle diameter of the backlight circle through a preset formula.

[0033] Therefore, by determining the range of the number of pixels occupied by the back aperture diameter, all interference circles outside the conditions are excluded, thereby improving the accuracy of detecting the fitting circle and improving the calculation accuracy of the corneal curvature radius.

[0034] Figure 2 FIG. 2 is a schematic diagram showing an example of a method 200 for determining a corneal curvature radius according to an embodiment of the present disclosure. Figure 2 In the example, each action can be Figure 1 It should be understood that the method 200 may also include additional actions not shown and / or may omit the actions shown, and the scope of the present disclosure is not limited in this respect.

[0035] At block 202 , based on a plurality of first keratometer images having a minimum corneal curvature radius and a plurality of second keratometer images having a maximum corneal curvature radius, a minimum pixel number range and a maximum pixel number range occupied by a backlight outer circle diameter are determined.

[0036] For the minimum corneal curvature radius (R5), in some embodiments, a plurality of first keratometer images may be binarized to generate a plurality of first binary images.

[0037] After the binarization process, the holes of the multiple first binary images can be filled to obtain multiple first filled backlight circle areas. For example, the imfill function of MATLAB can be used as the filling function, combined with the "holes" parameter to fill the hole area of ​​the binary image, that is, the circular area of ​​the backlight circle. At this time, the backlight circle area becomes a solid circular area, and this solid circular area is used as the subsequent pixel value preprocessing calculation area. Optionally, after the circle is filled, the redundant noise around the circle can be removed. For example, the bwareaopen function of MATLAB can be used to set the value of the small object to, for example, 5000. This can remove the small object without affecting the circular area, thereby improving the accuracy and speed of subsequent circle detection and fitting.

[0038] After the hole is filled, the number of pixels of the first diameters of the first filled back aperture areas may be determined. Figure 3 , which shows the calculation of the circular area diameter pixel after the keratometer original image is filled with a circle. Figure 3 As shown, the binary solid circular area (that is, the area filled with backlight ring) has only two values, 0 and 1. By drawing a straight line through the diameter of the effective solid circular area (the gray straight line in the figure), the number of accumulated values ​​of 1 can be used to calculate the number of pixels occupied by the diameter of the circular area (that is, the number of pixels of the diameter of the area filled with backlight ring).

[0039] Next, a minimum pixel number range may be generated based on the plurality of first diameter pixel numbers. For example, the maximum and minimum values ​​of the plurality of first diameter pixel numbers may be obtained, and the range between the two values ​​may be used as the minimum pixel number range, such as 90-100 pixels.

[0040] Similarly, for the maximum corneal curvature radius (R11), in some embodiments, multiple second keratometer images can be binarized to generate multiple second binary images. Subsequently, the multiple second binary images can be hole-filled to obtain multiple second filled back aperture areas. Then, the number of multiple second diameter pixels of the multiple second filled back aperture areas can be determined. Finally, based on the number of multiple second diameter pixels, a maximum pixel number range, such as 220-230 pixels, can be generated. The specific process is similar to the process of determining the minimum pixel number range, and will not be repeated here.

[0041] Back to Figure 2 At block 204, a backlight area range is determined based on a maximum pixel number range and a preset offset.

[0042] Specifically, the maximum number of pixels in the maximum pixel number range may be determined. For example, if the pixel value range occupied by the outer diameter of the backlight ring is between 220 and 230 pixels, the maximum number of pixels is determined to be 230.

[0043] Then, the back light ring area range can be determined based on the maximum number of pixels and the preset offset. Considering the sample center point (e.g., image center point) offset caused by objective factors such as sample jitter during the shooting process, for example, 30 pixels are offset up and down, and 230+30*2=290 pixels can be obtained. The range of 290 pixels*290 pixels or a larger range than this range (e.g., 300 pixels*300 pixels) can be used as the back light ring area range. Figure 4 An example of the backlight area range is shown in FIG. Figure 4 As shown, box 401 represents the back aperture area range (for example, 300 pixels*300 pixels), circle 402 is a predetermined circle of the curvature meter with a corneal curvature radius of 11 (the number of pixels occupied by the diameter is 240 pixels), and circle 403 and circle 404 respectively represent the situation when the center of the circle is offset to the maximum amount (for example, 30 pixels) upward and to the right within the set range.

[0044] It should be understood that although a square is used as an example to illustrate the range of the backlight circle area, this is only an example, and it can also be a rectangle or other shapes, and the scope of the present disclosure is not limited here.

[0045] Since the actual human eye curvature radius is between 5mm and 11mm, that is, we determine that the entire back aperture area of ​​the largest R11 keratometer is included in the entire back aperture area range, it can be ensured that the back aperture areas of both keratometers and the actual human eye can be displayed within the back aperture area range and other noises can be well removed. In addition, considering the sample center point offset caused by objective factors such as sample jitter during the shooting process, by reserving the upper and lower offset pixel space, the sample will not exceed the range of this area no matter how it jitters.

[0046] Back to Figure 2 In box 206, a human eye image is collected, wherein the distance between the cornea center point in the human eye image and the image center point is less than or equal to a preset offset, and the backlight circle in the human eye image is within the backlight circle area.

[0047] Taking the center point position of the image acquisition device (e.g., camera) interface (equivalent to the center point of the image) as the preset circle center point (X0, Y0), the distance between the center point of the cornea of ​​the acquired image, i.e., the center point of the circle (Xn, Yn), and the preset circle center point shall not exceed 30 pixels, i.e., [(X0-Xn)^2+(Y0-Yn)^2]^1 / 2<=30 pixels. The offset of the cornea center point within this range will not cause the useful area of ​​the back aperture to move out of the back aperture area range. Figure 5 Schematic diagram of a human eye image 500 is shown. Figure 5 As shown, in the human eye image 500 , the backlight circle 501 is located within the backlight circle area range 502 .

[0048] Through stable sampling within the backlight circle area, the execution rate of the method can be effectively improved, eliminating the influence of factors such as image offset jitter caused by objective reasons in the sampling process. By using the center point position of the image acquisition interface (i.e., the center point of the image) as the preset center point, a preset circle with a radius of 30 pixels, and a square frame area with a side length of 300 pixels with the same center (i.e., the backlight circle area), these two judgment criteria are double-monitored to achieve stable sampling of human eye images. Here, R11 is used as a reference. When R11 meets the conditions, R5 and the actual human eye must be within the frame range.

[0049] At box 208, based on the maximum pixel number range and the minimum pixel number range, circle detection and fitting are performed on the human eye image to obtain the number of pixels occupied by the outer circle diameter of the backlight circle in the human eye image.

[0050] In some embodiments, the human eye image may be smoothed and filtered to generate a smoothed human eye image. For example, a Gaussian smoothing filter may be used, and when the convolution size is set to 5*5, for example, the filtering effect is most consistent with the actual calculated value of the corneal curvature radius. By convolving the original image, the redundant content of the image is reduced, and the heterogeneity of the human eye (such as various attachments, bumps on the skin, etc.) is reduced, which facilitates subsequent circle detection and fitting. Figure 6 A schematic diagram 600 showing a comparison of an image before smooth filtering and an image after smooth filtering is shown.

[0051] Next, the human eye image after smoothing and filtering can be binarized to generate a binary human eye image. Binary image processing can effectively improve the accuracy of image edge detection and facilitate subsequent circle detection and fitting of images.

[0052] Subsequently, circle detection and fitting can be performed on the binary human eye image based on the maximum pixel number range and the minimum pixel number range to obtain the number of pixels occupied by the outer circle diameter of the backlight circle in the binary human eye image.

[0053] Circle detection and fitting can be achieved by using Hough transform. In Hough transform, the radius of the circular object to be detected can be set as a scalar. Here, the number of pixels occupied can be used as a specified digital type scalar calculation; the radius range can also be set, with two element vectors of integers of the specified digital type as the maximum value rmax and the minimum value rmin of the range. After the radius range of the circle to be detected is determined in a targeted manner, the characteristic polarity of the circular object to be detected can also be set. Because it is a binary image, the value in the image is 0 or 1, which can be replaced by dark 'Dark' or 'Bright'. Since the backlight circle of the object to be detected is brighter than the background, 'Bright' can be used as the characteristic polarity of the object to be detected. In addition, the calculation method can be set as the phase encoding method. The sensitivity factor plays a great role in the process of detecting circles by Hough transform, and its range can be set between 0 and 1.

[0054] Figure 7 A schematic diagram of circular fitting is shown. Figure 7 As shown, the fitted circle is 701, which is the outer circle of the backlight circle. By calculating the number of pixels occupied by the diameter of the fitted circle 701, the number of pixels occupied by the diameter of the outer circle of the backlight circle in the binary human eye image can be obtained.

[0055] Specifically, the area for circle detection and fitting in the binary human eye image can be determined based on the maximum pixel number range and the minimum pixel number range. For example, the maximum value in the maximum pixel number range can be used as the maximum number of pixels occupied by the outer diameter of the backlight ring, and the minimum value in the minimum pixel number range can be used as the minimum number of pixels occupied by the outer diameter of the backlight ring. Subsequently, the annular area enclosed by a circle with the center point of the image as the center and the determined minimum number of pixels / 2 (for example, 45 pixels) as the radius to a circle with the center point of the image as the center and the determined maximum number of pixels / 2 (for example, 115 pixels) as the radius can be determined as the area for circle detection and fitting in the binary human eye image.

[0056] Optionally, a certain offset can be considered. For example, the annular area enclosed by a circle with the center point of the image as the center and the number of pixels obtained by the determined minimum number of pixels / 2 (for example, 45 pixels) - the predetermined offset (for example, 10 pixels) as the radius, and a circle with the center point of the image as the center and the maximum number of pixels determined / 2 (for example, 115 pixels) + the predetermined offset (for example, 10 pixels) as the radius can be determined as the area in the binary human eye image for circle detection and fitting.

[0057] After determining the area for circle detection and fitting in the binary human eye image, circle detection and fitting can be performed in the determined area for circle detection and fitting based on a preset sensitivity value to obtain the number of pixels occupied by the outer diameter of the backlight ring in the binary human eye image. The sensitivity value can be determined to be between 0.95 and 0.99, for example.

[0058] Therefore, by setting the range of the number of pixels occupied by the back aperture diameter and the sensitivity value, the circle in the area determined for circle detection and fitting can be detected and fitted more quickly and accurately, thereby improving the speed and accuracy of circle detection and fitting.

[0059] Back to Figure 2 At frame 210, based on the number of pixels occupied by the outer diameter of the backlight circle obtained, the corneal curvature radius of the human eye image is determined through a preset formula.

[0060] The curvature radius can be calculated by the formula relationship between the image size of the backlight circle and the actual backlight circle size (here the radius of the backlight circle is used as a reference). The formula relationship is as follows: r = 2xD, such as Fig.11 As shown, r is the radius of curvature, x is the magnification of the image, that is, x=h / H, h is the size of the backlight circle image radius, H is the radius of the actual object of the backlight circle, and D is the distance from the actual backlight circle to the image. r=2h / H*D=h*(2D / H)=radii*pixelsize*(2D / H), where r represents the radius of corneal curvature, radii represents the number of pixels occupied by the acquired outer circle diameter of the backlight circle / 2, that is, the number of pixels occupied by the acquired outer circle radius of the backlight circle, pixelsize represents the pixel size of the image acquisition device, and 2D / H represents the coefficient. Pixelsize can be acquired in advance, and 2D / H can be determined empirically. For example, r=radii*0.025*4.06, and the radius of corneal curvature can be determined by this formula. The following will refer to Figure 8 , a method for determining the corneal curvature radius of a human eye image is described in detail.

[0061] At block 802, the pixel size of an image acquisition device is obtained.

[0062] In some embodiments, a standard resolution board image may be acquired through an image acquisition device, and the standard resolution board image includes a plurality of line pairs. The line pair may be composed of a dark portion and a bright portion. Fig. 9 As shown, the standard resolution plate image 900 may include multiple groups of line pairs, the fourth group of line pairs 901 may include multiple line pairs, 2 line pairs correspond to 1 mm, and the second group of line pairs 902 may include multiple line pairs, 1 line pair corresponds to 1 mm.

[0063] Subsequently, the standard resolution plate image may be binarized to generate a binary standard resolution plate image. Hole filling may be performed on the binary standard resolution plate image to obtain filled line pairs. The filled line pairs may be as follows: Fig.10 The filling process can be found above and will not be described here.

[0064] Next, the number of pixels occupied by the filled line pairs can be determined. Based on the determined number of pixels and the predetermined size of the line pairs, the pixel size of the image acquisition device is determined. Fig.10 As shown, the number of pixels occupied by the filled line pairs can be determined by a straight line passing through the line pairs. For example, for the second group of line pairs 902, the number of pixels occupied by 1.5 line pairs can be calculated to be 63, and thus the pixel size of the image acquisition device is calculated as pixelsize=1.5mm / 63=0.025mm=25um. Similarly, for the fourth group of line pairs 901, the number of pixels occupied by 1.5 line pairs can be calculated to be 30, and the pixel size of the image acquisition device is calculated as pixelsize=(3 / 4)mm / 30=25um.

[0065] Back to Figure 8 At block 804, a first coefficient of the corneal curvature radius relative to the outer diameter of the backlight circle is determined based on the pixel size, the minimum pixel number range, and the minimum corneal curvature radius.

[0066] For example, for R5, the minimum number of pixels ranges from 90 to 100. The average number of pixels occupied by the radius is 95. By reversing the formula r=radii*pixelsize*(2D / H), 5=47.5*0.025*(2D / H), the first coefficient 2D / H=4.21.

[0067] At block 806 , a second coefficient of the corneal curvature radius relative to the outer diameter of the backlight circle is determined based on the pixel size, the maximum pixel number range, and the maximum corneal curvature radius.

[0068] For example, for R11, the maximum number of pixels ranges from 220 to 230. The average number of pixels occupied by the radius is 225. By reversing the formula r=radii*pixelsize*(2D / H), 11=112.5*0.025*(2D / H), the second coefficient 2D / H=3.91.

[0069] At block 808, a final coefficient of the corneal curvature radius relative to the backlight outer diameter is determined based on the first coefficient and the second coefficient. For example, the first coefficient and the second coefficient may be averaged to determine the final coefficient, such as (4.21+3.91) / 2=4.06. It should be understood that the numerical values ​​here are only for illustration.

[0070] At block 810 , the corneal curvature radius of the human eye image is determined based on the final coefficient and the number of pixels occupied by the acquired outer diameter of the backlight circle.

[0071] For example, the corneal curvature radius of the human eye image can be determined by r=radii*pixelsize*a, where r represents the corneal curvature radius, raddi represents the number of pixels occupied by the outer circle diameter of the backlight circle / 2, that is, the number of pixels occupied by the outer circle radius of the backlight circle, pixelsize represents the pixel size, and a represents the final coefficient determined, for example, r=radii*0.025*4.06.

[0072] Therefore, by determining the range of the number of pixels occupied by the back aperture diameter, all interference circles outside the conditions are excluded, the accuracy of detecting the fitting circle is improved, and the calculation accuracy of the corneal curvature radius is improved, so that the error range of the curvature radius is within 0.05mm, which meets the ophthalmic medical evaluation standards. In addition, the circle in the image is identified by the circular Hough transform method to determine the pixel value occupied by the back aperture diameter. The circle recognition algorithm can adjust the recognition sensitivity and ignore the external light spot interference, because non-circular objects can be directly not recognized, which effectively improves the stability and efficiency of the algorithm.

[0073] In some embodiments, after the corneal curvature radius is determined, the diopter may also be determined by the following formula: k=0.337*1000 / r, where k represents the diopter and r represents the corneal curvature radius.

[0074] Fig.12 The block diagram of an electronic device 1200 suitable for implementing the embodiments of the present disclosure is schematically shown. The device 1200 can be used to implement Figure 1 The computing device 100 of the present invention is shown in the figure. As shown in the figure, the device 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 1202 or computer program instructions loaded from a storage unit 1208 to a random access memory (RAM) 1203. In the RAM 1203, various programs and data required for the operation of the device 1200 can also be stored. The CPU 1201, the ROM 1202, and the RAM 1203 are connected to each other via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0075] A number of components in the device 1200 are connected to the I / O interface 1205, including: an input unit 1206, such as a keyboard, a mouse, etc.; an output unit 1207, such as various types of displays, speakers, etc.; a storage unit 1208, such as a disk, an optical disk, etc.; and a communication unit 1209, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1209 allows the device 1200 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0076] The processing unit 1201 performs the various methods and processes described above, such as performing methods 200 and 800. For example, in some embodiments, the methods 200 and 800 may be implemented as a computer software program, which is stored in a machine-readable medium, such as a storage unit 1208. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1200 via the ROM 1202 and / or the communication unit 1209. When the computer program is loaded into the RAM 1203 and executed by the CPU 1201, one or more operations of the methods 200 and 800 described above may be performed. Alternatively, in other embodiments, the CPU 1201 may be configured to perform one or more actions of the methods 200 and 800 by any other suitable means (e.g., by means of firmware).

[0077] The present disclosure may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present disclosure.

[0078] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0079] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0080] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0081] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0082] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0083] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0084] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0085] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for determining the radius of corneal curvature, comprising: Determining a minimum pixel number range and a maximum pixel number range occupied by the outer circle diameter of the backlight circle based on a plurality of first keratometer images having a minimum corneal curvature radius and a plurality of second keratometer images having a maximum corneal curvature radius; Determining a backlight area range based on the maximum pixel number range and the preset offset; Collecting a human eye image, wherein the distance between the center point of the cornea in the human eye image and the center point of the image is less than or equal to the preset offset, and the backlight circle in the human eye image is located within the backlight circle area; Based on the maximum pixel number range and the minimum pixel number range, circle detection and fitting are performed on the human eye image to obtain the number of pixels occupied by the outer circle diameter of the backlight circle in the human eye image; as well as Based on the number of pixels occupied by the outer diameter of the backlight circle obtained, the corneal curvature radius of the human eye image is determined through a preset formula.

2. The method according to claim 1, wherein determining the minimum pixel number range comprises: Binarizing the plurality of first keratometer images to generate a plurality of first binary images; Perform hole filling on the plurality of first binary images to obtain a plurality of first filled back aperture areas; Determining a plurality of first diameter pixel numbers of the plurality of first filled back aperture areas; as well as The minimum pixel number range is generated based on the multiple first diameter pixel numbers.

3. The method according to claim 1, wherein determining the maximum pixel number range comprises: Binarizing the plurality of second keratometer images to generate a plurality of second binary images; Performing hole filling on the plurality of second binary images to obtain a plurality of second filled back aperture areas; Determining a plurality of second diameter pixel numbers of the plurality of second filled back aperture areas; as well as The maximum pixel number range is generated based on the plurality of second diameter pixel numbers.

4. The method according to claim 1, wherein determining the backlight area range comprises: Determining the maximum number of pixels in the maximum pixel number range; as well as Based on the maximum number of pixels and the preset offset, the backlight circle area range is determined.

5. The method according to claim 1, wherein performing circle detection and fitting on the human eye image comprises: Performing smoothing filtering on the human eye image to generate a smoothed filtered human eye image; Binarizing the smoothed and filtered human eye image to generate a binary human eye image; as well as Based on the maximum pixel number range and the minimum pixel number range, circle detection and fitting are performed on the binary human eye image to obtain the number of pixels occupied by the outer circle diameter of the backlight circle in the binary human eye image.

6. The method according to claim 5, wherein performing circle detection and fitting on the binary human eye image comprises: Based on the maximum pixel number range and the minimum pixel number range, determining an area in the binary human eye image for circle detection and fitting; as well as Based on the preset sensitivity value, circle detection and fitting are performed in the determined area for circle detection and fitting to obtain the number of pixels occupied by the outer circle diameter of the backlight circle in the binary human eye image.

7. The method according to claim 1, wherein determining the corneal curvature radius of the human eye image comprises: Obtaining the pixel size of the image acquisition device; Determine a first coefficient of the corneal curvature radius relative to the outer diameter of the backlight circle based on the pixel size, the minimum pixel number range and the minimum corneal curvature radius; Determine a second coefficient of the corneal curvature radius relative to the outer diameter of the backlight circle based on the pixel size, the maximum pixel number range, and the maximum corneal curvature radius; Determining a final coefficient of the corneal curvature radius relative to the outer diameter of the back aperture circle based on the first coefficient and the second coefficient; and The corneal curvature radius of the human eye image is determined based on the final coefficient and the number of pixels occupied by the acquired backlight circle outer circle diameter.

8. The method according to claim 7, wherein obtaining the pixel size of the image acquisition device comprises: Acquiring a standard resolution board image via the image acquisition device, the standard resolution board image comprising a plurality of line pairs; Binarizing the standard resolution plate image to generate a binary standard resolution plate image; Performing hole filling on the binary standard resolution plate image to obtain filled line pairs; Determining the number of pixels occupied by the filled line pairs; as well as The pixel size of the image acquisition device is determined based on the determined number of pixels and the predetermined size of the line pairs.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8.

11. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images