An image processing method based on intelligent pupil monitoring

Abstract

The present invention relates to the field of image processing technology, and in particular to an image processing method based on pupil intelligent monitoring, comprising: obtaining pupil plane image information, determining a pupil center point and an interference influence evaluation value of the pupil plane image; preprocessing the pupil plane image; preliminarily determining a unit construction point and a cell of a pupil stereo image; increasing the distance between the unit construction point and the pupil center point in the pupil stereo image and the area of ​​the cell according to the distance between the midpoint of a subdomain and the pupil center point of the pupil plane image; preliminarily filling the cells of the pupil stereo image according to the chromaticity mean of the subdomain; increasing the brightness of the cells of the pupil stereo image according to the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image and performing brightness correction; determining a processing strategy when the processing of the pupil image does not meet a preset standard according to the image continuity of the pupil stereo image, thereby realizing effective conversion from the pupil plane image to the pupil stereo image.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an image processing method based on intelligent pupil monitoring. Background Art

[0002] Intelligent pupil monitoring refers to the continuous and accurate monitoring and analysis of the pupil through high-precision sensors, advanced image processing algorithms and artificial intelligence technology to obtain information on pupil changes, and based on this, evaluate the individual's physiological state, health status or perform identity authentication. Intelligent pupil monitoring is widely used in medical health, human-computer interaction, security authentication and other fields.

[0003] Chinese patent publication number: CN117745929A, discloses a three-dimensional reconstruction method, device, electronic device and storage medium of an eyeball, and relates to the field of three-dimensional modeling technology. It includes: obtaining a first eyeball image; generating a second eyeball image set corresponding to each preset shooting angle according to the first eyeball image, wherein the preset shooting angle is different from the shooting angle of the first eyeball image; determining the target eyeball image corresponding to each preset shooting angle according to the quality of each second eyeball image in the second eyeball image set; and reconstructing the eyeball in the first eyeball image in three dimensions based on multiple target eyeball images and the first eyeball image. Thus, based on a real first eyeball image, the target eyeball images corresponding to other obscured shooting angles can be predicted, and the three-dimensional model of the eyeball can be obtained based on the first eyeball image and multiple target eyeball images. It can be seen that the construction process of the pupil stereo image in the above technical solution is equipment-dependent and costly. Summary of the invention

[0004] To this end, the present invention provides an image processing method based on intelligent pupil monitoring to overcome the problems of equipment dependence and high cost in the process of constructing pupil stereo images in the prior art.

[0005] To achieve the above object, the present invention provides an image processing method based on intelligent pupil monitoring, comprising:

[0006] Obtain pupil plane image information;

[0007] Determine the pupil center point and interference influence evaluation value of the pupil plane image;

[0008] Determining a preprocessing strategy of the pupil plane image based on the interference influence evaluation value includes dividing the pupil plane image into subdomains after performing a de-interference process on the pupil plane image, or directly dividing the pupil plane image into a plurality of subdomains;

[0009] Preliminarily determining a unit construction point of a pupil stereo image and a cell of the pupil stereo image according to a midpoint of a single sub-domain;

[0010] According to the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image, the distance between the unit construction point and the pupil center point in the pupil stereo image is increased, and the area of ​​the cell of the pupil stereo image is increased;

[0011] Preliminarily filling cells corresponding to the pupil stereo image according to the chromaticity mean value of a single sub-domain;

[0012] Increasing the brightness of the pupil stereoscopic image cell according to the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image;

[0013] Correcting the brightness of the pupil stereoscopic image cell when the distance between the center point of the pupil stereoscopic image cell and the center point of the virtual eyeball is greater than a preset distance threshold;

[0014] When it is determined that the processing of the pupil image does not meet the preset standard according to the image continuity of the pupil stereo image, the distance between the unit construction point and the pupil midpoint in the pupil stereo image is corrected, or the division size of the pupil plane image subdomain is reduced.

[0015] Furthermore, the interference influence evaluation value is determined according to the absolute value of the brightness difference between points equidistant on both sides of the pupil center point of the pupil plane image.

[0016] Furthermore, the determination process of the preprocessing strategy of the pupil plane image includes:

[0017] Obtaining the interference impact evaluation value;

[0018] Comparing the interference impact evaluation value with a preset interference impact evaluation value;

[0019] If the interference influence evaluation value is less than the preset interference influence evaluation value, it is determined that the preprocessing strategy of the pupil plane image is to directly divide the pupil plane image into a plurality of subdomains;

[0020] If the interference influence evaluation value is greater than or equal to the preset interference influence evaluation value, it is determined that the preprocessing strategy of the pupil plane image is to perform de-interference processing on the pupil plane image and then divide the image into sub-domains.

[0021] Furthermore, the process of performing de-interference processing on the pupil plane image includes:

[0022] Obtain the brightness of each point of the pupil plane image;

[0023] Compare the brightness of each point with the brightness of the center point of the pupil plane image;

[0024] If the brightness of the point is greater than the brightness of the center point of the pupil plane image, the brightness of the point is reduced to the brightness of a symmetrical point that is symmetrical to the point about the center point of the pupil plane image.

[0025] Further, the increase range of the distance between the unit construction point and the pupil center point in the pupil stereoscopic image is the same as the increase range of the area of ​​the unit cell of the pupil stereoscopic image.

[0026] Further, the increase amplitude of the distance between the unit construction point and the pupil center point in the pupil stereo image is positively correlated with the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image.

[0027] Furthermore, the increase amplitude of the brightness of the pupil stereoscopic image cell is positively correlated with the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image.

[0028] Further, the process of determining whether the processing of the pupil image does not meet the standard according to the image continuity of the pupil stereoscopic image includes:

[0029] Comparing the image continuity with a first preset continuity threshold and a second preset continuity threshold respectively;

[0030] If the image continuity is greater than or equal to the first preset continuity threshold and less than the second preset continuity threshold, correcting the distance between the unit construction point and the pupil midpoint in the pupil stereo image according to the difference between the image continuity and the first preset continuity threshold;

[0031] If the image continuity is greater than or equal to the second preset continuity threshold, the division size of the pupil plane image sub-domain is reduced according to the difference between the image continuity and the second preset continuity threshold.

[0032] Further, the image continuity is determined based on the brightness difference between all pupil stereoscopic image cells that the baseline passes through.

[0033] Furthermore, several reduction methods are provided for reducing the size of the subdomains of the pupil plane image, and each reduction method has a different reduction range for the size of the subdomains of the pupil plane image.

[0034] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention obtains pupil plane image information, determines the pupil center point of the pupil plane image and sets the interference influence evaluation value to pre-process the pupil plane image; preliminarily determines the unit construction point and the cell of the pupil stereo image according to the midpoint of a single subdomain; increases the distance between the unit construction point and the pupil center point in the pupil stereo image and the area of ​​the cell according to the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image; preliminarily fills the pupil stereo image cell according to the chromaticity mean of the subdomain; increases the brightness of the pupil stereo image cell according to the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image and performs brightness correction; determines the processing strategy when the processing of the pupil image does not meet the preset standard according to the image continuity of the pupil stereo image, thereby realizing the effective conversion from a single pupil plane image to a pupil stereo image and reducing the technical cost.

[0035] Furthermore, the present invention compares the interference influence evaluation value with the preset interference influence evaluation value to determine whether to perform de-interference processing and then divide the subdomains, or to directly perform subdomain division, thereby improving the efficiency of image processing.

[0036] Furthermore, the present invention performs de-interference processing on the pupil plane image to reduce the brightness of points whose brightness is greater than the brightness of the pupil center point to the brightness of its symmetrical points, thereby eliminating the interference of the high-brightness sub-domain on the overall pupil plane image.

[0037] Furthermore, the present invention reduces image distortion by setting the increase range of the distance between the unit construction point and the pupil center point in the pupil stereo image to be the same as the increase range of the area of ​​the pupil stereo image unit cell.

[0038] Furthermore, the present invention realizes dynamic adjustment of the distance by setting the increase amplitude of the distance between the unit construction point and the pupil center point in the pupil stereo image to be positively correlated with the distance between the subdomain midpoint and the pupil center point in the pupil plane image.

[0039] Furthermore, the present invention quantifies the image continuity by setting the brightness difference between all pupil stereoscopic image cells that the baseline passes through, thereby achieving accurate optimization of the pupil stereoscopic image.

[0040] Furthermore, the present invention determines a processing strategy when processing of the pupil image does not meet the standard based on the first preset continuity threshold and the second preset continuity threshold, thereby achieving accurate determination of the processing strategy.

[0041] Furthermore, the present invention provides several reduction methods for reducing the size of the sub-domains, thereby achieving precise adjustment of the reduction of the size of the sub-domains of the pupil plane image. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of an image processing method based on intelligent pupil monitoring according to an embodiment of the present invention;

[0043] Figure 2 A flowchart of a preprocessing strategy for determining pupil plane images according to an embodiment of the present invention;

[0044] Figure 3 A flowchart of an embodiment of the present invention for determining whether processing of a pupil image meets a standard;

[0045] Figure 4 The present invention is a flowchart of a method for determining a reduction method for dividing subdomains of a pupil plane image into smaller sizes according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] It should be pointed out that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical detection data and the corresponding historical detection results three months before the image processing by the method of the present invention. It can be understood by those skilled in the art that the method of the present invention can determine the above parameters for a single item by selecting the value with the highest proportion as the preset standard parameter according to the data distribution, using weighted summation to use the obtained value as the preset standard parameter, substituting each historical data into a specific formula and using the value obtained by the formula as the preset standard parameter or other selection methods, as long as the method of the present invention can clearly define the different specific situations in the single determination process through the obtained values.

[0048] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0049] See also Figure 1 , Figure 2 , Figure 3 as well as Figure 4 As shown, they are respectively a flow chart of an image processing method based on intelligent pupil monitoring according to an embodiment of the present invention; a flow chart of a preprocessing strategy for determining a pupil plane image according to an embodiment of the present invention; a flow chart of a method for determining whether the processing of a pupil image meets the standard according to an embodiment of the present invention; and a flow chart of a method for determining a reduction in the division size of a subdomain of a pupil plane image according to an embodiment of the present invention.

[0050] An image processing method based on intelligent pupil monitoring according to an embodiment of the present invention includes:

[0051] Step S1, obtaining pupil plane image information;

[0052] Step S2, determining the pupil center point and interference influence evaluation value of the pupil plane image;

[0053] Step S3, determining a preprocessing strategy of the pupil plane image based on the interference influence evaluation value, including performing de-interference processing on the pupil plane image and then dividing the pupil plane image into subdomains, or directly dividing the pupil plane image into a plurality of subdomains;

[0054] Step S4, preliminarily determining a unit construction point of a pupil stereoscopic image and a pupil stereoscopic image unit cell according to a midpoint of a single sub-domain;

[0055] Step S5, increasing the distance between the unit construction point and the pupil center point in the pupil stereo image according to the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image, and increasing the area of ​​the cell of the pupil stereo image;

[0056] Step S6, preliminarily filling the corresponding pupil stereoscopic image cells according to the chromaticity mean value of a single sub-domain;

[0057] Step S7, increasing the brightness of the pupil stereoscopic image cell according to the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image;

[0058] Step S8, correcting the brightness of the pupil stereoscopic image cell when the distance between the center point of the pupil stereoscopic image cell and the center point of the virtual eyeball is greater than a preset distance threshold;

[0059] Step S9, when it is determined that the processing of the pupil image does not meet the preset standard according to the image continuity of the pupil stereo image, the distance between the unit construction point and the pupil midpoint in the pupil stereo image is corrected, or the division size of the pupil plane image subdomain is reduced.

[0060] Specifically, the interference impact evaluation value is calculated by the following formula:

[0061] E=∣L(P1)-L(P2)∣=∣L(x1, y1)-L(x2, y2)∣

[0062] In the formula, a two-dimensional rectangular coordinate system is established with the pupil center point of the pupil plane image as the origin, the x-axis is a horizontal straight line passing through the pupil center point, and the y-axis is a vertical straight line passing through the pupil center point. The center point is O(0,0), and the points with equal spacing on both sides are P1(x1,y1) and P2(x2,y2), where P1 and P2 are symmetrical about the center point O, L(x,y) represents the brightness value of the image at point (x,y), and E represents the interference impact evaluation value, where the distance between P1 and P2 and the pupil center point is less than or equal to the radius of the iris in the pupil plane image.

[0063] Specifically, the brightness can be measured by, for example, a brightness meter, and the chromaticity mean can be obtained by, for example, Adobe Photoshop. There is no specific limitation, as long as the image brightness can be measured.

[0064] Specifically, the determination process of the preprocessing strategy of the pupil plane image includes:

[0065] Obtaining interference impact evaluation value;

[0066] The interference impact evaluation value is compared with a preset interference impact evaluation value,

[0067] If the interference influence evaluation value is less than the preset interference influence evaluation value, it is determined that the preprocessing strategy of the pupil plane image is to directly divide the pupil plane image into a plurality of subdomains;

[0068] If the interference influence evaluation value is greater than or equal to the preset interference influence evaluation value, it is determined that the preprocessing strategy of the pupil plane image is to perform de-interference processing on the pupil plane image and then divide the image into sub-domains.

[0069] Specifically, the preset interference impact evaluation value is set to 86.58Nit.

[0070] Specifically, the process of performing de-interference processing on the pupil plane image includes:

[0071] Obtain the brightness of each point of the pupil plane image;

[0072] Compare the brightness of each point with the brightness of the center point of the pupil plane image;

[0073] If the brightness of the point is greater than the brightness of the center point of the pupil plane image, the brightness of the point is reduced to the brightness of a symmetrical point that is symmetrical to the point about the center point of the pupil plane image.

[0074] Specifically, the increase range of the distance between the unit construction point and the pupil center point in the pupil stereoscopic image is the same as the increase range of the area of ​​the unit cell of the pupil stereoscopic image.

[0075] Specifically, the increase in the distance between the unit construction point and the pupil center point in the pupil stereo image is positively correlated with the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image. For example, the increase in the distance between the unit construction point and the pupil center point in the pupil stereo image is set to △D, and the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image is set to △Φ, then △D=α×△Φ, α is the distance adjustment coefficient, and α is set to 1.02. It can be understood that the larger the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image, the greater the increase in the distance between the unit construction point and the pupil center point in the pupil stereo image.

[0076] Specifically, the increase in the brightness of the pupil stereoscopic image cell is positively correlated with the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image. For example, the increase in the brightness of the pupil stereoscopic image cell is set to △M, and the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image is set to △Φ, then △M=β×△Φ, β is the brightness adjustment coefficient, and β is set to 1.22. It can be understood that the greater the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image, the greater the increase in the brightness of the pupil stereoscopic image cell.

[0077] Specifically, the process of determining whether the processing of the pupil image meets the standard according to the image continuity of the pupil stereoscopic image includes:

[0078] Comparing the image continuity with a first preset continuity threshold and a second preset continuity threshold respectively;

[0079] If the image continuity is less than the first preset continuity threshold, determining that the processing of the pupil image meets the preset standard and outputting a pupil stereoscopic image that meets the preset standard;

[0080] If the image continuity is greater than or equal to the first preset continuity threshold and less than the second preset continuity threshold, it is determined that the processing of the pupil image does not meet the preset standard and the distance between the unit construction point and the pupil midpoint in the pupil stereo image is corrected according to the difference between the image continuity and the first preset continuity threshold;

[0081] If the image continuity is greater than or equal to the second preset continuity threshold, it is determined that the processing of the pupil image does not meet the preset standard and the size of the sub-domains of the pupil plane image is reduced according to the difference between the image continuity and the second preset continuity threshold;

[0082] The first preset continuity threshold is set to 1.06, and the second preset continuity threshold is set to 13.16.

[0083] Specifically, the image continuity is calculated by the following formula:

[0084]

[0085] In the formula, A represents image continuity, f(m) represents the absolute value of the brightness difference between the boundaries of the mth adjacent cells, where m=1,2...j-1, j represents the total number of all pupil stereo image cells passing through the baseline, where the baseline is a curve passing through the center point of the pupil in the pupil stereo image.

[0086] Specifically, there are several reduction methods for reducing the size of the pupil plane image subdomains, wherein:

[0087] If the image continuity difference is less than the first preset difference of 0.45, then using the first preset adjustment coefficient of 0.94 to reduce the division size of the pupil plane image subdomain;

[0088] If the image continuity difference is greater than or equal to the first preset difference of 0.45 and less than the second preset difference of 1.38, then using the second preset adjustment coefficient of 0.83 to reduce the division size of the pupil plane image subdomain;

[0089] If the image continuity difference is greater than or equal to the second preset difference 1.38, then using a third preset adjustment coefficient of 0.76 to reduce the division size of the pupil plane image subdomain;

[0090] The image continuity difference is a difference between the image continuity and the second preset continuity threshold.

[0091] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An image processing method based on intelligent pupil monitoring, characterized in that: include: Obtain pupil plane image information; Determine the pupil center point and interference influence evaluation value of the pupil plane image; Determining a preprocessing strategy of the pupil plane image based on the interference influence evaluation value includes dividing the pupil plane image into subdomains after performing a de-interference process on the pupil plane image, or directly dividing the pupil plane image into a plurality of subdomains; Preliminarily determining a unit construction point of a pupil stereo image and a cell of the pupil stereo image according to a midpoint of a single sub-domain; According to the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image, the distance between the unit construction point and the pupil center point in the pupil stereo image is increased, and the area of ​​the cell of the pupil stereo image is increased; Preliminarily filling cells corresponding to the pupil stereo image according to the chromaticity mean value of a single sub-domain; Increasing the brightness of the pupil stereoscopic image cell according to the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image; Correcting the brightness of the pupil stereoscopic image cell when the distance between the center point of the pupil stereoscopic image cell and the center point of the virtual eyeball is greater than a preset distance threshold; When it is determined that the processing of the pupil image does not meet the preset standard according to the image continuity of the pupil stereo image, the distance between the unit construction point and the pupil midpoint in the pupil stereo image is corrected, or the division size of the pupil plane image subdomain is reduced.

2. The image processing method based on intelligent pupil monitoring according to claim 1, characterized in that: The interference influence evaluation value is determined according to the absolute value of the brightness difference between equally spaced points on both sides of the pupil center point of the pupil plane image.

3. The image processing method based on intelligent pupil monitoring according to claim 2 is characterized in that: The determination process of the preprocessing strategy of the pupil plane image includes: Obtaining the interference impact evaluation value; Comparing the interference impact evaluation value with a preset interference impact evaluation value; If the interference influence evaluation value is less than the preset interference influence evaluation value, it is determined that the preprocessing strategy of the pupil plane image is to directly divide the pupil plane image into a plurality of subdomains; If the interference influence evaluation value is greater than or equal to the preset interference influence evaluation value, it is determined that the preprocessing strategy of the pupil plane image is to perform de-interference processing on the pupil plane image and then divide the image into sub-domains.

4. The image processing method based on pupil intelligent monitoring according to claim 3 is characterized in that: The process of performing de-interference processing on the pupil plane image includes: Obtain the brightness of each point of the pupil plane image; Compare the brightness of each point with the brightness of the center point of the pupil plane image; If the brightness of the point is greater than the brightness of the center point of the pupil plane image, the brightness of the point is reduced to the brightness of a symmetrical point that is symmetrical to the point about the center point of the pupil plane image.

5. The image processing method based on intelligent pupil monitoring according to claim 4 is characterized in that: The increase range of the distance between the unit construction point and the pupil center point in the pupil stereoscopic image is the same as the increase range of the area of ​​the unit cell of the pupil stereoscopic image.

6. The image processing method based on intelligent pupil monitoring according to claim 5, characterized in that: The increase in the distance between the unit construction point and the pupil center point in the pupil stereo image is positively correlated with the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image.

7. The image processing method based on intelligent pupil monitoring according to claim 6, characterized in that: The increase amplitude of the brightness of the pupil stereoscopic image cell is positively correlated with the distance between the midpoint of the subdomain and the pupil center point of the pupil plane image.

8. The image processing method based on intelligent pupil monitoring according to claim 1, characterized in that: The process of determining, according to the image continuity of the pupil stereoscopic image, that the processing of the pupil image does not meet the standard comprises: Comparing the image continuity with a first preset continuity threshold and a second preset continuity threshold respectively; If the image continuity is greater than or equal to the first preset continuity threshold and less than the second preset continuity threshold, correcting the distance between the unit construction point and the pupil midpoint in the pupil stereo image according to the difference between the image continuity and the first preset continuity threshold; If the image continuity is greater than or equal to the second preset continuity threshold, the division size of the pupil plane image sub-domain is reduced according to the difference between the image continuity and the second preset continuity threshold.

9. The image processing method based on intelligent pupil monitoring according to claim 8, characterized in that: The image continuity is determined based on the brightness difference between all pupil stereo image cells that the baseline passes through.

10. The image processing method based on intelligent pupil monitoring according to claim 9, characterized in that: There are several reduction methods for reducing the size of the subdomains of the pupil plane image, and each reduction method has a different reduction range for the size of the subdomains of the pupil plane image.

Images