A pterygium detection method and mobile terminal

Abstract

The present invention discloses a pterygium detection method, which is suitable for execution in a mobile terminal, and the method comprises the steps of: collecting an eye image sequence of a user to be tested, selecting a qualified target image therefrom, wherein the target image includes a pupil area, an iris area, a sclera area, and an eyelid and an eye corner area in sequence from the inside to the outside; detecting the pupil contour, the iris contour, and the eyelid contour of the target image, and marking the intrusion area of ​​the pterygium according to the detection result; obtaining the measured contour line or the fitted contour line of the intrusion area, and determining one or more seed points in the intrusion area; taking the seed point as the starting point, using a region growth algorithm to obtain the pterygium in the intrusion area, and the region growth algorithm stops growing when it grows to the contour line of the region; and calculating the probability value of the pterygium appearing in the target image according to the region growth results of each region. The present invention also discloses a mobile terminal for executing the method.

Description

Technical Field

[0001] The present invention relates to the AI ​​(Artificial Intelligence) medical field, and in particular to a pterygium detection method and a mobile terminal. Background Art

[0002] Pterygium is a common and frequently occurring ophthalmic disease. It is often seen on the side of the nose and is triangular in shape. It is a growth of tissue on the conjunctiva and cornea at the palpebral fissure. When pterygium covers the cornea, it may cause astigmatism. After invading the cornea, it gradually increases in size and may even cover the pupil area, seriously affecting vision.

[0003] Pterygium can be in a quiescent or progressive stage. In the quiescent stage, pterygium does not grow for many years, has a flat head, a body without congestion, a smooth surface, and is film-like. Pterygium in this stage can be observed without treatment. In the progressive stage, pterygium continues to grow and expand, with a bulging head, a thickened body, an uneven surface, and large and dilated blood vessels. It looks red due to congestion, and pterygium in this stage may require surgical treatment.

[0004] There is no generally accepted theory on the cause of pterygium. It is generally believed that it is closely related to long-term exposure to ultraviolet rays. It may also be related to long-term chronic stimulation such as dust, chemical stimulation, and smoke. Therefore, carrying out extensive regular examinations, early warnings, disease assessments and other measures among susceptible populations will help to detect and treat them as early as possible. The traditional method requires doctors to conduct offline on-site diagnosis of patients in person, which requires patients to go to the site, which is inconvenient and inconvenient. Even if the patient goes to the site to take an eye image, most of the existing technologies are based on the iris circle to identify pterygium in the iris area. In fact, pterygium can be distributed in multiple areas of the eye, and it is not accurate to identify the iris alone. Summary of the invention

[0005] To this end, the present invention provides a pterygium detection method and a mobile terminal, in an effort to solve or at least alleviate the above problems.

[0006] According to one aspect of the present invention, a pterygium detection method is provided, which is suitable for execution in a mobile terminal, and the method comprises the steps of: acquiring a sequence of eye images of a user to be tested, selecting a qualified target image therefrom, wherein the target image includes, from the inside to the outside, a pupil area, an iris area, a sclera area, and an eyelid and eye corner area; detecting the pupil contour, the iris contour, and the eyelid contour of the target image, and determining the invasion area of ​​the pterygium according to the detection results; obtaining a measured contour line or a fitted contour line of the invasion area, and determining one or more seed points in the invasion area; taking the seed point as a starting point, using a region growing algorithm to obtain the pterygium of the invasion area, and the region growing algorithm stops growing when it grows to the contour line of the region; and calculating the probability value of the pterygium appearing in the target image according to the region growing results of each region.

[0007] Optionally, the pterygium detection method according to the present invention also includes the steps of: using a region growing algorithm to identify a complete pterygium containing the seed point from the seed point of the invasion area; and taking the union of the complete pterygium identified in all invasion areas as the total area of ​​the pterygium in the target image.

[0008] Optionally, in the pterygium detection method according to the present invention, the seed point is any one of the following: a pterygium point specified by a user, a random point in each area, or a feature point identified based on prior knowledge of pterygium.

[0009] Optionally, in the pterygium detection method according to the present invention, the region growing algorithm performs identification based on pixel color and pixel brightness, and the region growing result includes the area ratio of the pterygium in each intrusion region.

[0010] Optionally, in the pterygium detection method according to the present invention, the probability value is calculated based on the brightness and color differences between the pterygium and the pupil area, iris area, and sclera area, and prior knowledge of the brightness and color of the pterygium.

[0011] Optionally, the pterygium detection method according to the present invention further includes the step of uploading the target image, area percentage, probability value and user information to the server for storage.

[0012] Optionally, in the pterygium detection method according to the present invention, the detection result includes any one of the following: pupil contour completeness, left and right pupil difference, iris contour completeness, left and right iris difference, left and right sclera difference, and color and brightness difference from normal eyes.

[0013] Optionally, in the pterygium detection method according to the present invention, the mobile terminal has a pterygium detection application, the application has an eye position prompt box and a photo button, and the step of collecting a sequence of eye images of the user to be tested includes: under the guidance of the eye position prompt box, calling the camera lens assembly of the mobile terminal through the photo button of the application to obtain multiple eye images of the user to be tested, and the eye images do not contain scene reflection spots.

[0014] Optionally, in the pterygium detection method according to the present invention, the eye position prompt box has an eye contour prompt line and / or an eye feature prompt point; the eye contour prompt line includes an eyelid contour line and / or an iris contour line; the eye feature prompt point includes a left eye corner positioning point and / or a right eye corner positioning point.

[0015] Optionally, in the pterygium detection method according to the present invention, the mobile terminal has an LED fill light and / or a macro lens for collecting the eye image sequence.

[0016] Optionally, in the pterygium detection method according to the present invention, the step of selecting a qualified target image includes: selecting an image with qualified image focus, motion blur and eye angle as the target image; the image focus, motion blur and eye angle are calculated based on the camera parameters of the mobile terminal, the eye physiological parameters and the eye image sequence parameters.

[0017] Optionally, in the pterygium detection method according to the present invention, the camera parameters include focal length, optical center and distortion parameters; the eye physiological parameters include interpupillary distance, iris diameter, and relative position of pupil and iris; the eye image sequence parameters include the spectrum of each image in the image sequence, interpupillary distance, iris diameter, relative position of pupil and iris, and eccentricity of pupil and iris contours.

[0018] Optionally, in the pterygium detection method according to the present invention, the pupil contour and the iris contour are detected using a Hough circle algorithm, and the eyelid contour and the eye corner are detected using a facial feature point algorithm.

[0019] According to another aspect of the present invention, there is provided a mobile terminal, comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing the pterygium detection method as described above.

[0020] According to another aspect of the present invention, there is provided a readable storage medium storing one or more programs, wherein the one or more programs include instructions, which, when executed by a mobile terminal, enable the mobile terminal to perform the pterygium detection method as described above.

[0021] According to the technical solution of the present invention, a mobile terminal is used to obtain an eye image of a user to be tested, and the pterygium problem in the eye image can be identified through the terminal program, which can quickly screen, detect and evaluate the pterygium in the eye image, thereby realizing remote detection of pterygium. The present invention can be deployed on an application program of a mobile terminal, is easy to promote and apply, and can detect the disease early and provide medical treatment. Furthermore, the present invention can also utilize the rear camera of the mobile terminal and the fill light with occlusion and attenuation to capture eye images, detect pterygium in the progressive and quiescent stages, and generate calculation results of the severity. Afterwards, the application uploads the test results to the server to establish a patient file to assist doctors in remote diagnosis, prevention and treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To achieve the above and related purposes, certain illustrative aspects are described herein in conjunction with the following description and accompanying drawings, which indicate various ways in which the principles disclosed herein can be practiced, and all aspects and their equivalents are intended to fall within the scope of the claimed subject matter. The above and other purposes, features and advantages of the present disclosure will become more apparent by reading the following detailed description in conjunction with the accompanying drawings. Throughout the present disclosure, the same reference numerals generally refer to the same parts or elements.

[0023] Figure 1 A schematic diagram of a mobile terminal 100 according to an embodiment of the present invention is shown;

[0024] Figure 2 A flow chart of a pterygium detection method 200 according to an embodiment of the present invention is shown;

[0025] Figure 3 A schematic diagram showing various complex situations when capturing eye images according to an embodiment of the present invention;

[0026] Figure 4 and Figure 5 Schematic diagrams showing a target image according to an embodiment of the present invention and a pterygium segmentation result in the target image are shown respectively;

[0027] Figure 6 and Figure 7 Interface diagrams of an application for detecting pterygium according to an embodiment of the present invention are respectively shown. DETAILED DESCRIPTION

[0028] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary 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 enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0029] Figure 1 The mobile terminal 100 according to one embodiment of the present invention is a block diagram showing a structure of the mobile terminal 100. The mobile terminal 100 may include a memory interface 102, one or more data processors, an image processor and / or a central processing unit 104, and a peripheral interface 106.

[0030] The memory interface 102, one or more processors 104 and / or the peripheral interface 106 may be discrete components or integrated in one or more integrated circuits. In the mobile terminal 100, various components may be coupled via one or more communication buses or signal lines. Sensors, devices, and subsystems may be coupled to the peripheral interface 106 to facilitate various functions.

[0031] For example, motion sensor 110, light sensor 112, and distance sensor 114 can be coupled to peripheral interface 106 to facilitate functions such as orientation, lighting, and ranging. Other sensors 116 can also be connected to peripheral interface 106, such as a positioning system (e.g., a GPS receiver), an accelerometer, a temperature sensor, a biometric sensor, or other sensing devices, which can help implement related functions.

[0032] The camera subsystem 120 and the optical sensor 122 may be used to facilitate camera functions such as recording photographs and video clips, wherein the camera subsystem and the optical sensor may be, for example, a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS) optical sensor. Communication functions may be facilitated by one or more wireless communication subsystems 124, which may include radio frequency receivers and transmitters and / or optical (e.g., infrared) receivers and transmitters. The specific design and implementation of the wireless communication subsystem 124 may depend on one or more communication networks supported by the mobile terminal 100. For example, the mobile terminal 100 may include a device designed to support LTE, 3G, GSM networks, GPRS networks, EDGE networks, Wi-Fi or WiMax networks, and Bluebooth TM The communication subsystem 124 of the network.

[0033] The audio subsystem 126 may be coupled to a speaker 128 and a microphone 130 to facilitate voice-enabled functions such as voice recognition, voice replication, digital recording, and telephony. The I / O subsystem 140 may include a touch screen controller 142 and / or one or more other input controllers 144. The touch screen controller 142 may be coupled to a touch screen 146. For example, the touch screen 146 and the touch screen controller 142 may detect contact and movement or pause therewith using any of a variety of touch sensing technologies, including but not limited to capacitive, resistive, infrared, and surface acoustic wave technologies.

[0034] One or more other input controllers 144 may be coupled to other input / control devices 148, such as one or more buttons, rocker switches, thumb wheels, infrared ports, USB ports, and / or pointing devices such as styluses. The one or more buttons (not shown) may include an up / down button for controlling the volume of the speaker 128 and / or the microphone 130.

[0035] The memory interface 102 may be coupled to the memory 150. The memory 150 may include a high-speed random access memory and / or a non-volatile memory, such as one or more disk storage devices, one or more optical storage devices, and / or a flash memory (e.g., NAND, NOR). The memory 150 may store an operating system 152, such as an operating system such as Android, iOS, or Windows Phone. The operating system 152 may include instructions for processing basic system services and performing hardware-dependent tasks. The memory 150 may also store an application 154 (i.e., an application program, hereinafter referred to as an application). When the mobile terminal is running, the operating system 152 will be loaded from the memory 150 and executed by the processor 104. When the application 154 is running, it will also be loaded from the memory 150 and executed by the processor 104. The application 154 runs on the operating system and uses the interfaces provided by the operating system and the underlying hardware to implement various user-desired functions, such as instant messaging, web browsing, picture management, video playback, etc. The application 154 may be provided independently of the operating system or may be built-in to the operating system, including various social application software, such as QQ, WeChat, Weibo, etc., as well as various video playback and game live broadcast application software, and may also include system built-in application programs such as photo albums, calculators, and voice recorders. In addition, when the application 154 is installed in the mobile terminal 100, a driver module may also be added to the operating system.

[0036] The program for executing the pterygium detection method 200 provided in the embodiment of the present invention is a type of application 154. In some embodiments, the mobile terminal 100 is configured to execute the pterygium detection method 200 according to the present invention, and the mobile terminal may be an iOS terminal.

[0037] Figure 2 A flow chart of a pterygium detection method 200 according to an embodiment of the present invention is shown, which is suitable for being executed in a mobile terminal, such as being executed in the mobile terminal 100, and is used to detect pterygium in an eye image of a user.

[0038] like Figure 2 As shown, the method starts at step S210. In step S210, a sequence of eye images of the user to be tested is collected, and a qualified target image is selected from the sequence, the target image including the pupil area, the iris area, the sclera area, and the eyelid and eye corner area from the inside to the outside.

[0039] According to one embodiment of the present invention, a mobile terminal has a pterygium detection application, which has an eye position prompt box and a photo button. The eye position prompt box has an eye contour prompt line and / or an eye feature prompt point; the eye contour prompt line includes an eyelid contour line and / or an iris contour line; the eye feature prompt point includes a left eye corner positioning point and / or a right eye corner positioning point. The photo button can call a camera lens assembly, such as calling a rear camera. In addition, the mobile terminal has an LED fill light and / or a macro lens for collecting eye image sequences. Among them, the macro lens with self-powered LED auxiliary lighting is clamped on the rear camera of the terminal to obtain a higher resolution eye image. At this time, the photo button can turn on the fill light, the rear camera or the macro lens, etc., to obtain the eye image of the person to be tested, and the eye image is displayed on the terminal screen in the form of a preview.

[0040] Based on this, the step of collecting the eye image sequence of the user to be tested includes: under the guidance of the eye position prompt box, the camera lens assembly of the mobile terminal is called through the photo button of the application to obtain multiple eye images of the user to be tested, and the eye images do not contain the reflected light spots of the scene. Among them, the camera continuously captures images at a certain frame rate, and the images captured within a period of time are saved in the memory or storage card to obtain the eye image sequence.

[0041] Here, the eye images of the person can be obtained separately for the left and right eyes, and the person to be tested can take photos of the corresponding eye images according to the text prompts of the left and right eyes on the terminal screen. Each time a photo is taken, an eye prompt line or prompt point is displayed in a rectangular frame on the screen, which is convenient for the user to take photos after completing eye positioning.

[0042] Moreover, considering the complex situations that may be faced when capturing eye images, such as Figure 3As shown, from top to bottom af six situations are respectively emmetropia, strabismus, blocking one side of the iris and pupil, blocking both sides of the iris, opening the eyelids, and reflecting the external scenery. Therefore, the present invention provides a variety of eye positioning methods, specifically including automatic eye positioning, semi-automatic eye positioning, and semi-automatic eye feature point positioning. Automatic eye positioning is based on traditional Adaboost algorithms or algorithms such as SSD based on deep learning. The eye feature points of automatic eye positioning are LBP features or features obtained through convolutional neural network training. During semi-automatic positioning, an eye positioning frame is manually assisted to mark features that are easy for humans to understand, such as the corners of the eyes and several points on the eyelids. During acquisition, try to make the eyes fall within the prompt box on the interface. When automatic eye positioning fails, the target image captured in the prompt box can be used for the manual marking process of subsequent semi-automatic detection.

[0043] Considering that eyes with lesions may affect automatic eye detection, blinking can be used to assist eye positioning and eyelid boundary detection. If necessary, the eye position can be manually marked and tracked. For complex situations such as elderly people with loose eyelids or small eyelid openings that need to be opened for inspection, manual marking of feature points can be used to locate and track the target area.

[0044] In addition, when acquiring eye images, external light interference should be avoided and the images should be taken indoors to avoid direct sunlight. During the acquisition process, the mobile terminal and the human eye should be kept relatively stable as much as possible so that the acquisition and detection process can be completed as quickly as possible. At the same time, the visible light diffuse illumination method is used to evenly illuminate the eye area, and the light source appears as a reflected light spot on the eye image; the reflected image of indoor scenes on the cornea should also be avoided, such as brighter objects such as windows, screens, and lamps. In an ideal eye image, there is at most only a light spot of the fill light.

[0045] Moreover, the present invention can also use terminal LED fill light, slit lamp and other light sources with frosted filters or other substitutes to reduce eye irritation. Among them, the white light LED spectrum of the mobile terminal camera flash is usually composed of blue light in the range of 400-460nm and excitation light band in the range of 460-610. For visible light in the band of 305-700nm, the weighted retinal irradiance should be less than 220μW / cm2. When using a slit lamp as auxiliary lighting, it should be operated from the darkest level.

[0046] It should be understood that when photographing the eyes with a terminal, there may be a forward and backward focusing process and shaking, causing defocus blur and motion blur. In order to observe whether there is a pterygium at the corner of the eye, the subject needs to turn the eyeball left and right when collecting eye images. Therefore, it is necessary to screen the acquired image sequence to obtain the target image.

[0047] According to another embodiment of the present invention, the step of selecting a qualified target image includes: selecting an image with qualified image focus, motion blur and eye angle as the target image, wherein the image focus, motion blur and eye angle are calculated based on the camera parameters of the mobile terminal, the eye physiological parameters and the eye image sequence parameters.

[0048] Specifically, the camera parameters include focal length, optical center and distortion parameters; the eye physiological parameters include interpupillary distance, iris diameter, relative position of pupil and iris; the eye image sequence parameters include the spectrum of each image in the image sequence, interpupillary distance, iris diameter, relative position of pupil and iris, and eccentricity of pupil and iris contours. The indicators used by the present invention to select qualified images include that the spectrum of the clear image should contain more high-frequency components, and the pupil and iris contours with appropriate angles should be close to concentric circles. When the selected qualified eye image is recognized, pterygium detection is continued.

[0049] Subsequently, in step S220, the pupil contour, iris contour, and eyelid contour of the target image are detected, and the invasion area of ​​the pterygium is determined according to the detection results.

[0050] The detection result includes at least one of the following: pupil contour integrity, left and right pupil difference, iris contour integrity, left and right iris difference, left and right sclera difference, and color and brightness difference with normal eyes. The actual pupil contour may not be a complete circle, and the pupil contour integrity can be positioned as the ratio of the actual pupil contour length to the circumference of the fitted circle (length_contour_pupil_left / perimeter_circle_pupil_left). The left and right iris difference may include the difference in iris diameter (abs(d_iris_left-d_iris_right) / d_iris_right), the difference in iris area brightness histogram, etc. The present invention can judge the invasion area of ​​pterygium based on these comprehensive results.

[0051] According to one embodiment, in step S220, the present invention detects whether the pupil contour, iris contour, and eyelid contour of the target image are complete, and marks one or more areas outside the complete contour as intrusion areas. Correspondingly, one or more areas within the complete contour are marked as non-intrusion areas.

[0052] In eye images, pterygium usually appears as an irregular shape without a clear outline. For pterygium of different development levels, starting from the canthus, it may cover the sclera, iris and pupil in sequence. The segmentation algorithm attempts to detect targets such as pupil contour, iris contour, eyelid contour, canthus and sclera area, and then analyzes the possibility and severity of the presence of pterygium in the sclera, iris and pupil. When the pupil contour, iris contour and eyelid contour are known, the sclera area can be automatically determined. The detection order is pupil contour, iris contour, eyelid contour, canthus, sclera area, or eyelid contour, canthus, pupil contour, iris contour, sclera area.

[0053] When pupil contour detection fails, it may be because the pterygium has invaded more of the pupil area, which includes the pupil area, iris area, sclera area, eyelid area, and eye canthus area. If the pupil contour detection is complete, it means that the pterygium has not invaded the pupil area.

[0054] When the pupil contour is complete but the iris contour detection fails, it means that the pterygium has invaded the iris area, and the invaded area includes the iris area, sclera area, eyelid and eye canthus area. If the iris contour detection is complete, it means that the pterygium has not invaded the iris area and pupil area.

[0055] When the iris contour is complete but the eyelid and canthus contour detection fails, it means that the pterygium has invaded the sclera area, and the invaded area includes the sclera area, eyelid and canthus area. If the eyelid and canthus contour detection is complete, it generally means that pterygium has not occurred.

[0056] There are many methods for detecting pupil contours, iris contours and eyelid contours. The present invention is not limited to a specific form. All algorithms that can detect pupil contours, iris contours and eyelid contours of eye images are within the protection scope of the present invention. According to one embodiment, the pupil contour and iris contour are detected using the Hough circle algorithm, and the eyelid contour and eye corner are detected using the face feature point algorithm.

[0057] Then, in step S230, the measured contour line or the fitted contour line of the intrusion area is obtained, and one or more seed points are determined in the intrusion area.

[0058] Of course, the contour lines of each intrusion area can also be the contour lines hand-drawn by the user in the eye image. It is preferred to use the measured contour line, that is, the contour line detected in step S220. If there is no measured contour line, the fitted contour line is obtained according to the existing contour points. If the fitted contour line is not accurate, the contour line hand-drawn by the user can be used. Obtaining the measured contour line or the fitted contour line of each intrusion area is actually segmenting each intrusion area.

[0059] According to one embodiment, the seed point is any one of the following: a pterygium point specified by a user, a random point in each region, or a feature point identified based on prior knowledge of pterygium. One or more seed points may be determined in each intrusion region.

[0060] Subsequently, in step S240, the pterygium in the intrusion region is obtained by using the region growing algorithm with the seed point as the starting point, and the region growing algorithm stops growing when it grows to the contour line of the region.

[0061] That is, when the pupil contour detection fails, the user can specify the pupil and the approximate pterygium area in the pupil. The algorithm performs pterygium segmentation in the pupil, and uses the information to detect pterygium in the iris and sclera by methods such as region growing. When the iris contour detection fails, the user can specify the estimated iris contour points and the approximate pterygium area in the iris. The algorithm performs pterygium segmentation in the iris, and uses the information to detect pterygium in the sclera by methods such as region growing. When the eyelid contour and canthus detection fail, and thus the sclera area detection fails, the user can specify the sclera area and the approximate pterygium area in the sclera. Generally, pterygium that only exists in the sclera is usually early and less significant. The user can further specify multiple sclera areas, and the algorithm detects pterygium by comparative analysis.

[0062] Here, the region growing algorithm is used for identification based on features such as pixel color and pixel brightness. The pupil area, iris area, sclera area, eyelid area, and eye canthus area all have corresponding image primary colors and brightness, and the pterygium grown in these areas also has corresponding pixel colors and brightness. Based on these differences, the pterygium is gradually identified.

[0063] In addition, in the above implementation, the region growing algorithm will automatically stop growing when it grows to the contour line to determine the pterygium in each region. In another implementation, the region growing algorithm will not stop growing when it grows to the contour line, but will continue to grow until the entire pterygium is identified. Specifically, from the seed point of the intrusion area, the region growing algorithm is used to identify the complete pterygium containing the seed point; the complete pterygium identified from all intrusion areas is taken as the total area of ​​the pterygium in the target image. At this time, the area ratio of the total pterygium area in the target image can be calculated based on the pixel area occupied by the total area and the area within the eyelid contour.

[0064] Then, in step S250, the probability value of the presence of pterygium in the target image is calculated according to the region growing results of each region.

[0065] According to one embodiment, the region growth result includes the area proportion of pterygium in each intrusion region. Given the contours of each region and the pterygium pixels detected in each region, the area proportion of pterygium in the region can be calculated based on plane geometry knowledge. The application of the present invention marks the possibility of the presence of pterygium in the eye image pixel by pixel, and counts the proportion of pterygium in the pupil, iris, sclera and other regions.

[0066] As can be seen from the foregoing, the present invention calculates the proportion of pterygium in each intrusion area, and can also calculate the proportion of pterygium in the entire target image. According to these proportion values, the probability value of the presence of pterygium in the target image can be calculated. The corresponding relationship between each proportion value and the probability value can be set by those skilled in the art as needed, and the present invention does not limit this.

[0067] In another implementation, the probability value is calculated based on the brightness and color differences between the pterygium and the pupil area, iris area, and sclera area, as well as prior knowledge of the brightness and color of the pterygium. The probability value can be a weighted combination of these differences and prior knowledge, and the weighted coefficient is obtained through experiments or training.

[0068] According to another embodiment, after the probability value is calculated, the method 200 may further include the step of uploading the target image, area percentage, probability value and user information to a server for storage. Figure 4 is a schematic diagram of a target image of the present invention, Figure 5 This is the result image after processing the target image, in which the eyelid area, iris area, and pupil area are segmented.

[0069] Figure 6 and Figure 7 FIG. 1 shows a schematic diagram of an application program interface of a mobile terminal according to an embodiment of the present invention, which displays the detection result of pterygium, wherein Figure 6 For vertical screen mode, Figure 7 It is landscape mode, which can further magnify the eye image. Figure 6 and Figure 7 exist Figure 5 Based on the data, the area ratio and probability value of pterygium were calculated. After uploading these test results to the server, a patient file can be established to provide a reference for doctors' remote evaluation.

[0070] When operating the terminal, first click the collection function button to enter the name and other information collection page (you can click to skip the input), and then enter the collection page after input. The collection interface includes a preview screen, an indicative rectangular frame, a collection button, an image / result viewing button, and a simple graphic showing whether the result is sick. In addition, after the image is clicked, it can be switched between the result image and the original image, and the image can be switched by sliding left and right. After that, the original image and the corresponding test results are selected and uploaded to the server to establish a patient file. At the same time, the present invention provides a function of modifying parameter options. After clicking, a sliding button appears, and the sliding button can modify some parameters to realize the control of the algorithm.

[0071] According to the technical solution of the present invention, a terminal application is used to capture an eye image using a rear camera and a fill light with occlusion attenuation, detect pterygium in the progressive and static stages in the eye image, and evaluate the severity. Afterwards, the application uploads the detection results to a server to provide a reference for the diagnosis process.

[0072] A9. A method as described in A8, wherein the eye position prompt box has an eye contour prompt line and / or an eye feature prompt point; the eye contour prompt line includes an eyelid contour line and / or an iris contour line; the eye feature prompt point includes a left eye corner positioning point and / or a right eye corner positioning point. A10. A method as described in any one of A1-A9, wherein the mobile terminal has an LED fill light and / or a macro lens for capturing the eye image sequence. A11. A method as described in any one of A1-A10, wherein the step of selecting a qualified target image includes: selecting an image with qualified image focus, motion blur and eye angle as the target image; the image focus, motion blur and eye angle are calculated based on the camera parameters of the mobile terminal, eye physiological parameters and eye image sequence parameters.

[0073] A12. The method as described in A11, wherein the camera parameters include focal length, optical center and distortion parameters; the eye physiological data include interpupillary distance, iris diameter, and relative position of pupil and iris; the eye image sequence parameters include the spectrum of each image in the image sequence, interpupillary distance, iris diameter, relative position of pupil and iris, and eccentricity of pupil and iris contours. A13. The method as described in A1, wherein the pupil contour and iris contour are detected using the Hough circle algorithm, and the eyelid contour and eye corner are detected using the facial feature point algorithm.

[0074] The various techniques described herein may be implemented in combination with hardware or software, or a combination thereof. Thus, the method and apparatus of the present invention, or some aspects or portions of the method and apparatus of the present invention may be in the form of program codes (i.e., instructions) embedded in a tangible medium, such as a floppy disk, a CD-ROM, a hard disk drive, or any other machine-readable storage medium, wherein when the program is loaded into a machine such as a computer and executed by the machine, the machine becomes a device for practicing the present invention.

[0075] In the case where the program code is executed on a programmable computer, the computing device generally includes a processor, a storage medium readable by the processor (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device. The memory is configured to store the program code; the processor is configured to execute the method of the present invention according to the instructions in the program code stored in the memory.

[0076] By way of example and not limitation, computer readable media include computer storage media and communication media. Computer readable media include computer storage media and communication media. Computer storage media stores information such as computer readable instructions, data structures, program modules or other data. Communication media generally embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and includes any information delivery medium. Any combination of the above is also included within the scope of computer readable media.

[0077] In the description provided herein, algorithms and displays are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the examples of the present invention. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to implement the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0078] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0079] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0080] Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or may be divided into multiple submodules.

[0081] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0082] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the following claims, any one of the claimed embodiments may be used in any combination.

[0083] In addition, some of the embodiments are described herein as methods or combinations of method elements that can be implemented by a processor of a computer system or by other devices that perform the functions. Therefore, a processor with necessary instructions for implementing the method or method elements forms a device for implementing the method or method elements. In addition, the elements described herein of the device embodiments are examples of devices for implementing the functions performed by the elements for the purpose of implementing the invention.

[0084] As used herein, unless otherwise specified, the use of ordinal numbers "first," "second," "third," etc. to describe common objects merely indicates that different instances of similar objects are involved, and is not intended to imply that the objects so described must have a given order in time, space, order, or in any other manner.

[0085] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative, not restrictive, with respect to the scope of the present invention, which is defined by the appended claims.

Claims

1. A pterygium detection method, suitable for execution in a mobile terminal, the method comprising the steps of: Collecting a sequence of eye images of the user to be tested, and selecting a qualified target image from the sequence, wherein the target image includes, from the inside to the outside, a pupil area, an iris area, a sclera area, and an eyelid and eye corner area; Detecting the pupil contour, iris contour, and eyelid contour of the target image, and determining the invasion area of ​​pterygium according to the detection results; Obtaining a measured contour line or a fitted contour line of the intrusion area, and determining one or more seed points in the intrusion area; Taking the seed point as a starting point, a region growing algorithm is used to obtain the pterygium in the intrusion region, wherein the region growing algorithm stops growing when the region contour line is reached; and The probability value of pterygium appearing in the target image is calculated according to the region growing results of each region.

2. The method according to claim 1, further comprising the steps of: Using a region growing algorithm from a seed point of the invasion region to identify a complete pterygium containing the seed point; The complete pterygium identified from all intrusive regions was taken as the total area of ​​pterygium in the target image.

3. The method of claim 1, wherein: The seed point is any one of the following: a pterygium point specified by a user, a random point in each area, or a feature point identified based on prior knowledge of pterygium.

4. The method according to any one of claims 1 to 3, wherein: The region growing algorithm is used for identification based on pixel color and pixel brightness, and the region growing result includes the area ratio of pterygium in each intrusion region.

5. The method of claim 1, wherein: The probability value is calculated based on the brightness and color differences between the pterygium and the pupil area, the iris area, and the sclera area, as well as prior knowledge of the brightness and color of the pterygium.

6. The method as claimed in claim 4 further comprises the step of uploading the target image, area percentage, probability value and user information to a server for storage.

7. The method of claim 1, wherein: The detection result includes any one of the following: pupil contour completeness, left-right pupil difference, iris contour completeness, left-right iris difference, left-right sclera difference, and color and brightness difference from normal eyes.

8. The method of claim 1, wherein: The mobile terminal has a pterygium detection application, the application has an eye position prompt box and a photo button, and the step of collecting an eye image sequence of the user to be tested includes: Under the guidance of the eye position prompt box, the camera lens assembly of the mobile terminal is called through the photo button of the application to obtain multiple eye images of the user to be tested, and the eye images do not contain scene reflection spots.

9. The method of claim 8, wherein: The eye position prompt frame has eye contour prompt lines and / or eye feature prompt points; The eye contour prompt line includes an eyelid contour line and / or an iris contour line; The eye feature prompting points include a left eye corner positioning point and / or a right eye corner positioning point.

10. The method of claim 1, wherein: The mobile terminal has an LED fill light and / or a macro lens for collecting the eye image sequence.

11. The method of claim 1, wherein: The step of selecting a qualified target image comprises: Select an image with satisfactory image focus, motion blur and eye angle as the target image; The image focus, motion blur and eye angle are calculated based on camera parameters of the mobile terminal, eye physiological parameters and eye image sequence parameters.

12. The method of claim 11, wherein: The camera parameters include focal length, optical center and distortion parameters; The eye physiological parameters include interpupillary distance, iris diameter, and relative position of pupil and iris; The eye image sequence parameters include the frequency spectrum of each image in the image sequence, the interpupillary distance, the iris diameter, the relative position of the pupil and the iris, and the eccentricity of the pupil and iris contours.

13. The method of claim 1, wherein: The pupil contour and iris contour are detected by using the Hough circle algorithm, and the eyelid contour and eye corner are detected by using the facial feature point algorithm.

14. A mobile terminal, comprising: Memory; one or more processors; One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for executing any of the methods according to claims 1-13.

15. A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform any of the methods according to claims 1-13.

Images