Optical fiber breakage detection method and device and electronic equipment

Abstract

The invention provides an optical fiber breakage detection method and device and electronic equipment. The optical fiber breakage detection method comprises the steps that when an incident end of an endoscope is irradiated by a light source, an end face image shot by an optical fiber bundle at an emergent end of the endoscope is obtained, and the optical fiber bundle comprises a plurality of optical fibers; when it is determined that a plurality of adjacent optical fibers in the optical fiber bundle are fractured according to the end face image, identifying unfractured optical fibers in the optical fiber bundle according to the end face image; and according to the number of the unbroken optical fibers and the total number of the optical fibers contained in the optical fiber bundle, calculating the fiber fracture rate of the optical fiber bundle, thereby improving the calculation accuracy and calculation efficiency of the fiber fracture rate.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a method, device and electronic equipment for detecting broken optical fibers. Background Art

[0002] An endoscope system generally includes a light source device and an endoscope. The light emitted by the light source device is transmitted through the optical fiber bundle in the endoscope and then irradiated to the observed object, so that an image of the observed object can be obtained. In order to obtain high-quality images, higher lighting conditions need to be met. During the use of the endoscope, the optical fiber bundle is often bent and squeezed, resulting in optical fiber breakage (i.e. broken wires) in the optical fiber bundle, affecting the light transmission efficiency of the optical fiber bundle, and further affecting the lighting conditions of the observed object. Therefore, the lighting conditions are closely related to the broken wire rate of the optical fiber.

[0003] Due to the small size of the optical fiber, the accuracy and efficiency of detecting the broken fiber rate by naked eye are not high. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a method, device and electronic equipment for detecting broken optical fibers, which can improve the efficiency and accuracy of detecting the broken optical fibers.

[0005] A first aspect of an embodiment of the present application provides a method for detecting broken optical fibers, comprising:

[0006] Acquire an end face image of an optical fiber bundle at an output end of the endoscope when a light source irradiates the input end of the endoscope, wherein the optical fiber bundle includes a plurality of optical fibers;

[0007] In a case where it is determined according to the end face image that a plurality of adjacent optical fibers in the optical fiber bundle are all broken, identifying the unbroken optical fibers in the optical fiber bundle according to the end face image;

[0008] The broken fiber rate of the optical fiber bundle is calculated according to the number of the unbroken optical fibers and the total number of optical fibers contained in the optical fiber bundle.

[0009] In one embodiment, after acquiring the end face image of the optical fiber bundle at the output end of the endoscope when the light source irradiates the input end of the endoscope, the method further comprises:

[0010] If a spot region with a convexity less than a first preset value exists in the end face image, it is determined that a plurality of adjacent optical fibers in the optical fiber bundle are broken; and the brightness of the spot region is lower than the first preset brightness.

[0011] In one embodiment, after acquiring the end face image of the optical fiber bundle at the output end of the endoscope when the light source irradiates the input end of the endoscope, the method further comprises:

[0012] If a spot area with a size larger than a second preset value exists in the end face image, it is determined that a plurality of adjacent optical fibers in the optical fiber bundle are broken; and the brightness of the spot area is lower than the first preset brightness.

[0013] In one embodiment, after acquiring the end face image of the optical fiber bundle at the output end of the endoscope when the light source irradiates the input end of the endoscope, the method further comprises:

[0014] Determining a dark spot in the end surface image whose brightness is lower than a second preset brightness;

[0015] Clustering is performed according to the distances between the dark spots, and the spot area is determined according to the clustering result.

[0016] In one embodiment, the incident end is an end of an insertion portion of the endoscope, and the exit end is an end of a connection portion of the endoscope.

[0017] In one embodiment, the step of identifying an unbroken optical fiber in the optical fiber bundle according to the end face image comprises:

[0018] Identifying an object to be processed in the end face image;

[0019] Filtering out optical fiber images from the object to be processed according to the size of the object to be processed;

[0020] Unbroken optical fibers in the optical fiber bundle are determined based on the screened optical fiber images.

[0021] In one embodiment, the step of selecting the optical fiber image from the object to be processed according to the size of the object to be processed includes:

[0022] Determining identification parameters of the object to be processed according to the size of the object to be processed, wherein the identification parameters include any one or more of roundness, eccentricity and convexity;

[0023] According to the identification parameters, the optical fiber image is screened out from the object to be processed.

[0024] In one embodiment, the step of selecting the optical fiber image from the object to be processed according to the identification parameter includes:

[0025] Determining a roundness range, an eccentricity range, and a convexity range according to the size and deformation characteristics of the optical fiber in the endoscope;

[0026] The optical fiber image is screened out from the object to be processed according to the identification parameter, the roundness range, the eccentricity range and the convexity range.

[0027] A second aspect of an embodiment of the present application provides an optical fiber detection method, comprising:

[0028] Acquire an end face image of an optical fiber bundle at an output end of the endoscope when a light source irradiates the input end of the endoscope, wherein the optical fiber bundle includes a plurality of optical fibers;

[0029] Identifying an object to be processed in the end face image;

[0030] Filtering out optical fiber images from the object to be processed according to the size of the object to be processed;

[0031] The broken fiber rate of the optical fiber bundle is calculated based on the screened optical fiber images.

[0032] In one embodiment, the step of selecting the optical fiber image from the object to be processed according to the size of the object to be processed includes:

[0033] Determining identification parameters of the object to be processed according to the size of the object to be processed, wherein the identification parameters include any one or more of roundness, eccentricity and convexity;

[0034] According to the identification parameters, the optical fiber image is screened out from the object to be processed.

[0035] In one embodiment, calculating the broken fiber rate of the optical fiber bundle according to the screened optical fiber image includes:

[0036] In the case where it is determined according to the end face image that a plurality of adjacent optical fibers in the optical fiber bundle are all broken, determining the unbroken optical fibers in the optical fiber bundle according to the screened optical fiber images;

[0037] The broken fiber rate of the optical fiber bundle is calculated according to the number of the unbroken optical fibers and the total number of optical fibers contained in the optical fiber bundle.

[0038] In one embodiment, after acquiring the end face image of the optical fiber bundle at the output end of the endoscope when the light source irradiates the input end of the endoscope, the method further comprises:

[0039] If a spot region with a convexity less than a first preset value exists in the end face image, it is determined that a plurality of adjacent optical fibers in the optical fiber bundle are broken; and the brightness of the spot region is lower than the first preset brightness.

[0040] In one embodiment, after acquiring the end face image of the optical fiber bundle at the output end of the endoscope when the light source irradiates the input end of the endoscope, the method further comprises:

[0041] Determining a dark spot in the end surface image whose brightness is lower than a second preset brightness;

[0042] Clustering is performed according to the distances between the dark spots, and the spot area is determined according to the clustering result.

[0043] In one embodiment, the incident end is an end of an insertion portion of the endoscope, and the exit end is an end of a connection portion of the endoscope.

[0044] A third aspect of the present application provides an optical fiber broken wire detection device, comprising:

[0045] A first acquisition module, used to acquire an end face image of an optical fiber bundle at an output end of the endoscope when a light source irradiates the input end of the endoscope, wherein the optical fiber bundle includes a plurality of optical fibers;

[0046] a first identification module, configured to identify unbroken optical fibers in the optical fiber bundle according to the end face image when it is determined according to the end face image that a plurality of adjacent optical fibers in the optical fiber bundle are all broken;

[0047] The first calculation module is used to calculate the broken fiber rate of the optical fiber bundle according to the number of the unbroken optical fibers and the total number of optical fibers contained in the optical fiber bundle.

[0048] A fourth aspect of the present application provides an optical fiber broken wire detection device, comprising:

[0049] A second acquisition module, used to acquire an end face image of an optical fiber bundle at an output end of the endoscope when a light source irradiates the input end of the endoscope, wherein the optical fiber bundle includes a plurality of optical fibers;

[0050] A second recognition module, used for recognizing the object to be processed in the end face image;

[0051] A screening module, used for screening out the optical fiber image from the object to be processed according to the size of the object to be processed;

[0052] The second calculation module is used to calculate the broken fiber rate of the optical fiber bundle according to the screened optical fiber image.

[0053] A fifth aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first or second aspect above when executing the computer program.

[0054] A sixth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect or the second aspect above is implemented.

[0055] A seventh aspect of an embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes any one of the methods in the first aspect or the second aspect.

[0056] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0057] By acquiring the end face image of the optical fiber bundle at the output end of the endoscope, it is determined whether there are multiple adjacent optical fibers that are broken based on the end face image. In the case where multiple adjacent optical fibers are broken, since the brightness of the broken optical fibers is low, it is not easy to identify the number of broken optical fibers based on the image area corresponding to the area where multiple adjacent optical fibers are broken. Therefore, using unbroken optical fibers to determine the broken fiber rate of the optical fiber bundle can improve the calculation accuracy and efficiency of the broken fiber rate.

[0058] By acquiring the end face image of the optical fiber bundle at the output end of the endoscope, the optical fiber image is screened out from the object to be processed according to the size of the object to be processed in the end face image, thereby excluding non-optical fiber images, and then the broken wire rate of the optical fiber bundle is determined based on the screened optical fiber image, the calculation accuracy and efficiency of the broken wire rate can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0060] Figure 1 is a schematic diagram of an endoscope provided in one embodiment of the present application;

[0061] Figure 2 is a schematic diagram of an optical fiber broken wire detection device provided in an embodiment of the present application;

[0062] Figure 3 This is a schematic diagram of the implementation process of the optical fiber broken wire detection method provided in one embodiment of the present application;

[0063] Figure 4 is a schematic diagram of an end face image of an optical fiber bundle provided in an embodiment of the present application;

[0064] Figure 5 is an end view of an optical fiber bundle in which a plurality of adjacent optical fibers are broken, provided by an embodiment of the present application;

[0065] Figure 6 is an end view of an optical fiber bundle provided by an embodiment of the present application in which multiple adjacent optical fibers are not broken;

[0066] Figure 7 It is a schematic diagram of the implementation process of a method for detecting broken optical fibers provided in another embodiment of the present application;

[0067] Figure 8 It is a schematic diagram of an optical fiber broken wire detection device provided in an embodiment of the present application;

[0068] Fig. 9 is a schematic diagram of an optical fiber broken wire detection device provided in another embodiment of the present application;

[0069] Fig.10 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0071] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0072] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0073] In addition, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0074] Endoscopic systems generally include light source equipment and endoscopes. Figure 1 As shown, the endoscope 1 includes an insertion portion 12, an operating portion 13 and a connecting portion 14, wherein the insertion portion 12 includes a head end portion 11. The optical fiber bundle includes a plurality of optical fibers, and the optical fiber bundle runs through the entire endoscope, that is, the optical fiber bundle starts from the connecting portion 14, passes through the operating portion 13 and the insertion portion 12 in sequence, and ends at the head end portion 11 of the insertion portion 12. The connecting portion 14 is connected to a light source device, and the light emitted by the light source device is transmitted through the optical fiber and emitted from the head end portion. The head end portion 11 is placed in the observation area, and the observation area can be observed.

[0075] The operating part 13 is provided with a direction adjustment button for controlling the insertion part 12 to bend in different directions, so that different positions of the observation area can be observed. Optical fibers are generally consumable parts, and they may break during the installation, use and storage of the endoscope. For example, the bending of the insertion part 12 may easily cause the optical fiber to break, which affects the light transmission efficiency of the optical fiber bundle and further affects the lighting conditions of the observation area. Therefore, the lighting conditions of the observation area are closely related to the breakage rate of the optical fiber.

[0076] Due to the small size of the optical fiber, manual detection of the optical fiber breakage rate is not accurate and efficient.

[0077] To this end, the present application provides a method for detecting broken optical fibers, which recognizes the end face image of the optical fiber bundle and calculates the broken fiber rate based on the image recognition result, thereby improving the calculation accuracy and efficiency of the broken fiber rate.

[0078] The following is an exemplary description of the optical fiber broken wire detection method provided in the embodiment of the present application.

[0079] The optical fiber broken wire detection method provided in the embodiment of the present application is executed by an electronic device, which can be an independent optical fiber broken wire detection device (which can refer to the optical fiber broken wire detection device as a whole, or can refer to some parts of the optical fiber broken wire detection device that have computing capabilities), or a computing device on an endoscope system, or a computing device that is connected to the optical fiber broken wire detection device in communication. The optical fiber broken wire detection device is at least used to provide a light source and capture an end face image of the endoscope output end.

[0080] The following takes the case where the electronic device is an independent optical fiber breakage detection device as an example to explain the optical fiber breakage detection device.

[0081] For example, Figure 2 As shown, in some embodiments, the optical fiber broken wire detection device 2 includes a box 21, a display screen 22, a button switch 23, a light box 24 and a camera 25. Two mounting holes are provided on the box 21, and the two mounting holes are respectively aligned with the light box 24 and the camera 25. When it is necessary to detect the optical fiber broken wire rate of the endoscope, the incident end of the endoscope 1 is inserted into one of the mounting holes and connected to the light box 24, so that the light emitted by the light box 24 can illuminate the incident end of the endoscope 1, and the output end of the endoscope 1 is inserted into the other mounting hole, so that the camera 25 can collect the end face image of the optical fiber bundle at the output end of the endoscope 1.

[0082] In one embodiment, the incident end is the end of the insertion part of the endoscope (i.e., the head end 11), and the emission end is the end 14A of the connection part of the endoscope. In another embodiment, the incident end is the end of the connection part of the endoscope, and the emission end is the end of the insertion part of the endoscope. That is, both methods can realize the detection of optical fiber breakage.

[0083] In the embodiment of the present application, the entrance and exit of light in the endoscope are collectively referred to as a lens or an end. Specifically, according to different actual conditions, the lens can be the light outlet of the insertion part (also referred to as a light outlet window, etc.) or the light guide rod of the connection part. In practical applications, the insertion part generally includes multiple lenses, and all optical fibers at the connection part are collected, that is, there is only one entrance and exit for light. When the light source is incident from the connection part, the insertion part is photographed to obtain images of multiple lenses. At this time, the broken wire situation can be analyzed independently for each lens, and the total broken wire rate can be summarized. When the light source is incident from the insertion part, since the connection part has only one lens (such as a light guide rod), the connection part can be photographed to obtain an image of a total fiber bundle. At this time, the total image taken can be analyzed to obtain the total broken wire rate. In practical applications, the corresponding scheme can be selected according to actual needs to calculate the required broken wire rate, which is not limited here.

[0084] As an optional embodiment of the present application, the insertion part of the endoscope can be selected as the incident end, and the connection part of the endoscope can be selected as the exit end, so that the camera can capture the optical fiber end face image of the exit end. In this case, only one lens is required to calculate the broken wire rate, so the calculation amount of the image processing process can be reduced.

[0085] The optical fiber detection device also includes a computing module with data processing capability. The computing module can be connected to the camera 25 for communication or can be integrated on the camera 25 .

[0086] When it is detected that the button switch 23 is pressed, the computing module generates an instruction to start the detection, and controls the display screen 22, the light box 24, and the camera 25 to start. The light emitted by the light box 24 illuminates the incident end of the endoscope 1, and the light is emitted from the exit end of the endoscope 1 after being transmitted by the optical fiber. The camera 25 collects the end face image taken by the optical fiber bundle at the exit end of the endoscope. The computing device calculates the broken wire rate of the optical fiber bundle based on the end face image. The display screen 25 can display the broken wire rate of the optical fiber, and can also display the end face image.

[0087] Understandably, Figure 2 The optical fiber broken wire detection device shown is only an example. In actual use, it can be constructed according to needs. Figure 2 The same or different optical fiber broken wire detection devices. For example, the optical fiber broken wire detection device may not include a display screen or a push button switch.

[0088] Below Figure 2 Taking the optical fiber broken wire detection device shown as an example, the optical fiber broken wire detection method provided in the embodiment of the present application is exemplarily introduced.

[0089] like Figure 3 As shown, a method for detecting broken optical fibers provided by an embodiment of the present application includes:

[0090] S301: Acquire an end face image of an optical fiber bundle at an output end of an endoscope when a light source irradiates the input end of the endoscope, wherein the optical fiber bundle includes a plurality of optical fibers.

[0091] The light source may be a light source device in an endoscope system or a light box in an optical fiber broken wire detection device. The incident end may be the end of the insertion part of the endoscope, and the emission end may be the end of the connection part of the endoscope. The camera captures the end face image of the optical fiber at the emission end to obtain the end face image of the connection part. Compared with obtaining multiple end face images of the insertion part by using the insertion part as the emission end, obtaining the end face image of the connection part can reduce the amount of calculation in the subsequent image processing process.

[0092] The end face image at the end of the endoscope is the image of the fiber bundle, which is an image composed of multiple fiber images (i.e., the end face images of the optical fibers). The end face image can be circular or other irregular shapes. For example, Figure 4 As shown, the end face image is circular and is composed of a plurality of optical fiber images 41 .

[0093] S302: When it is determined according to the end face image that a plurality of adjacent optical fibers in the optical fiber bundle are all broken, identifying unbroken optical fibers in the optical fiber bundle according to the end face image.

[0094] Specifically, the end face image is composed of multiple fiber images. If the fiber is broken, the brightness of the fiber image is low, that is, the brightness of the fiber image corresponding to the broken fiber is lower than the brightness of the fiber image corresponding to the unbroken fiber. If the adjacent fibers are all broken (that is, the fibers are broken in pieces), the adjacent fiber images form a spot area with lower brightness. For example, the brightness of the spot area is lower than the first preset brightness, and the first preset brightness can be determined according to the brightness of the light output by the broken fiber. The electronic device can determine whether multiple fibers are broken in the fiber bundle according to whether there is a spot area composed of multiple fiber images in the end face image.

[0095] In one embodiment, the spot region includes one or more dark spots, the dark spots are optical fiber images of the broken optical fiber in the end face image, and the brightness of the dark spots is lower than a second preset brightness, which is determined according to the brightness of the light output by the broken optical fiber. The electronic device can identify the image with a preset pixel value in the end face image as a dark spot through pixel recognition. If the spot region includes multiple dark spots, the distance between adjacent dark spots is less than a preset interval, and the preset interval is determined according to the radius of the optical fiber image.

[0096] Exemplarily, the electronic device may identify a dark spot in the end face image whose brightness is lower than a second preset brightness according to the pixel value of each pixel in the end face image. For example, after acquiring the end face image, the electronic device performs image color space conversion on the end face image, for example, converts it into a unified HSV color space, and then performs binarization processing on the converted image to obtain a binarized image, and uses a dark spot with a pixel value of 0 in the binarized image as a dark spot with a brightness lower than the second preset brightness. The pixel threshold of the binarization processing is determined according to the edge pixel value of the dark spot. The electronic device may identify a dark spot with a pixel value of 0 in the binarized image according to an image recognition algorithm.

[0097] After identifying the dark spots, the electronic device clusters them according to the distance between the dark spots and determines the spot area according to the clustering results. Figure 5 As shown, after identifying the dark spots, the electronic device calculates the distance between the dark spots and divides the adjacent dark spots whose distance is less than the preset interval into a spot area 51, thereby obtaining the spot area in the end face image. The preset interval is determined according to the radius of the optical fiber.

[0098] In another embodiment, the electronic device may also directly identify the spot area from the end surface image according to preset features of the spot area (such as pixel values, contour shapes, etc.).

[0099] After determining the spot area, the electronic device further determines whether the spot area is composed of multiple optical fiber images.

[0100] In one embodiment, after determining the spot area, the electronic device determines the convexity of the spot area. If the convexity of the spot area is less than the first preset value, it is determined that the spot area is composed of multiple fiber images, and then it is determined that there are adjacent optical fibers in the fiber bundle that are broken. Among them, the convexity is a quantitative characterization characteristic of the contour shape of the image. In the embodiment of the present application, it is used to quantify the contour shape characteristics of the spot area. Specifically, after identifying the contour of the image, the smallest convex polygon containing all points of the contour is the convex hull. The convexity can be determined by calculating the difference between the contour and the convex hull. The closer the image is to a circle, the greater the convexity. The first preset value can be determined according to the convexity of the shape contour when the optical fiber is deformed. Since the optical fiber image is circular, even if it is deformed, it is still a shape close to a circle. The spot area composed of multiple optical fiber images is an irregular shape, that is, the contour of the spot area composed of multiple optical fiber images will appear uneven. Therefore, by calculating the convexity of the spot area, it can be determined whether the spot area is circular, and then it can be determined whether the spot area is a fiber image or composed of multiple optical fiber images.

[0101] In another embodiment, after determining the spot area, the electronic device determines the size of the spot area. If the size of the spot area is greater than a second preset value, it is determined that the spot area is composed of multiple fiber images, and further determines that adjacent optical fibers in the optical fiber bundle are broken. The size of the spot area may be the maximum length of the spot area or the area of ​​the spot area. The second preset value is determined according to the radius of the optical fiber image. If the size of the spot area is greater than the second preset value, it means that the spot area is composed of multiple optical fiber images.

[0102] In one embodiment, after acquiring the end face image, the electronic device identifies the object to be processed in the end face image, which is a closed image in the end face image, and the closed image includes the fiber image of the broken fiber and the fiber image of the unbroken fiber, and may also include non-fiber images (such as the gap between adjacent fibers). The electronic device determines the size of each object to be processed, determines the size range of the fiber object according to the size of the fiber in the endoscope, and then screens out the fiber image from the object to be processed according to the size range.

[0103] In one embodiment, the electronic device determines the identification parameters of the object to be processed according to the size of the object to be processed, and the identification parameters may include any one or more of roundness, eccentricity and convexity. Among them, roundness indicates the degree of closeness of the figure to the theoretical circle, and the roundness of the figure can be determined by the difference between the maximum radius and the minimum radius of the figure. The eccentricity indicates the ratio of the distance between the two foci of the ellipse to the length of the major axis. The closer the ellipse is to the circle, the smaller the eccentricity.

[0104] The electronic device can determine that the object to be processed is close to a circle, and further determine that the object to be processed is a fiber image, when it is determined that the object to be processed satisfies any one or more of the following conditions: the roundness is within a set roundness range, the eccentricity is within a set eccentricity range, and the convexity is within a set convexity range. It can be understood that the number of conditions that the object to be processed needs to meet can be set according to actual needs.

[0105] In one embodiment, the electronic device determines the roundness range, eccentricity range, and convexity range according to the size and deformation characteristics of the optical fiber in the endoscope. The deformation characteristics indicate the degree of deformation of the optical fiber when it is squeezed or stretched. According to the degree of deformation, the outline of the optical fiber when it is deformed by squeezing or stretching can be determined. The corresponding optical fiber image when the optical fiber is squeezed or stretched is close to an ellipse. The electronic device determines the roundness range, eccentricity range, and convexity range corresponding to the optical fiber according to the size of the optical fiber and the outline of the optical fiber when it is deformed. Afterwards, the electronic device determines whether the roundness, eccentricity, and convexity of the object to be processed are respectively within the roundness range, eccentricity range, and convexity range according to the roundness, eccentricity, and convexity of the optical fiber image. If so, it is determined that the object to be processed is an optical fiber image. If not, it is determined that the object to be processed is not an optical fiber image.

[0106] After the electronic device determines the optical fiber image, it can determine the optical fiber image corresponding to the broken optical fiber and the optical fiber image corresponding to the unbroken optical fiber in the optical fiber image according to the brightness of the optical fiber image. For example, the optical fiber image with a pixel of 0 is used as the optical fiber image corresponding to the broken optical fiber, and the optical fiber image with a pixel of 255 is used as the optical fiber image corresponding to the unbroken optical fiber. Since the optical fibers in the optical fiber bundle correspond one-to-one with the optical fiber image in the end face image, after the electronic device determines the optical fiber image corresponding to the unbroken optical fiber, it can identify the unbroken optical fiber in the optical fiber bundle.

[0107] In one embodiment, the electronic device may first identify a spot region in the end face image, and determine whether multiple adjacent optical fibers in the optical fiber bundle are all broken according to the spot region. If multiple adjacent optical fibers in the optical fiber bundle are all broken, the electronic device then determines the object to be processed in the region other than the spot region in the end face image, determines the optical fiber image in the object to be processed, and determines the number of optical fiber images corresponding to the unbroken optical fibers from the optical fiber image, which is the number of unbroken optical fibers.

[0108] In another embodiment, the electronic device may also respectively identify the spot area and the fiber image in the end face image, and if it is determined based on the spot area that multiple adjacent optical fibers in the fiber bundle are broken, the number of unbroken optical fibers is determined based on the fiber image.

[0109] In the above embodiment, whether the object to be processed is an optical fiber image is determined based on the roundness, eccentricity and convexity of the object to be processed, so that non-optical fiber images can be excluded. In subsequent calculations, only the optical fiber image is processed, which improves the accuracy of image recognition, thereby improving the accuracy of the subsequent broken wire rate, and improving the running speed of the algorithm.

[0110] S303: Calculate the broken fiber rate of the optical fiber bundle according to the number of the unbroken optical fibers and the total number of optical fibers included in the optical fiber bundle.

[0111] like Figure 5 As shown, when there are multiple adjacent optical fibers in the optical fiber bundle that are all broken, the brightness of the optical fiber images corresponding to the multiple adjacent optical fibers is low, so the optical fiber images corresponding to the multiple adjacent optical fibers form a spot area 51, that is, the optical fiber images in the spot area are adhered to each other, so it is impossible to identify the individual optical fiber images in the spot area, and thus it is impossible to identify the number of broken optical fibers in the optical fiber bundle. However, the optical fiber images corresponding to the unbroken optical fibers have a higher brightness in the end face image and are easier to identify. The electronic device can determine the broken fiber rate of the optical fiber bundle based on the number of unbroken optical fibers and the total number of optical fibers contained in the optical fiber bundle. Exemplarily, after the electronic device determines the number of unbroken optical fibers, the total number of optical fibers minus the number of unbroken optical fibers is the number of broken optical fibers, and the ratio of the number of broken optical fibers to the total number of optical fibers is the broken fiber rate.

[0112] In one embodiment, if Figure 6 As shown, if the electronic device determines that there is no spot region with a convexity less than the first preset value in the end face image, or determines that there is no spot region with a size greater than the second preset value in the end face image, it can be determined that there are no adjacent optical fibers in the optical fiber bundle that are broken. In this case, the optical fiber images 61 do not interfere with each other, and the number of broken optical fibers is generally small. Therefore, after determining the optical fiber image, the electronic device further determines the optical fiber image of the broken optical fiber, and then counts the number of broken optical fibers in the optical fiber bundle. According to the number of broken optical fibers and the total number of optical fibers contained in the optical fiber bundle, the broken fiber rate of the optical fiber bundle can be determined.

[0113] In one embodiment, after calculating the broken wire rate of the optical fiber bundle, the electronic device outputs the broken wire rate, for example, displaying the broken wire rate on a display screen of an optical fiber broken wire detection device. After calculating the broken wire rate, the electronic device can also determine whether the condition for replacing the optical fiber is met according to a preset broken wire rate threshold. If the broken wire rate is greater than the broken wire rate threshold (for example, 50%), a prompt message suggesting replacement of the optical fiber is output; if the broken wire rate is less than the broken wire rate threshold, a prompt message indicating that the endoscope can continue to be used is output.

[0114] Optionally, the electronic device can also output the end face image while outputting the broken wire rate or prompt information on whether to replace the optical fiber, and mark the broken wire area in the end face image. It can also output the number of broken wire areas (i.e., spot areas) at the same time to facilitate users to determine the damage of the optical fiber.

[0115] In the above embodiment, by obtaining the end face image of the optical fiber bundle at the output end of the endoscope, it is determined whether multiple adjacent optical fibers are broken based on the end face image. In the case where multiple adjacent optical fibers are broken, since the brightness of the broken optical fibers is low, it is not easy to identify the number of broken optical fibers based on the image area corresponding to the area where multiple adjacent optical fibers are broken. Therefore, the calculation accuracy and efficiency of the broken fiber rate can be improved by using unbroken optical fibers to determine the broken fiber rate of the optical fiber bundle.

[0116] like Figure 7 As shown, another embodiment of the present application provides a method for detecting broken optical fibers, including:

[0117] S701: Acquire an end face image of an optical fiber bundle at an output end of an endoscope when a light source irradiates the input end of the endoscope, wherein the optical fiber bundle includes a plurality of optical fibers.

[0118] The end face image is the same as the end face image in S301 and will not be described in detail here.

[0119] In one embodiment, the incident end is the end of the insertion portion of the endoscope, and the output end is the end of the connection portion of the endoscope, so that the broken wire rate of the entire optical fiber bundle can be determined by analyzing an image of the connection portion.

[0120] S702: Identify the object to be processed in the end face image.

[0121] The object to be processed is a closed image in the end face image, and the closed image includes the fiber image of the broken fiber and the fiber image of the unbroken fiber, and also includes the image surrounded by the gap between the fibers. The electronic device can identify the closed image in the end face image according to the image recognition algorithm.

[0122] S703: Filtering out optical fiber images from the object to be processed according to the size of the object to be processed.

[0123] Among them, the size range of the optical fiber image can be determined according to the size of the optical fiber in the endoscope, and whether the object to be processed is a optical fiber image can be determined according to whether the object to be processed is within the size range.

[0124] In one embodiment, the electronic device determines the identification parameters of the object to be processed according to the size of the object to be processed, and the identification parameters may include any one or more of roundness, eccentricity and convexity. Then, according to the identification parameters, the optical fiber image is screened out from the object to be processed. The method of screening the optical fiber image according to the identification parameters is the same as the above, and will not be repeated here.

[0125] In one embodiment, the electronic device determines the roundness range, eccentricity range and convexity range according to the size and deformation characteristics of the optical fiber in the endoscope, and then selects the optical fiber image from the object to be processed according to the identification parameters of the object to be processed, as well as the roundness range, eccentricity range and convexity range. Exemplarily, when the electronic device determines that the identification parameters of the object to be processed meet any one or more of the following conditions, it determines that the object to be processed is an optical fiber image: the roundness is within the roundness range, the eccentricity is within the eccentricity range, and the convexity is within the convexity range.

[0126] S704: Calculate the broken fiber rate of the optical fiber bundle according to the screened optical fiber images.

[0127] Specifically, the electronic device determines the optical fiber image corresponding to the broken optical fiber or the optical fiber image corresponding to the unbroken optical fiber from the screened optical fiber images, and can determine the number of unbroken optical fibers or the number of broken optical fibers, and then determines the broken fiber rate of the optical fiber bundle based on the total number of optical fibers included in the optical fiber bundle.

[0128] In one embodiment, when the electronic device determines that multiple adjacent optical fibers in the optical fiber bundle are all broken according to the end face image, the electronic device determines the unbroken optical fibers in the optical fiber bundle according to the screened optical fiber images, and calculates the broken fiber rate of the optical fiber bundle according to the number of unbroken optical fibers and the total number of optical fibers contained in the optical fiber bundle. When multiple adjacent optical fibers in the optical fiber bundle are all broken, the brightness of the optical fiber images corresponding to the multiple adjacent optical fibers is low, so the optical fiber images corresponding to the multiple adjacent optical fibers are adhered to each other, resulting in the optical fiber images corresponding to the broken optical fibers cannot be identified from the end face image, and thus the number of broken optical fibers in the optical fiber bundle cannot be identified. However, the optical fiber images corresponding to the unbroken optical fibers have a higher brightness in the end face image and are easier to identify. Therefore, by determining the unbroken optical fibers from the screened optical fiber images and determining the broken fiber rate of the optical fiber bundle according to the number of unbroken optical fibers and the total number of optical fibers contained in the optical fiber bundle, the accuracy of the calculated broken fiber rate can be improved.

[0129] In one embodiment, if adjacent optical fibers in the optical fiber bundle are not all broken, there is no mutual interference between the optical fiber images. After screening out the optical fiber images, the electronic device further determines the optical fiber images of the broken optical fibers, and then counts the number of broken optical fibers in the optical fiber bundle. According to the number of broken optical fibers and the total number of optical fibers contained in the optical fiber bundle, the broken fiber rate of the optical fiber bundle can be determined.

[0130] In one embodiment, after acquiring the end face image, the electronic device identifies a spot area in the end face image whose brightness is lower than a first preset brightness, and determines the convexity of the spot area. If a spot area with a convexity less than the first preset value exists in the end face image, it means that the spot area is composed of fiber images corresponding to multiple broken optical fibers, and then determines that multiple adjacent optical fibers in the optical fiber bundle are broken.

[0131] In one embodiment, after acquiring the end face image, the electronic device determines dark spots in the end face image whose brightness is lower than a second preset brightness, clusters the dark spots according to the distance between them, determines a spot area according to the distance result, and after determining the spot area, further determines the convexity of the spot area.

[0132] In the above embodiment, by acquiring the end face image of the optical fiber bundle at the output end of the endoscope, the optical fiber image is screened out from the object to be processed according to the size of the object to be processed in the end face image, thereby excluding non-optical fiber images, and then the broken wire rate of the optical fiber bundle is determined based on the screened optical fiber image, the calculation accuracy and efficiency of the broken wire rate can be improved.

[0133] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0134] Corresponding to the optical fiber breakage detection method described in the above embodiments, Figure 8 and Fig. 9 FIG. shows a structural block diagram of an optical fiber breakage detection device provided by an embodiment of the present application. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown.

[0135] As Figure 8 shown, an optical fiber breakage detection device provided by an embodiment of the present application includes

[0136] A first acquisition module 81, configured to acquire an end face image of an optical fiber bundle photographed at an exit end of the endoscope when a light source irradiates an incident end of the endoscope, where the optical fiber bundle includes a plurality of optical fibers;

[0137] A first recognition module 82, configured to recognize unbroken optical fibers in the optical fiber bundle according to the end face image when it is determined that there are a plurality of adjacent broken optical fibers in the optical fiber bundle according to the end face image;

[0138] A first calculation module 83, configured to calculate a wire breakage rate of the optical fiber bundle according to the number of unbroken optical fibers and the total number of optical fibers included in the optical fiber bundle.

[0139] In one embodiment, the first recognition module 82 is further configured to:

[0140] If there is a spot area with a convexity less than a first preset value in the end face image, it is determined that there are a plurality of adjacent broken optical fibers in the optical fiber bundle; the brightness of the spot area is lower than a first preset brightness.

[0141] In one embodiment, the first recognition module 82 is further configured to:

[0142] If there is a spot area with a size greater than a second preset value in the end face image, it is determined that there are a plurality of adjacent broken optical fibers in the optical fiber bundle; the brightness of the spot area is lower than a first preset brightness.

[0143] In one embodiment, the first recognition module 82 is further configured to:

[0144] Determine dark spots with a brightness lower than a second preset brightness in the end face image;

[0145] Cluster according to the distances between the dark spots, and determine the spot area according to the clustering result.

[0146] In one embodiment, the incident end is the end of the insertion part of the endoscope, and the exit end is the end of the connection part of the endoscope.

[0147] In one embodiment, the first recognition module 82 is further configured to:

[0148] Identifying an object to be processed in the end face image;

[0149] Filtering out optical fiber images from the object to be processed according to the size of the object to be processed;

[0150] Unbroken optical fibers in the optical fiber bundle are determined based on the screened optical fiber images.

[0151] In one embodiment, the first identification module 82 is further configured to:

[0152] Determining identification parameters of the object to be processed according to the size of the object to be processed, wherein the identification parameters include any one or more of roundness, eccentricity and convexity;

[0153] According to the identification parameters, the optical fiber image is screened out from the object to be processed.

[0154] In one embodiment, the first identification module 82 is further configured to:

[0155] Determining a roundness range, an eccentricity range, and a convexity range according to the size and deformation characteristics of the optical fiber in the endoscope;

[0156] The optical fiber image is screened out from the object to be processed according to the identification parameter, the roundness range, the eccentricity range and the convexity range.

[0157] like Fig. 9 As shown, another embodiment of the present application provides an optical fiber broken wire detection device comprising:

[0158] A second acquisition module 91 is used to acquire an end face image of a fiber bundle at an exit end of the endoscope when a light source irradiates the incident end of the endoscope, wherein the fiber bundle includes a plurality of optical fibers;

[0159] A second recognition module 92, used to recognize the object to be processed in the end face image;

[0160] A screening module 93, used for screening out the optical fiber image from the object to be processed according to the size of the object to be processed;

[0161] The second calculation module 94 is used to calculate the broken fiber rate of the optical fiber bundle according to the screened optical fiber image.

[0162] In one embodiment, the screening module 93 is specifically used for:

[0163] Determining identification parameters of the object to be processed according to the size of the object to be processed, wherein the identification parameters include any one or more of roundness, eccentricity and convexity;

[0164] According to the identification parameters, the optical fiber image is screened out from the object to be processed.

[0165] In one embodiment, the second calculation module 94 is specifically used for:

[0166] In the case where it is determined according to the end face image that a plurality of adjacent optical fibers in the optical fiber bundle are all broken, determining the unbroken optical fibers in the optical fiber bundle according to the screened optical fiber images;

[0167] The broken fiber rate of the optical fiber bundle is calculated according to the number of the unbroken optical fibers and the total number of optical fibers contained in the optical fiber bundle.

[0168] In one embodiment, the second identification module 92 is further configured to:

[0169] If a spot region with a convexity less than a first preset value exists in the end face image, it is determined that a plurality of adjacent optical fibers in the optical fiber bundle are broken; and the brightness of the spot region is lower than the first preset brightness.

[0170] In one embodiment, the second identification module 92 is further configured to:

[0171] Determining a dark spot in the end surface image whose brightness is lower than a second preset brightness;

[0172] Clustering is performed according to the distances between the dark spots, and the spot area is determined according to the clustering result.

[0173] In one embodiment, the incident end is an end of an insertion portion of the endoscope, and the exit end is an end of a connection portion of the endoscope.

[0174] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0175] Fig.10 1 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server.

[0176] like Fig.10 As shown, the electronic device of this embodiment includes: a processor 101, a memory 102, and a computer program 103 stored in the memory 102 and executable on the processor 101. When the processor 101 executes the computer program 103, the steps in the above-mentioned optical fiber broken wire detection method embodiment are implemented, for example Figure 1 Steps S301 to S303 shown, Figure 7The steps S701 to S704 shown. Alternatively, when the processor 101 executes the computer program 103, it implements the functions of each module / unit in the above-described device embodiments. For example Figure 8 the functions of the first acquisition module 81 to the first calculation module 83 shown, Fig. 9 the functions of the second acquisition module 91 to the second calculation module 94 shown.

[0177] Exemplarily, the computer program 103 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 102 and executed by the processor 101 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 103 in the electronic device.

[0178] Those skilled in the art can understand that Fig.10 merely examples of electronic devices, which do not constitute a limitation on the electronic devices, may include more or fewer components than shown, or combine certain components, or different components. For example, the electronic device may further include input / output devices, network access devices, buses, etc.

[0179] The processor 101 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0180] The memory 102 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. The memory 102 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 102 may also include both an internal storage unit of the electronic device and an external storage device. The memory 102 is used to store the computer program and other programs and data required by the electronic device. The memory 102 may also be used to temporarily store data that has been output or is to be output.

[0181] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0182] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0183] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0184] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0185] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0186] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0187] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0188] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting broken optical fibers, It is characterized in that include: Acquire an end face image of an optical fiber bundle at an output end of the endoscope when a light source irradiates the input end of the endoscope, wherein the optical fiber bundle includes a plurality of optical fibers; In a case where it is determined according to the end face image that a plurality of adjacent optical fibers in the optical fiber bundle are all broken, identifying the unbroken optical fibers in the optical fiber bundle according to the end face image; The broken fiber rate of the optical fiber bundle is calculated according to the number of the unbroken optical fibers and the total number of optical fibers contained in the optical fiber bundle.

2. The method according to claim 1, It is characterized in that After acquiring the end face image of the optical fiber bundle at the output end of the endoscope when the light source irradiates the input end of the endoscope, the method further includes: If a spot region with a convexity less than a first preset value exists in the end face image, it is determined that a plurality of adjacent optical fibers in the optical fiber bundle are broken; and the brightness of the spot region is lower than the first preset brightness.

3. The method according to claim 1, It is characterized in that After acquiring the end face image of the optical fiber bundle at the output end of the endoscope when the light source irradiates the input end of the endoscope, the method further includes: If a spot area with a size larger than a second preset value exists in the end face image, it is determined that a plurality of adjacent optical fibers in the optical fiber bundle are broken; and the brightness of the spot area is lower than the first preset brightness.

4. The method according to claim 2 or 3, It is characterized in that After acquiring the end face image of the optical fiber bundle at the output end of the endoscope when the light source irradiates the input end of the endoscope, the method further includes: Determining a dark spot in the end surface image whose brightness is lower than a second preset brightness; Clustering is performed according to the distances between the dark spots, and the spot area is determined according to the clustering result.

5. The method according to claim 1, It is characterized in that The incident end is an end of an insertion portion of the endoscope, and the emission end is an end of a connection portion of the endoscope.

6. The method according to claim 1, It is characterized in that The step of identifying an unbroken optical fiber in the optical fiber bundle according to the end face image comprises: Identifying an object to be processed in the end face image; Filtering out optical fiber images from the object to be processed according to the size of the object to be processed; Unbroken optical fibers in the optical fiber bundle are determined based on the screened optical fiber images.

7. The method according to claim 6, It is characterized in that The step of selecting the optical fiber image from the object to be processed according to the size of the object to be processed comprises: Determining identification parameters of the object to be processed according to the size of the object to be processed, wherein the identification parameters include any one or more of roundness, eccentricity and convexity; According to the identification parameters, the optical fiber image is screened out from the object to be processed.

8. The method according to claim 7, It is characterized in that The step of selecting the optical fiber image from the object to be processed according to the identification parameter includes: Determining a roundness range, an eccentricity range, and a convexity range according to the size and deformation characteristics of the optical fiber in the endoscope; The optical fiber image is screened out from the object to be processed according to the identification parameter, the roundness range, the eccentricity range and the convexity range.

9. An optical fiber broken wire detection device, It is characterized in that include: A first acquisition module, used to acquire an end face image of an optical fiber bundle at an output end of the endoscope when a light source irradiates the input end of the endoscope, wherein the optical fiber bundle includes a plurality of optical fibers; a first identification module, configured to identify unbroken optical fibers in the optical fiber bundle according to the end face image when it is determined according to the end face image that a plurality of adjacent optical fibers in the optical fiber bundle are all broken; The first calculation module is used to calculate the broken fiber rate of the optical fiber bundle according to the number of the unbroken optical fibers and the total number of optical fibers contained in the optical fiber bundle.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images