Search

CN-120997142-B - Sheep oestrus monitoring system based on cell image morphology recognition

CN120997142BCN 120997142 BCN120997142 BCN 120997142BCN-120997142-B

Abstract

The invention discloses a sheep oestrus monitoring system based on cell image morphology recognition, which is characterized by comprising a sample acquisition module (100) for acquiring a sheep vagina epithelial cell sample and dyeing the cell sample, a microscopic imaging module (200) for optically amplifying the dyed cell sample to generate a cell morphology image, an image processing module (300) for extracting cell edge contours and quantifying morphology irregular characteristics, and an intelligent analysis module (400) for comprehensively analyzing a nuclear off-center proportion and morphology irregular indexes to judge sheep oestrus states. The sheep estrus monitoring system based on cell image morphology recognition has the beneficial effects that the high-sensitivity capturing of the estrus early biological markers is realized by fusing double morphological criteria of cell nucleus space displacement analysis and contour geometric distortion detection, and the timeliness and the accuracy of propagation regulation are remarkably improved.

Inventors

  • LIU GUOQIN
  • ZHAO HAIYAN
  • LIU XIAOHUI
  • WANG HONGNA

Assignees

  • 邯郸科技职业学院

Dates

Publication Date
20260508
Application Date
20250724

Claims (7)

  1. 1. The sheep oestrus monitoring system based on cell image morphology recognition is characterized by comprising a sample acquisition module (100), a microscopic imaging module (200), an image processing module (300), an intelligent analysis module (400) and a monitoring output module (500); The sample collection module (100) comprises a cell extraction unit (101) and a dyeing processing unit (102), wherein the cell extraction unit (101) is used for obtaining a sheep vagina epithelial cell sample, and the dyeing processing unit (102) is used for performing dyeing processing on the cell sample; the microscopic imaging module (200) is used for carrying out optical amplification imaging on the stained cell sample to generate a cell morphology image; The image processing module (300) comprises a nuclear positioning unit (301) and a morphology recognition unit (302), wherein the nuclear positioning unit (301) is used for recognizing the position of a cell nucleus and detecting the state of the nuclear off-center, and the morphology recognition unit (302) is used for extracting the outline of the cell edge and quantifying the morphology irregular characteristics; the intelligent analysis module (400) comprehensively analyzes the core off-center proportion and the morphological irregularity index through a preset cell morphology discrimination algorithm to judge the oestrus state of sheep; the monitoring output module (500) records the judging result of the intelligent analysis module (400) in real time, generates an oestrus state monitoring report and dynamically updates the oestrus state monitoring report; The intelligent analysis module (400) for judging the estrus state of sheep comprises the following steps: estrus status conditions, nuclear deviation > 0.5 and morphological irregularity index > 0.75; the non-oestrus condition is that the degree of nuclear deviation is less than or equal to 0.3 or the morphological irregularity index is less than or equal to 0.4; the transition state conditions are core deviation e (0.3, 0.5) and morphology irregularity index e (0.4, 0.75), Wherein the threshold parameter is dynamically updated according to the statistical distribution of the historical data in the monitoring output module (500); The morphology recognition unit (302) performs the following operations: extracting Fourier descriptors of cell outlines by an edge detection algorithm, and reserving the first 20 harmonic components; calculating the Hausdorff distance between the reconstructed contour and the original contour; calculating the profile curvature variance as a morphological irregularity index, wherein the expression is as follows: ; where k i is the contour point curvature, For average curvature, N is the number of contour points, and Hausdorff distance is the maximum mismatch degree measure between two point sets; The core positioning unit (301) calculates a core deviation degree: dividing the cell nucleus and the cytoplasmic region by adopting a network division technology; if a plurality of cell nuclei coexist in the same cytoplasmic area, taking a maximum nuclear deviation value; Cell radius is calculated as equivalent circle diameter: ; A is the pixel area of the cytoplasmic region; locating a cell centroid (Cx, cy) and a cell nucleus centroid (Nx, ny); Calculating the deviation degree: 。
  2. 2. The sheep estrus monitoring system based on cell image morphology recognition according to claim 1, wherein the staining processing unit (102) uses a rayleigh staining solution to stain the cell sample for 3-5 minutes.
  3. 3. The sheep estrus monitoring system based on cell image morphology recognition of claim 1, wherein the microscopic imaging module (200) comprises a microscope, a high-speed focusing mechanism, a multispectral LED light source and an image fusion processor; the image fusion processor synthesizes the images with different wave bands and focal plane images into a high signal-to-noise ratio image.
  4. 4. The sheep estrus monitoring system based on cell image morphology recognition of claim 1, wherein the monitoring output module (500) is configured to, prior to triggering the estrus confirmation report: Invoking the mean value of the density of the white blood cells of the sheep in the monitoring output module (500) for the last 30 days If the currently detected leukocyte density W c is less than 0.6 And keratinocyte accounts for > 65%, activate the continuous detection; Otherwise, the single detection report mode is maintained.
  5. 5. The sheep estrus monitoring system of claim 4, wherein the estrus confirmation report comprises: Cell subtype classification statistical diagram showing the thermodynamic diagram of the spatial distribution of keratinocytes, nucleated cells, white blood cells; estrus risk factor r=α ∈dev+β ∈index where α=0.7, beta=0.3; And (5) reproducing a window period prediction curve, and fitting and generating based on historical estrus interval data.
  6. 6. An electronic device, comprising: One or more processors; A storage device having one or more programs stored thereon; When executed by the one or more processors, causes the one or more processors to implement the system of any of claims 1-5.
  7. 7. A computer readable storage medium having stored thereon executable instructions, which when executed by a processor cause the processor to implement the system of any of claims 1-5.

Description

Sheep oestrus monitoring system based on cell image morphology recognition Technical Field The invention belongs to the field of animal reproduction inspection, and particularly relates to a sheep oestrus monitoring system based on cell image morphology recognition. Background In modern animal husbandry management, flock breeding efficiency directly affects economic benefits, wherein accurate identification of estrus is a key link of breeding regulation. The prior art for monitoring sheep oestrus mainly comprises three types of artificial observation methods, biochemical detection methods and traditional image analysis methods: The existing oestrus detection methods have obvious defects including sensitivity defects, efficiency bottlenecks and cost constraints, the existing detection methods cannot capture morphological changes of cells in the early oestrus, the cell classification counting system is insensitive to characteristics such as irregular morphology and nuclear deviation, the rate of missing messages is high, the biochemical detection needs a laboratory environment, the average delay from sampling to output results is 3.5 hours, the real-time decision requirement of a breeding window period cannot be met, imported high-resolution microscopy equipment is relied on, and the special cell morphological characteristics of sheep species in China are not adapted. The more essential technical contradiction is that the prior art system does not take the space displacement of the cell nucleus and geometric distortion of the outline as oestrus criteria, but the space displacement of the cell nucleus and the geometric distortion of the outline are just early biological markers of the indigenous sheep variety of China (see China journal of livestock (2024,56) (05): 231-235). Therefore, there is a need to develop an oestrus monitoring system that combines morphological micro-change recognition capability, low cost, pasture deployment. Currently, there is no good system on the market to solve the above problems. Disclosure of Invention This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application. The present invention has been made in view of the above and/or existing problems in a monitoring system for sheep oestrus based on cell image morphology recognition. Therefore, the problem to be solved by the present invention is how to detect a system for detecting oestrus status of sheep efficiently by cell images. In order to solve the technical problems, the invention provides a sheep estrus monitoring system based on cell image morphology recognition, which comprises, The system comprises a sample acquisition module, a microscopic imaging module, an image processing module, an intelligent analysis module and a monitoring output module; The sample collection module comprises a cell extraction unit and a dyeing processing unit, wherein the cell extraction unit is used for obtaining a sheep vagina epithelial cell sample, and the dyeing processing unit is used for dyeing the cell sample; The microscopic imaging module is used for carrying out optical amplification imaging on the dyed cell sample to generate a cell morphology image; the image processing module comprises a nuclear positioning unit and a morphology recognition unit, wherein the nuclear positioning unit is used for recognizing the position of a cell nucleus and detecting the state of the nuclear deviating from the center, and the morphology recognition unit is used for extracting the outline of the cell edge and quantifying the irregular morphology characteristics; The intelligent analysis module comprehensively analyzes the core deviation center proportion and the morphological irregularity index through a preset cell morphology discrimination algorithm to judge the oestrus state of sheep; And the monitoring output module records the judging result of the intelligent analysis module in real time, generates an oestrus state monitoring report and dynamically updates the oestrus state monitoring report. As a preferable scheme of the sheep estrus monitoring system based on cell image morphology recognition, the estrus threshold model of the state judging unit comprises the following steps: Estrus state conditions, namely a core deviation degree is more than 0.5, and a morphological irregularity index is more than 0.75, wherein the estrus state is shown in two diagrams of fig. 6-7; The non-oestrus state condition is that the degree of nuclear deviation is less than or equal to 0.3 or the morphological irregularity index is less than or equal to 0.4, as shown in two graphs of figures 2-3, namely the non-oestrus state; The transition conditions are nuclear deviation e (0.3, 0.5) and