Egg incubation detection method and system based on image intelligent identification

Abstract

The invention relates to the technical field of egg incubation detection systems, in particular to an egg incubation detection method and system based on intelligent image recognition. The technical problem is that when an egg incubation detection system is used, manual observation and experience judgment are generally depended, the incubation condition is evaluated by regularly opening an incubator and observing the appearance, smell, sound and other characteristics of eggs, and the incubation environment may be affected; according to the technical scheme, the egg incubation detection method and system based on intelligent image recognition comprise the egg incubation detection method. Compared with a traditional egg incubation detection system, regular manual inspection is needed, an incubator needs to be opened during each inspection, and the incubation environment may be affected, the egg incubation detection system can automatically shoot and analyze images in real time or at regular time by arranging the data analysis module, manual intervention is not needed, and the detection efficiency is improved. And the system is based on an image processing technology and an intelligent identification algorithm, so that the incubation condition can be evaluated more objectively.

Description

Technical Field

[0001] The present invention relates to the technical field of egg hatching detection systems, and in particular to an egg hatching detection method and system based on image intelligent recognition. Background Art

[0002] The definition of an egg hatching detection system can be summarized as a system that integrates multiple technologies and methods, and is designed to automatically and intelligently monitor and evaluate the status, development and hatching results of eggs during the incubation process. This system usually combines advanced technologies in multiple fields such as machine vision, image processing, sensor technology, data analysis and algorithms to achieve comprehensive monitoring and accurate detection of the egg hatching process. However, when using an egg hatching detection system, it generally relies on manual observation and experience judgment. The incubator is opened regularly to observe the appearance, smell, sound and other characteristics of the eggs to evaluate the hatching situation. The detection efficiency is low because manual inspections are required regularly, and the incubator needs to be opened for each inspection, which may affect the hatching environment. Summary of the invention

[0003] In order to overcome the problem that when using the egg hatching detection system, it is generally dependent on manual observation and experience judgment. The incubator is opened regularly to observe the appearance, smell, sound and other characteristics of the eggs to evaluate the hatching situation. The detection efficiency is low because manual inspections are required regularly, and the incubator needs to be opened for each inspection, which may affect the hatching environment.

[0004] The technical solution of the present invention is: an egg hatching detection method based on image intelligent recognition, including the following methods:

[0005] S11: Use a high-resolution camera to take clear images of the eggs from multiple angles, such as the top, bottom, and sides;

[0006] S12: performing preprocessing operations such as denoising and contrast enhancement on the image to improve image quality;

[0007] S13: Using image processing techniques, such as edge detection and texture analysis, to extract features such as cracks and stains on the egg surface;

[0008] S14: Using machine learning or deep learning models, such as convolutional neural networks (CNNs), to classify and identify features and determine whether the eggs are suitable for hatching;

[0009] S15: According to the identification results, eggs that are not suitable for hatching are marked and removed.

[0010] Preferably, when performing quality inspection on the inside of the egg, the following steps are included:

[0011] S21: Scanning the egg using an X-ray or near-infrared imaging device to obtain an image of the internal structure;

[0012] S22: filtering, segmenting, etc. the image to distinguish regions such as yolk, egg white, and eggshell;

[0013] S23: Analyze the location, size, shape of the yolk, and the density and uniformity of the egg white;

[0014] S24: Based on the characteristic analysis results, evaluate the internal quality of the egg and determine its hatching potential;

[0015] S25: The evaluation results are output to guide egg selection and subsequent management during the incubation process.

[0016] Preferably, the embryo development monitoring during the incubation of eggs comprises the following steps:

[0017] S31: At a specific time point of incubation, such as 5-10 days, 19 days, etc., use an egg candling device to perform a fluoroscopic inspection of the eggs;

[0018] S32: recording the fluoroscopic image and performing necessary image processing to enhance the visibility of the embryo;

[0019] S33: Evaluate the developmental status of the embryo based on its morphology, size, vascular distribution and other characteristics in the image;

[0020] S34: Identify eggs with abnormal development or stopped development and mark them for culling;

[0021] S35: Adjust the temperature, humidity and other conditions of the incubator according to the monitoring results to optimize the incubation environment.

[0022] Preferably, when predicting the success rate of egg hatching, the following steps are included:

[0023] S41: Collect a large amount of data on the egg incubation process, including egg surface quality, internal quality, incubation conditions, embryo development, etc.

[0024] S42: extracting features related to hatching success rate from the data;

[0025] S43: Use machine learning algorithms such as logistic regression, random forest, neural network, etc. to train prediction models;

[0026] S44: Evaluate model performance through cross-validation and other methods, and perform necessary optimization;

[0027] S45: Use the trained model to predict the hatching success rate of new eggs and provide decision support for hatching management.

[0028] An egg hatching detection system based on image intelligent recognition includes:

[0029] Data acquisition module: used for real-time collection of egg hatching data;

[0030] Data transmission module: used to transmit the egg hatching data collected by the data acquisition module;

[0031] Data preprocessing module: used for preprocessing the egg hatching data transmitted by the data transmission module;

[0032] Data analysis module: used for multi-level analysis of egg hatching data;

[0033] Human-computer interaction module: used to provide an interactive interface between the user and the detection system.

[0034] Preferably, the data acquisition module includes a plurality of high-definition pan-tilt cameras, which collect image information of eggs in real time or at a fixed time, and are used to collect various data generated during the egg hatching process, so as to provide data support for the egg hatching detection system.

[0035] Preferably, the data transmission module includes an Ethernet communication interface, a WIFI communication interface, a 485 communication interface and a 232 communication interface. The collected data is transmitted to the data preprocessing module through the built-in communication interface of the data acquisition module, which is used to realize remote transmission and real-time sharing of data, and provide data support for monitoring, analysis and optimization of the production process.

[0036] Preferably, the data preprocessing module is used to preprocess the collected egg images to improve the accuracy of subsequent image analysis and recognition, including image denoising, enhancement, filtering, binarization and other operations to eliminate interference factors in the image and highlight the key features of the eggs.

[0037] Preferably, the data analysis module is used to extract key features of eggs, such as shape, color, texture, etc., from the preprocessed images, and use these features for identification. Based on machine learning or deep learning algorithms, such as convolutional neural networks, support vector machines, etc., the extracted features are learned and classified to distinguish different types such as normal eggs, broken eggs, and contaminated eggs. At the same time, according to preset rules or algorithms, the identified egg types are counted, classified and evaluated to provide data support for subsequent hatching management.

[0038] Preferably, the human-computer interaction module is used to provide an interactive interface between the user and the detection system, so that the user can easily operate the system, view the detection results and obtain relevant information, including user login, system configuration, detection result display, history query and other functions. The user can use this module to set detection parameters, start or stop detection tasks, and view detection results and statistical information in real time.

[0039] Beneficial effects of the present invention:

[0040] 1. Compared with the traditional egg hatching detection system, which generally relies on manual observation and experience judgment, the incubator is opened regularly to observe the appearance, smell, sound and other characteristics of the eggs to evaluate the hatching situation. The detection efficiency is low because manual inspection is required regularly, and the incubator needs to be opened for each inspection, which may affect the hatching environment. The egg hatching detection system can automatically take images and analyze them in real time or at a fixed time by setting a data analysis module without manual intervention. Moreover, because the system is based on image processing technology and intelligent recognition algorithms, it can evaluate the hatching situation more objectively.

[0041] 2. The data analysis module is used to extract key features of eggs, such as shape, color, texture, etc., from the preprocessed images, and use these features for identification. Based on machine learning or deep learning algorithms, such as convolutional neural networks and support vector machines, the extracted features are learned and classified to distinguish different types of eggs, such as normal eggs, damaged eggs, and contaminated eggs. At the same time, according to preset rules or algorithms, the identified egg types are counted, classified, and evaluated to provide data support for subsequent hatching management;

[0042] 3. The data acquisition module includes multiple high-definition pan-tilt cameras, which collect image information of eggs in real time or at regular intervals to collect various data generated during the egg hatching process and provide data support for the egg hatching detection system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 What is shown is a schematic flow chart of an egg hatching detection method based on image intelligent recognition of the present invention;

[0044] Figure 2 Shown is a schematic diagram of the workflow of an egg internal quality detection method of an egg hatching detection method based on image intelligent recognition of the present invention;

[0045] Figure 3 Shown is a schematic diagram of the embryo development monitoring process of an egg hatching detection method based on image intelligent recognition of the present invention. DETAILED DESCRIPTION

[0046] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0047] See also Figure 1-3 The present invention provides an embodiment: an egg hatching detection method based on image intelligent recognition, comprising the following methods:

[0048] S11: Use a high-resolution camera to take clear images of the eggs from multiple angles, such as the top, bottom, and sides;

[0049] S12: performing preprocessing operations such as denoising and contrast enhancement on the image to improve image quality;

[0050] S13: Using image processing techniques, such as edge detection and texture analysis, to extract features such as cracks and stains on the egg surface;

[0051] S14: Using machine learning or deep learning models, such as convolutional neural networks (CNNs), to classify and identify features and determine whether the eggs are suitable for hatching;

[0052] S15: According to the identification results, eggs that are not suitable for hatching are marked and removed.

[0053] Preferably, when performing quality inspection on the inside of the egg, the following steps are included:

[0054] S21: Scanning the egg using an X-ray or near-infrared imaging device to obtain an image of the internal structure;

[0055] S22: filtering, segmenting, etc. the image to distinguish regions such as yolk, egg white, and eggshell;

[0056] S23: Analyze the location, size, shape of the yolk, and the density and uniformity of the egg white;

[0057] S24: Based on the characteristic analysis results, evaluate the internal quality of the egg and determine its hatching potential;

[0058] S25: The evaluation results are output to guide egg selection and subsequent management during the incubation process.

[0059] Preferably, the embryo development monitoring during the incubation of eggs comprises the following steps:

[0060] S31: At a specific time point of incubation, such as 5-10 days, 19 days, etc., use an egg candling device to perform a fluoroscopic inspection of the eggs;

[0061] S32: recording the fluoroscopic image and performing necessary image processing to enhance the visibility of the embryo;

[0062] S33: Evaluate the developmental status of the embryo based on its morphology, size, vascular distribution and other characteristics in the image;

[0063] S34: Identify eggs with abnormal development or stopped development and mark them for culling;

[0064] S35: Adjust the temperature, humidity and other conditions of the incubator according to the monitoring results to optimize the incubation environment.

[0065] Preferably, when predicting the success rate of egg hatching, the following steps are included:

[0066] S41: Collect a large amount of data on the egg incubation process, including egg surface quality, internal quality, incubation conditions, embryo development, etc.

[0067] S42: extracting features related to hatching success rate from the data;

[0068] S43: Use machine learning algorithms such as logistic regression, random forest, neural network, etc. to train prediction models;

[0069] S44: Evaluate model performance through cross-validation and other methods, and perform necessary optimization;

[0070] S45: Use the trained model to predict the hatching success rate of new eggs and provide decision support for hatching management.

[0071] An egg hatching detection system based on image intelligent recognition includes:

[0072] Data acquisition module: used for real-time collection of egg hatching data;

[0073] Data transmission module: used to transmit the egg hatching data collected by the data acquisition module;

[0074] Data preprocessing module: used for preprocessing the egg hatching data transmitted by the data transmission module;

[0075] Data analysis module: used for multi-level analysis of egg hatching data;

[0076] Human-computer interaction module: used to provide an interactive interface between the user and the detection system.

[0077] Preferably, the data acquisition module includes a plurality of high-definition pan-tilt cameras, which collect image information of eggs in real time or at a fixed time, and are used to collect various data generated during the egg hatching process, so as to provide data support for the egg hatching detection system.

[0078] Preferably, the data transmission module includes an Ethernet communication interface, a WIFI communication interface, a 485 communication interface and a 232 communication interface. The collected data is transmitted to the data preprocessing module through the built-in communication interface of the data acquisition module, which is used to realize remote transmission and real-time sharing of data, and provide data support for monitoring, analysis and optimization of the production process.

[0079] Preferably, the data preprocessing module is used to preprocess the collected egg images to improve the accuracy of subsequent image analysis and recognition, including image denoising, enhancement, filtering, binarization and other operations to eliminate interference factors in the image and highlight the key features of the eggs.

[0080] Preferably, the data analysis module is used to extract key features of eggs, such as shape, color, texture, etc., from the preprocessed images, and use these features for identification. Based on machine learning or deep learning algorithms, such as convolutional neural networks, support vector machines, etc., the extracted features are learned and classified to distinguish different types such as normal eggs, broken eggs, and contaminated eggs. At the same time, according to preset rules or algorithms, the identified egg types are counted, classified and evaluated to provide data support for subsequent hatching management.

[0081] Preferably, the human-computer interaction module is used to provide an interactive interface between the user and the detection system, so that the user can easily operate the system, view the detection results and obtain relevant information, including user login, system configuration, detection result display, history query and other functions. The user can use this module to set detection parameters, start or stop detection tasks, and view detection results and statistical information in real time.

[0082] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of those skilled in the art without departing from the spirit of the present invention.

Claims

1. An egg hatching detection method based on image intelligent recognition; characterized in that: The following methods are included: S11: Use a high-resolution camera to take clear images of the eggs from multiple angles, such as the top, bottom, and sides; S12: performing preprocessing operations such as denoising and contrast enhancement on the image to improve image quality; S13: Using image processing techniques, such as edge detection and texture analysis, to extract features such as cracks and stains on the egg surface; S14: Using machine learning or deep learning models, such as convolutional neural networks (CNNs), to classify and identify features and determine whether the eggs are suitable for hatching; S15: According to the identification results, eggs that are not suitable for hatching are marked and removed.

2. The egg hatching detection method based on image intelligent recognition according to claim 1, characterized in that: When testing the quality of the inside of an egg, the following steps are involved: S21: Scanning the egg using an X-ray or near-infrared imaging device to obtain an image of the internal structure; S22: filtering, segmenting, etc. the image to distinguish regions such as yolk, egg white, and eggshell; S23: Analyze the location, size, shape of the yolk, and the density and uniformity of the egg white; S24: Based on the characteristic analysis results, evaluate the internal quality of the egg and determine its hatching potential; S25: The evaluation results are output to guide egg selection and subsequent management during the incubation process.

3. The egg hatching detection method based on image intelligent recognition according to claim 2, characterized in that: When monitoring embryonic development during incubation of eggs, the following steps are involved: S31: At a specific time point of incubation, such as 5-10 days, 19 days, etc., use an egg candling device to perform a fluoroscopic inspection of the eggs; S32: recording the fluoroscopic image and performing necessary image processing to enhance the visibility of the embryo; S33: Evaluate the developmental status of the embryo based on its morphology, size, vascular distribution and other characteristics in the image; S34: Identify eggs with abnormal development or stopped development and mark them for culling; S35: Adjust the temperature, humidity and other conditions of the incubator according to the monitoring results to optimize the incubation environment.

4. The egg hatching detection method based on image intelligent recognition according to claim 3, characterized in that: When predicting the success rate of egg hatching, the following steps are involved: S41: Collect a large amount of data on the egg incubation process, including egg surface quality, internal quality, incubation conditions, embryo development, etc. S42: extracting features related to hatching success rate from the data; S43: Use machine learning algorithms such as logistic regression, random forest, neural network, etc. to train prediction models; S44: Evaluate model performance through cross-validation and other methods, and perform necessary optimization; S45: Use the trained model to predict the hatching success rate of new eggs and provide decision support for hatching management.

5. An egg hatching detection system based on image intelligent recognition, comprising: Data acquisition module: used for real-time collection of egg hatching data; Data transmission module: used to transmit the egg hatching data collected by the data acquisition module; Data preprocessing module: used for preprocessing the egg hatching data transmitted by the data transmission module; Data analysis module: used for multi-level analysis of egg hatching data; Human-computer interaction module: used to provide an interactive interface between the user and the detection system.

6. The egg hatching detection system based on image intelligent recognition according to claim 5, characterized in that: The data acquisition module includes multiple high-definition pan-tilt cameras, which collect image information of eggs in real time or at regular intervals to collect various data generated during the egg incubation process and provide data support for the egg hatching detection system.

7. The egg hatching detection system based on image intelligent recognition according to claim 6, characterized in that: The data transmission module includes Ethernet communication interface, WIFI communication interface, 485 communication interface and 232 communication interface. The collected data is transmitted to the data preprocessing module through the built-in communication interface of the data acquisition module, which is used to realize the remote transmission and real-time sharing of data, and provide data support for the monitoring, analysis and optimization of the production process.

8. The egg hatching detection system based on image intelligent recognition according to claim 7, characterized in that: The data preprocessing module is used to preprocess the collected egg images to improve the accuracy of subsequent image analysis and recognition, including image denoising, enhancement, filtering, binarization and other operations to eliminate interference factors in the image and highlight the key features of the eggs.

9. The egg hatching detection system based on image intelligent recognition according to claim 8, characterized in that: The data analysis module is used to extract key features of eggs, such as shape, color, texture, etc., from the preprocessed images, and use these features for identification. Based on machine learning or deep learning algorithms, such as convolutional neural networks, support vector machines, etc., the extracted features are learned and classified to distinguish different types such as normal eggs, damaged eggs, and contaminated eggs. At the same time, according to preset rules or algorithms, the identified egg types are counted, classified, and evaluated to provide data support for subsequent hatching management.

10. The egg hatching detection system based on image intelligent recognition according to claim 9, characterized in that: The human-computer interaction module is used to provide an interactive interface between the user and the detection system, allowing the user to easily operate the system, view the detection results and obtain relevant information, including user login, system configuration, detection result display, historical record query and other functions. The user can use this module to set detection parameters, start or stop detection tasks, and view detection results and statistical information in real time.

Images