Electronic apparatus and lossless egg sex identification method

Abstract

Disclosed and designed in the present invention are an electronic apparatus and a lossless egg sex identification method. The electronic apparatus comprises a memory storing computer-readable instructions and a processor, wherein when executing the computer-readable instructions, the processor is configured to process a spectral image in a specific waveband of a fertilized egg. The present invention can directly process a spectral image in a specific waveband of a fertilized egg, and the efficiency with which the sex of an egg is identified by means of the apparatus is higher, thereby greatly shortening the time taken.

Description

An electronic device and a non-destructive method for identifying the sex of eggs. Technical Field

[0001] This invention relates to the field of egg sex identification technology, and in particular to an electronic device and method for non-destructive identification of egg sex using neural network algorithms. Background Technology

[0002] Currently, the main methods for determining the sex of early egg embryos, both domestically and internationally, include the following:

[0003] I. Identification methods based on volatile organic compounds (VOCs): This method determines VOCs by analyzing the gases emitted from eggshells, but it requires a long time to collect gas samples and is not suitable for batch applications. Although techniques such as chemical ionization have recently been proposed for rapid detection of gas components, the accuracy and repeatability of these models are still poorly understood, and their repeatability remains unknown.

[0004] II. Polymerase Chain Reaction (PCR)-based identification method: PCR is a commonly used technique for sex identification in avian research. It amplifies sex-specific genes located on the Z and W sex chromosomes. This method mainly involves three steps: DNA isolation, PCR, and gel electrophoresis. After screening the PCR products by agarose gel electrophoresis, males and females show clear differences, which can be used to classify embryos. However, this method is not only uneconomical, requiring specialized equipment and precise experiments, but also quite time-consuming, making it unsuitable for large-scale application in practical scenarios.

[0005] III. Raman Spectroscopy-Based Identification Method: This method analyzes the spectrum of blood in extraembryonic vessels using Raman spectroscopy by opening a window in the eggshell. The identification accuracy can reach 90% on day 3.5 of incubation. However, invasive testing carries the risk of infection, and opening and sealing the eggshell increases identification costs, making it unsuitable for parallel application in large-scale hatcheries. Summary of the Invention

[0006] In view of the problems existing in the above-mentioned methods for detecting the sex of eggs, the present invention is proposed.

[0007] Therefore, one of the problems to be solved by the present invention is how to provide an electronic device capable of processing spectral images of specific wavelengths of fertilized eggs.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an electronic device comprising: a memory storing computer-readable instructions; and a processor configured, when executing the computer-readable instructions, to: process spectral images of specific bands of fertilized eggs; the ability to process spectral images of specific bands of fertilized eggs includes: screening spectral image bands that represent features of fertilized eggs; and further extracting image features and channel features of fertilized eggs, wherein the spectral images of specific bands include spectral images of the 945.354nm, 762.407nm, 409.377nm, and 644.587nm bands.

[0009] As a preferred embodiment of the electronic device described in this invention, the spectral images of the specific wavelength bands include spectral images of the following wavelength bands: 945.354nm, 762.407nm, 409.377nm, 644.587nm, 888.39nm, 399.991nm, 618.669nm, 578.621nm, 728.801nm, 954.091nm, 562.989nm, 470.638nm, 1004.87nm, 904.482nm, 520.684nm, 779.97nm, 718.592nm, 441.857nm, 840.049nm, 494.166nm, 670.619nm, and 829.789nm.

[0010] In a preferred embodiment of the electronic device described in this invention, the image feature bands for screening fertilized eggs are captured through a channel attention mechanism to capture information on the correlation between potential channels in the average spectrum of the spectral image, thereby assigning greater weight to important channels.

[0011] As a preferred embodiment of the electronic device described in this invention, the image feature bands for screening fertilized eggs are processed as follows: each channel of the spectral image is downsampled to a mean; an improvement operation is performed to obtain a vector with multiple dimensions; the obtained vectors are summed to obtain the weight of each channel; the weights are multiplied by each channel of the spectral image to include the importance features of the channels in the output data.

[0012] In a preferred embodiment of the electronic device described in this invention, the image feature bands for screening fertilized eggs are obtained by performing an improvement operation on the SE layer. This improvement operation involves performing first-order and second-order derivative operations. Specifically...

[0013] Among them, AvgP i Let D1 be the mean of the i-th channel image, and n be the number of channels in the spectral image. i Let D2 be the first derivative corresponding to the i-th channel. iLet be the second derivative of the i-th channel.

[0014] In a preferred embodiment of the electronic device of the present invention, the following steps are taken: further extracting image features and channel features of fertilized eggs, further extracting image texture information and channel information, and reducing the channel features.

[0015] In a preferred embodiment of the electronic device of the present invention, the further extraction of image features and channel features of the fertilized egg is performed as follows: the channel dimension is reduced by pointwise convolution; depthwise convolution is performed on the reduced channels to extract the image features within each channel; pointwise convolution is performed again to fuse the information between channels and obtain the output image of the reduced channels.

[0016] In a preferred embodiment of the electronic device described in this invention, the further extraction of image features and channel features of fertilized eggs is achieved through a depthwise separable convolution algorithm.

[0017] As a preferred embodiment of the electronic device of the present invention, it further includes: acquiring a spectral image of a fertilized egg in a specific band; and segmenting a region of interest from the spectral image in the specific band.

[0018] Another problem that this invention aims to solve is how to provide a method for non-destructive identification of the sex of eggs.

[0019] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for non-destructive identification of the sex of eggs, comprising: an image acquisition device acquiring a spectral image of a specific wavelength band of a fertilized egg; preprocessing the spectral image of the specific wavelength band; and processing the preprocessed spectral image of the specific wavelength band of the fertilized egg using an electronic device.

[0020] As a preferred embodiment of the method for non-destructive identification of egg sex according to the present invention, the method includes: preprocessing the spectral image of the specific band, including segmenting the region of interest from the spectral image of the specific band.

[0021] As a preferred embodiment of the method for non-destructive identification of egg sex according to the present invention, the step of segmenting the region of interest from the spectral image of the specific band includes: merging the R, G, and B bands of the spectral image of the specific band, selecting the egg range and obtaining a grayscale image; further processing the grayscale image to segment the spectral image of the region of interest from the spectral image of the specific band.

[0022] The beneficial effects of this invention are that it designs an electronic device that can directly process spectral images of fertilized eggs in specific wavelengths, making the identification of male and female eggs more efficient and significantly reducing the time required. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0024] Figure 1 is a block diagram of the configuration of an electronic device according to an embodiment of the present disclosure.

[0025] Figure 2 is a schematic diagram of processing a spectral image of a fertilized egg in a specific band according to one embodiment of the present invention.

[0026] Figure 3 shows the characteristic wavelengths selected by analyzing the spectral images of fertilized eggs in specific bands according to the present invention.

[0027] Figure 4 is a schematic diagram of assigning greater weight to important channels through a channel attention mechanism in one embodiment of the present invention.

[0028] Figure 5 is a schematic diagram of the region of interest extraction process described in this invention.

[0029] Figure 6 is a schematic diagram of acquiring spectral images of fertilized eggs in a specific wavelength band according to one embodiment of the present invention. Detailed Implementation

[0030] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0031] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0032] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0033] Example 1

[0034] The first embodiment of the present invention provides an electronic device for non-destructive identification of the sex of eggs, which can directly process spectral images of fertilized eggs in specific wavelengths.

[0035] In one implementation, the electronic device 100 can be implemented as any of a variety of devices, such as a smartphone, server device, desktop PC, laptop PC, tablet PC, TV, set-top box, kiosk, and wearable device. Alternatively, the electronic device 100 can be implemented as a system comprising multiple distributed devices capable of communicating with each other.

[0036] Referring to FIG1, electronic device 100 may include memory 101 and processor 102. Memory 101 may store various data related to the operating system and components of electronic device 100 for controlling the operation of components of electronic device 100. Memory 101 may include software, programs, and at least one instruction for controlling the functions of one or more components of electronic device 100.

[0037] The memory can be implemented as non-volatile memory (e.g., hard disk, solid-state drive (SSD), flash memory), volatile memory, etc.

[0038] The processor 102 can control the operation of the electronic device 100. In terms of hardware, the processor 120 may include a central processing unit (CPU), a graphics processing unit (GPU), a neural processing unit (NPU), etc., and can perform calculations or data processing for controlling other components included in the electronic device 100.

[0039] The processor 102 can be implemented as a microprocessor unit (MPU) or central processing unit (CPU) coupled to a system bus and a memory 101 such as random access memory (RAM) and read-only memory (ROM).

[0040] The processor 102 can not only control the hardware components included in the electronic device 100, but also control the execution of one or more software modules included in the electronic device 100, and the results of the processor 102 controlling the software modules can be derived for controlling the hardware components and their functions to perform the operation of the electronic device 100.

[0041] Specifically, the processor 102 can control the electronic device 100 by executing at least one instruction stored in the memory 101.

[0042] The operation of the electronic device 100 will be described in more detail below.

[0043] The processor 102, when executing computer-readable instructions, is configured to process spectral images of specific bands of fertilized eggs. Specifically, processing spectral images of specific bands of fertilized eggs includes screening spectral image bands that represent features of the fertilized eggs and further extracting image features and channel features of the fertilized eggs.

[0044] The term "spectral image" as used herein includes hyperspectral images or multispectral images.

[0045] Among them, the image feature bands for screening fertilized eggs can be identified by machine learning algorithms such as RF (Random Forest Simplified), CARS (Competitive Adapative Reweighted Sampling), SPA (Successive Projections Algorithm), and PCA (Principal Component Analysis).

[0046] Further extraction of image features and channel features of fertilized eggs can be achieved through conventional deep learning methods, such as depthwise separable convolution, full convolution, or dilated convolution.

[0047] In one implementation, the input spectral image of a fertilized egg at a specific wavelength is a 22-channel or 4-channel image composed of 22 or 4 wavelengths selected (see Figure 2). Taking 22 channels as an example: each channel image is a grayscale image with a width and length of 224, i.e., the input dimension is (22, 224, 224), and the value of each pixel is between 0 and 255. After processing the spectral image bands that select the features of the fertilized egg, the output dimension remains unchanged at (22, 224, 224), but each channel image contains channel weight information, where each color represents a different channel image. The darker the color, the higher the importance and weight of the channel. Subsequently, depthwise separable convolution is used to further extract image features and channel information, adjusting the number of channels from 22 to 32, and the output dimension is (32, 224, 224). Similarly, the darker the color of each channel, the higher its importance. Here, the function of depthwise separable convolution is mainly to extract and integrate the texture information of images from different channels, and the output channel images are mostly dark. When the hyperspectral camera acquires 4 wavelengths, the downsampling factor for the spectral image band processing for screening the characteristics of fertilized eggs is adjusted from 4 times to 1 times. That is, the first Linear remaps the three 4-dimensional vectors to 4 dimensions without performing dimensionality reduction. After the first filtering layer 100, the output dimension is (4, 224, 224). After the depthwise separable convolution, the output dimension is (32, 224, 224).

[0048] Of course, those skilled in the art should also be aware that a third or fourth filter layer, or even more, can be used.

[0049] Meanwhile, the inventors' comparative experiments proved that the electronic device can be used to identify the sex of chicken and quail eggs, but it is not necessarily applicable to duck eggs, goose eggs and other poultry eggs. Its identification effect is not as good as the combination of screening spectral image bands of fertilized eggs and further extracting image features and channel features of fertilized eggs in this embodiment.

[0050] In this embodiment, the "spectral image of a specific band" that is directly processed by the electronic device 100 includes spectral images of four bands: 945.354 nm, 762.407 nm, 409.377 nm, and 644.587 nm.

[0051] Referring to Figure 3, the wavelength contribution values ​​shown in Figure 3 are distributed across the entire wavelength band. To filter out a few effective bands, a certain sampling interval is set, and the wavelengths between the intervals are uniquely selected from the largest to the smallest contribution value. When the sampling interval is set to a factor of 440 (1, 2, 4, 5, 10, 20, 22), the accuracy of 0.946 can be maintained for the 4-band inputs of 945.354nm, 762.407nm, 409.377nm, and 644.587nm.

[0052] Example 2

[0053] As shown in Figure 3, in this embodiment, the "spectral image of a specific band" directly processed by the electronic device 100 includes spectral images of twenty-two bands: 945.354nm, 762.407nm, 409.377nm, 644.587nm, 888.39nm, 399.991nm, 618.669nm, 578.621nm, 728.801nm, 954.091nm, 562.989nm, 470.638nm, 1004.87nm, 904.482nm, 520.684nm, 779.97nm, 718.592nm, 441.857nm, 840.049nm, 494.166nm, 670.619nm, and 829.789nm.

[0054] Meanwhile, with 22-band input, the accuracy of the electronic device 100 analysis remained at 0.954.

[0055] Example 3

[0056] Compared to Example 1, the method for screening spectral image bands of fertilized eggs in this embodiment captures information about the correlation between potential channels in the average spectrum through a channel attention mechanism, and assigns greater weight to important channels.

[0057] Channel attention mechanisms adaptively rescale the features of each channel by modeling the interdependencies between feature channels. This allows the network to focus on more useful channels and enhances its discriminative learning capabilities. Channel attention enables neural networks to automatically determine which channels are important or unimportant and then assign appropriate weights. Each channel of the feature map is treated as a feature detector, so channel features focus on "what" is useful information in the image.

[0058] The phrase "capturing information about the correlations between potential channels in the average spectrum" specifically refers to the average spectrum, which is the result of averaging spectral data from multiple samples within a given region. Spectra typically describe the properties or composition of an object by measuring the intensity of light at different wavelengths. When analyzing spectra, the focus is usually on the intensity variations between different wavelengths and the correlations between them. This correlation helps in understanding how signals at different wavelengths change over time, conditions, or other factors, thereby revealing the properties or state of an object.

[0059] Understanding the correlations in average spectra helps in data analysis and pattern identification. When the spectral data of different samples show consistent trends at certain wavelengths, a correlation can be considered to exist between these wavelengths. This correlation indicates that these wavelengths are important for distinguishing different categories of samples or features.

[0060] The reason the model can classify based on average spectral curves is that these curves represent typical spectral features of different categories or characteristics. When these features are fed into the machine learning model for training, the model can learn the differences between different categories, and when it receives new spectral data, it can make classification predictions based on these learned features.

[0061] In this implementation, the channel attention mechanism can be implemented using ECANet (Efficient Channel Attention for Deep Convolutional Neural Networks), SE layer attention mechanism (Squeeze-and-Excitation Networks), CBAM network architecture (Convolutional Block Attention Module), STN network (Spatial Transformer Networks), or STL network structure (Spatial Transformer Layer), etc.

[0062] The concept of "important channels" can be understood as follows: Taking the improved attention mechanism of the SE layer as an example, see Figure 4, with 22 channels as an example: AvgPool2d is the average spectrum of the input spectral image, D1 and D2 are the first and second derivatives of AvgPool2d, respectively, all three being 22-dimensional vectors. Sigmoid is a function that scales the input to 0-1, Linear is a non-linear transformation, and the ReLU function sets inputs less than 0 to 0. After another Linear transformation, the three 22-dimensional vectors are directly added together. Finally, after being transformed by the Sigmoid function and projected to the 0-1 interval, a pointwise multiplication operation is performed with the original spectral image, that is, the i-th value is directly multiplied by the i-th input channel (i∈[0,22]). The output dimension is still 22 channels, but after the improved attention mechanism of the SE layer, it includes the importance information of the channels.

[0063] Example 4

[0064] The method for selecting spectral image bands for fertilized eggs in this embodiment, compared to Embodiment 4, performs the following processing: Each channel of the acquired spectral image is downsampled to an average value. For example, a two-dimensional average pooling operation (AvgPool2d) can be used to downsample each channel of the spectral image to an average value, and the downsampled images of all channels constitute the average spectrum. Then, after passing through two fully connected layers or a nonlinear transformation and improvement operation, a multi-dimensional vector is obtained. For example, if the spectral image of a specific band has 22 channels, after passing through two fully connected layers or a nonlinear transformation and improvement operation, three 22-dimensional vectors are obtained. The obtained vectors are then summed to obtain the weight of each channel; finally, the weight is multiplied by each channel of the original image, and the output data includes the importance features of the channels.

[0065] The mathematical formula corresponding to the "nonlinear transformation" mentioned here is as follows:

[0066] Output = input × weight T +bias,

[0067] Where: input is the input tensor of size (N, in_features), where N is the size of the input and in_features is the number of input features; weight is the weight matrix of size (out_features, in_features), where out_features is the number of output features; bias is the bias vector of size (out_features), specifically, it can be represented as:

[0068] Where x is the input tensor, x ij Let w be the tensor in the i-th row and j-th column of the input matrix. j Let w be the j-th column tensor. From the expression, we know that the output tensor y... i That is, the sum of the dot product of all data in the i-th row of x and all data in the j-th column of w, plus the constant b.

[0069] In this embodiment, the "improved operation" can be, for example, the SG (Savitzjy Golay) smoothing algorithm, the MSC (Multiplicative Scatter Correction) multivariate scattering correction, the SNV (Standard Normalized Variate) variable standardization, the D1 (1st Derivatives) first derivative, the D2 (2nd Derivatives) second derivative, or a combination of first and second derivative operations.

[0070] For example, the method for combining first and second derivatives is as follows:

[0071] Among them, AvgP i Let D1 be the mean of the i-th channel image, and n be the number of channels in the spectral image. i Let D2 be the first derivative corresponding to the i-th channel. i Let be the second derivative of the i-th channel.

[0072] Example 5

[0073] In this embodiment, the method of screening the spectral image bands of fertilized eggs directly employs the SE layer.

[0074] In another implementation, the SE layer was modified.

[0075] Specifically, this improved operation preferably combines the operations of first and second derivatives, specifically,

[0076] Among them, AvgP i Let D1 be the mean of the i-th channel image, and n be the number of channels in the spectral image. i Let D2 be the first derivative corresponding to the i-th channel. i Let be the second derivative of the i-th channel.

[0077] Example 6

[0078] Further extraction of image features and channel features of fertilized eggs is performed. In this embodiment, image texture information and channel information are further extracted, and the channel features are reduced.

[0079] In this embodiment, the following processing is performed: the channel dimension is reduced by pointwise convolution; depthwise convolution is performed on the reduced channels to extract the features within each channel; pointwise convolution is performed again to fuse the information between channels, resulting in the output image with reduced channels.

[0080] The second filtering layer can be implemented using conventional convolution methods. Taking classic full convolution and dilated convolution as examples, comparative experiments show that depthwise separable convolution not only achieves the best accuracy of 0.954, but also requires fewer parameters and training parameters than full convolution and dilated convolution, which helps reduce the model's inference time and accelerate the prediction efficiency of eggs.

[0081] Preferably, depthwise separable convolutional layers are used to further extract image features and channel features of fertilized eggs, which yields the best results.

[0082] In another embodiment, the provided electronic device 100 is an integrated device capable of acquiring spectral images of fertilized eggs in specific bands (see Figure 5), and then segmenting the region of interest from the spectral images of specific bands. In this step, the R, G, and B bands of the spectral images of specific bands are first merged, the egg range is selected and a grayscale image is obtained, and then the grayscale image is further processed to segment the spectral image of the region of interest from the spectral images of specific bands; finally, the spectral images of fertilized eggs in specific bands are processed again.

[0083] Example 7

[0084] This embodiment of the invention provides a method for non-destructive identification of the sex of eggs, which includes three steps: First, an image acquisition device 200 acquires a spectral image of a fertilized egg in a specific wavelength band. The acquisition process is shown in Figure 6. A halogen lamp light source 300 illuminates the fertilized egg 400 placed on a moving platform 500, and the image acquisition device 200 acquires a spectral image of a specific wavelength band. Then, the spectral image of the specific wavelength band is preprocessed. Finally, an electronic device 100 processes the preprocessed spectral image of the fertilized egg in the specific wavelength band.

[0085] In another embodiment, preprocessing of the spectral image of a specific band includes segmenting the region of interest from the spectral image of the specific band. Specifically, referring to Figure 5, the R, G, and B bands of the spectral image of the specific band are merged, the range of the egg is selected, and a grayscale image is obtained; the grayscale image is further processed to segment the spectral image of the region of interest from the spectral image of the specific band.

[0086] In a preferred embodiment, the image acquisition device 200 is capable of directly acquiring spectral images including four bands: 945.354 nm, 762.407 nm, 409.377 nm, and 644.587 nm.

[0087] In another preferred embodiment, the image acquisition device 200 is capable of directly acquiring spectral images in twenty-two bands, including 945.354 nm, 762.407 nm, 409.377 nm, 644.587 nm, 888.39 nm, 399.991 nm, 618.669 nm, 578.621 nm, 728.801 nm, 954.091 nm, 562.989 nm, 470.638 nm, 1004.87 nm, 904.482 nm, 520.684 nm, 779.97 nm, 718.592 nm, 441.857 nm, 840.049 nm, 494.166 nm, 670.619 nm, and 829.789 nm.

[0088] Compared with existing technologies, this invention can directly acquire spectral images of specific wavelengths through electronic devices to accurately determine the sex of early chicken embryos. Furthermore, the identification process is primarily completed autonomously by the equipment, resulting in a high degree of automation and significantly reducing labor and time costs.

[0089] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An electronic device (100), characterized in that: include, Memory (101), storing computer-readable instructions; and, The processor (102), when executing computer-readable instructions, is configured to process spectral images of specific bands of fertilized eggs; The ability to process spectral images of specific wavelengths of fertilized eggs includes, Spectral image bands for screening characteristics of fertilized eggs; and, Further extract image features and channel features of fertilized eggs; The spectral image of the specific band includes, Spectral images in the 945.354nm, 762.407nm, 409.377nm and 644.587nm bands.

2. The electronic device (100) as claimed in claim 1, characterized in that: The spectral image of the specific band also includes, Spectral images of the 888.39nm, 399.991nm, 618.669nm, 578.621nm, 728.801nm, 954.091nm, 562.989nm, 470.638nm, 1004.87nm, 904.482nm, 520.684nm, 779.97nm, 718.592nm, 441.857nm, 840.049nm, 494.166nm, 670.619nm, and 829.789nm bands.

3. The electronic device (100) as claimed in claim 1 or 2, characterized in that: The spectral image bands used to screen fertilized eggs capture information about the correlation between potential channels in the average spectrum of the spectral image of a specific band through a channel attention mechanism, assigning greater weight to important channels.

4. The electronic device (100) as claimed in claim 3, characterized in that: The spectral image bands used to screen fertilized eggs are processed as follows. Each channel of the spectral image is downsampled to a mean; By performing improvements, a multi-dimensional vector is obtained; The resulting vectors are summed to obtain the weight of each channel; The weights are multiplied by each channel of the spectral image to include channel importance features in the output data.

5. The electronic device (100) as claimed in claim 1, 2 or 4, characterized in that: The image feature bands used to screen fertilized eggs are obtained by improving the SE layer. This improvement involves performing first-order and second-order derivative operations. Specifically... Among them, AvgP i Let D1 be the mean of the i-th channel image, and n be the number of channels in the spectral image. i Let D2 be the first derivative corresponding to the i-th channel. i Let be the second derivative of the i-th channel.

6. The electronic device (100) as claimed in claim 1, 2 or 4, characterized in that: The process further extracts image features and channel features of fertilized eggs, further extracts image texture information and channel information, and reduces the channel features.

7. The electronic device (100) as claimed in claim 6, characterized in that: The image features and channel features of the fertilized eggs are further extracted and processed as follows. The channel dimension is reduced by using pointwise convolution; The reduced channels are subjected to depthwise convolution to extract the image features within each channel; Then, perform pointwise convolution again to fuse the information between channels, resulting in an output image with fewer channels.

8. The electronic device (100) as claimed in claim 1, 2, 4 or 7, characterized in that: The further extraction of image features and channel features of fertilized eggs is achieved through a depthwise separable convolution algorithm.

9. The electronic device (100) as claimed in claim 1, 2, 4 or 7, characterized in that: It also includes, Acquire spectral images of fertilized eggs in specific wavelength bands; The region of interest is segmented from the spectral image of the specific band.

10. A method for non-destructive identification of the sex of eggs, characterized in that: include, The image acquisition device (200) acquires spectral images of fertilized eggs in specific wavelength bands; Preprocess the spectral image of the specific waveband; The spectral images of fertilized eggs in specific wavelengths are processed using an electronic device (100).

11. The method for non-destructive identification of egg sex as described in claim 10, characterized in that: Preprocessing the spectral image of the specific band includes segmenting the region of interest from the spectral image of the specific band.

12. The method for non-destructive identification of egg sex as described in claim 11, characterized in that: The segmentation of the region of interest from the spectral image of the specific band includes, The spectral image of the specific band is merged into R, G, and B bands, the egg range is selected, and a grayscale image is obtained. The grayscale image is further processed to segment the spectral image of the region of interest from the spectral image of the specific band.

Images