Method and imaging system for determining the sex of an egg embryo

Abstract

The invention relates to a method for determining the sex of the embryo in an egg (O), said method comprising the steps of: Placing the egg (O) in a horizontal position on a support (4), the longitudinal axis (X) of the egg being parallel to said support on which it rests; Emitting, using a light source, a luminous flux (F) in the visible range to the egg, in a direction transverse to the egg (O); Acquiring images of the egg on at least three distinct spectral bands, called observation spectral bands, between 500 nm and 630 nm, and on a spectral band called the normalization band between 630 nm and 700 nm; Processing the acquired images to generate a normalized image; Processing the normalized image using a predictive model (MOD) to determine the sex of the embryo in the egg. Figure to be published with the abstract: Figure 2

Description

Title of the invention: Imaging method and system for determining the sex of an egg embryo. Technical field of the invention

[0001] The present invention relates to the field of poultry production and in particular to the non-invasive determination of the gender of avian egg embryos during incubation. State of the art

[0002] The search for an early and non-invasive sexing technique for poultry eggs (chicken, duck) has been a subject of interest to the poultry industry for several years.

[0003] Invasive techniques have been proposed in the prior art, in particular in patent applications WO98 / 14781, DE102007013102, WO2010 / 103111, US2011 / 0144473A1, WO2017 / 174337.

[0004] Non-invasive optical techniques have also been proposed. Some of these techniques relate to the detection of egg fertility and not to sexing. In this regard, US patent 9,435,732 and US patent 6,029,080 can be cited in particular.

[0005] Other non-invasive optical techniques have also been proposed, these being based on the exploitation of spectral and / or spatial characteristics, obtained by mono, multi or hyperspectral imaging, or by spectrometry, in wavelength ranges extending from the visible to the near infrared.

[0006] The referenced publication "COR1ON MATTHIAS et AL: In ovo sexing of eggs from brown breeds with a gender-specific color using visible-near-infrared spectroscopy: effect of incubation day and measurement configuration", POULTRYSCIENCE, col.101, n°5; 1 May 2022 page 101782, XP055962758, Oxford, describes for example a technique for sexing chicken eggs by spectroscopic analysis.

[0007] This prior document describes a technique for sexing brown hens by estimating the eumelanin content found in large quantities in the feathers of females. The solution is based on an analysis of spectral data. This approach focuses on identifying the most significant spectral signatures for sex prediction. However, this sex prediction is delayed, as it is only possible on the 14th day of incubation, with the onset of feather development.

[0008] The referenced publication "Nan Jia et al.: Exploratory Study of Sex Identification for Chicken Embryos Based on Blood Vessel Images and Deep Leaming", Agriculture 2023, 13(8), 1480, MDP1, presents a technique for sexing white eggs using conventional imaging (RGB camera) with only the green channel for observation of the egg's cardiovascular system. The analysis is limited The technique relies on spatial information available in this band and cannot exploit any spectral information due to the lack of finer spectral selection. Furthermore, the technique requires drastic selection of eggs based on size, shape, cleanliness, and shell quality. These sorting conditions are incompatible with industrial-scale application of the technique.

[0009] In addition to the choice of biological markers used for sexing, there are also several configurations for imaging embryos. Candling for sexing generally uses a visible light-emitting diode (LED) that illuminates the egg from the air sac side and a camera positioned at 90° to the egg's axis of symmetry to capture the light scattering image. This configuration is not ideal because the homogeneity of the illumination within the egg is poor. Indeed, since the light is scattered in all directions, the longer the path of the light within the egg, the greater the light absorption. This results in a light intensity gradient from the air sac to the tip, which is further accentuated as the light must pass through the yolk, the latter being more absorbent than the white.The strong absorption of yellow at this stage of incubation comes from the development of the cardiovascular system which contains hemoglobin, exhibiting a very high absorption capacity in the wavelength range of the light-emitting diode's illumination between 400nm and 620nm.

[0010] To have a reliable and robust sexing method, several points must be taken into account: - The biological variability of eggs. For this, it is important to improve the detection of cardiovascular systems. - The geometric variability of eggs, the variable dimensions of the eggs modifying the optical absorption properties.

[0011] It is necessary to be able to provide the maximum amount of relevant information to the predictive model used for sexing. During imaging, it is not uncommon for part of the cardiovascular system to be invisible due to incomplete migration during the preparation stage. Rather than eliminating these eggs for sexing, a solution should be proposed that allows them to be sexed like the others.

[0012] There is therefore a need for a reliable method in which all steps contribute to determining the sex of the embryo in the egg. The method must be simple and sufficiently rapid to be industrialized, and allow for the sexing of all types of eggs, with varying biological and geometric configurations.

[0013] The process makes it possible in particular to characterize an embryo at the earliest possible stage. Description of the invention

[0014] This objective is achieved by a method for determining the gender of the embryo of an egg, said method comprising the steps of: - The egg is placed horizontally on a support, with the longitudinal axis of the egg parallel to the support on which it rests. - Emission, using a light source, of a luminous flux in the visible spectrum, directed towards the egg in a direction transverse to the egg, - Acquisition of images of the egg, on at least three distinct spectral bands, called observation spectral bands, between 500nm and 630nm, and on a spectral band called normalization between 630nm and 700nm, - Processing of acquired images to generate a normalized image, - Processing of the normalized image using a predictive model to determine the gender of the embryo in the egg.

[0015] According to a particular feature, image acquisition on a first spectral observation band is implemented on a spectral band centered on 580nm.

[0016] According to another feature, image acquisition on the spectral observation bands is implemented on spectral bands centered on wavelengths equal to 530nm or 550nm, 580nm and 600nm.

[0017] According to another feature, image acquisition on the normalization spectral band is implemented on a spectral band centered on 642nm.

[0018] According to another feature, the acquisition of images of the egg is carried out at several angles around the longitudinal axis of the egg.

[0019] According to another feature, the acquisition of images of the egg from several angles is carried out by rotating the egg on itself around its longitudinal axis.

[0020] According to another feature, image acquisition is implemented using a monochrome camera.

[0021] According to another feature, the predictive model is developed by learning, and in that it incorporates spectral images of eggs.

[0022] According to another feature, the predictive model includes metadata, including temporal data, said temporal data being chosen from one or more of the following data: the date of laying of the egg, the date and time of incubation, the date and time of acquisition of each image.

[0023] The invention also relates to a multi-band imaging system used for determining the gender of an egg embryo, said system comprising: - A suitable support to hold the egg in a horizontal position, - A controlled light source to emit a visible light flux towards the egg, following a direction transverse to the egg, - Means for acquiring images of the egg, on at least three distinct spectral bands, called observation spectral bands, between 500nm and 630nm, and on a spectral band called normalization between 630nm and 700nm, - A unit for processing acquired images, configured to generate a normalized image and to process said normalized image using a predictive model in order to determine the gender of the embryo in the egg.

[0024] According to one particular feature, the acquisition means include a camera (C).

[0025] According to another feature, the acquisition means include a filtering set, adapted to filter the luminous flux emitted by the light source according to said spectral observation bands and said spectral normalization band.

[0026] According to another feature, a first spectral band of observation is centered on 580nm.

[0027] According to another feature, the spectral observation bands are centered on wavelengths equal to 530nm or 550nm, 580nm and 600nm.

[0028] According to another feature, the normalization spectral band is centered on 642nm. Brief description of the figures

[0029] Other features and advantages will become apparent in the detailed description that follows, given in relation to the accompanying drawings in which: - Fig. 1 schematically represents the structure of an egg; - Figure [Fig. 2] schematically represents the imaging system of the invention applied to the sexing of an egg; - Figure 3 shows a diagram illustrating the spectral absorptions of major chemical components of an egg; - Figures 4A and 4B show the relative transmission spectra of a white egg and a brown egg respectively; - Figure 5 shows a diagram representing the transmission spectra the main components of a white duck egg; - Figure 6 illustrates the principle of spectral normalization with a brown egg, with a first image acquired on a reference spectral band centered on 580nm and normalized images of this reference spectral band by different wavelengths greater than 580nm; - Figure 7 illustrates the normalization principle with a brown egg and its Of interest, the images at the top are those acquired at three wavelengths distinct and the bottom images being those obtained after normalization at 596nm and 642nm; - Fig. 8 shows images obtained after normalization to three wavelengths for white eggs; - Fig. 9 shows an example of the realization of a support allowing multi-angle acquisition;

[0030] Detailed description of at least one embodiment

[0031] In the following description and as illustrated by [Fig. 1], the egg O is defined by its axis of revolution symmetry (axis (X)) in the longitudinal direction and by its ovoid surface. Its equator corresponds to the imaginary line drawn on its surface along its entire circumference, at the level of its widest cross-section.

[0032] The system of the invention is used to determine the sex (male or female) of the embryo in the egg.

[0033] The method and system of the invention are based in particular on an analysis by imaging, and not by spectroscopic analysis.

[0034] As is known, with reference to [Fig. 1], the egg O comprises a shell 20, in which is present the embryo 21 to which the eye 22 belongs, and the cardiovascular system 23 containing, in particular, hemoglobin. The egg also comprises an air chamber or sac 24 which is generally located on the opposite side from the tip of the egg. In [Fig. 1], the egg O is shown horizontally, with the air sac 24 positioned to the side.

[0035] The invention applies more particularly to duck or chicken eggs but it is relevant for the sexing of all types of eggs.

[0036] The method of the invention makes it possible to perform sexing using an imaging system. According to the invention, sexing is performed non-invasively. Figure 2 illustrates this principle for a single O egg, but it is possible to replicate it for a set of several eggs.

[0037] With reference to [Fig. 2], the imaging system mainly comprises a light source E capable of generating a luminous flux F and an image sensor, for example a camera C. The system also includes a processing unit coupled to the camera C to acquire and process the images. The processing unit UC uses a predictive model (referenced MOD) to perform the sexing.

[0038] The imaging system is configured to implement: - A multi-band acquisition with specific spectral filtering (via a filtering set 5) to retain only photons of wavelengths suitable for observing the cardiovascular system and which provide relevant information for determining gender; - A spectral normalization principle to attenuate, in the image obtained, the elements / artifacts of the egg O that disrupt the observation of the cardiovascular system (such as calcium stains on the shell, soiling, feathers, etc.) while standardizing the spectral response (with respect to variable biological / geometric phenomena such as the size of an egg,

[0039] Within the scope of the invention, the system may also provide for the possibility of multi-angle image acquisition for repeating measurements and / or detecting hidden information to improve the accuracy of the sexing model. To this end, means 3 may be provided for acting on the support to rotate the egg O around its axis. It would also be possible to move the sensor C.

[0040] The principles of the invention described below are suitable both for enriching a predictive sexing model and for the sexing operation itself, i.e. for determining the gender of the embryo of an egg.

[0041] It should be noted that for the application to in-ovo sexing in ducks and chickens, observation of the cardiovascular system was considered optimal between 72h (beginning of observation of the development of the cardiovascular system) and up to 120h after the start of incubation (beyond this, the cardiovascular system becomes more complex).

[0042] Multi-band acquisition with spectral filters specific to determining the gender of the egg embryo

[0043] The aim is to identify the wavelengths suitable for determining the gender of the embryo of egg O, that is to say in the end the spectral bands of observation relevant for sexing.

[0044] In conjunction with [Fig. 3], it can be seen that the strong absorption of the egg yolk at an incubation stage exceeding 3 days results from the development of the cardiovascular system, which contains oxygen-carrying oxyhemoglobin (HbO2) and deoxyhemoglobin (HbR), which no longer contains oxygen. These two compounds exhibit very strong absorption in the visible wavelength range between 300 nm and 630 nm (as illustrated by [Fig. 3]), and in particular peaks between 540 and 580 nm.

[0045] Beyond 700nm, water, the major component in an egg, quickly absorbs all the light flux, making any observation impossible.

[0046] From [Fig.4A] and [Fig.4B], it can also be seen that light transmission through an egg with its shell only starts beyond 500nm, all wavelengths below 500nm being absorbed by the shell, whether in white or brown eggs.

[0047] The invention therefore aims to use observation wavelengths of the egg in a spectral range between 500nm and 630nm (on the diagram in [Fig. 3], two successive peaks can indeed be observed in this wavelength range). This Filtering allows for the specific selection of wavelengths of interest for efficient observation of the cardiovascular system through an egg.

[0048] According to the invention, an acquisition is therefore made using several filtering wavelengths in the wavelength range of 500nm to 630nm. With richer spectral information, it is thus possible to obtain a signature / fingerprint of the concentration of the different chemical elements constituting the observed egg.

[0049] By way of exception, image acquisition is performed on at least three distinct spectral bands. Generally, the aim is to find a compromise between the complexity and cost of the acquisition system, the accuracy of the model, and the computational speed.

[0050] Even if sexing on a single spectral band would be possible (but less efficient), this joint exploitation of extended spatial and spectral information allows the development of a more precise and robust predictive model, in particular for in-ovo sexing in ducks and chickens.

[0051] To select the relevant spectral bands for observation, one can take into account the level of absorption of the main components of the egg O. From [Fig.5], it can be seen that absorption increases with the concentration of blood, which explains a lower level of transmission at the level of the embryo (heart) compared to the level of transmission of the blood vessels.

[0052] By considering each component of the egg independently, it is observed that higher sexing accuracy is obtained using the transmission spectra of the embryo after 3 days of incubation, compared to the yolk and blood vessels. This proves that the sex information, at this stage, is primarily located in the blood, the concentration of which is highest in the embryo. The spectra of the yolk and blood vessels also carry sex information, but it is less pronounced than that present in the embryo.

[0053] If we take, nevertheless, the spectra of the embryo with those relating to the yolk between 480 and 680 nm, we obtain a high sexing accuracy which varies little with the dataset.

[0054] The table below shows that the sexing accuracy, with a simple algorithm based on spectral analysis, reaches the highest values ​​using transmission data between the 576 nm and 587 nm spectral bands. The choice of this wavelength band is particularly relevant for sexing eggs. Below 530 nm or above 620 nm, the spectral information is more limited for accurately sexing eggs. Wavelength 480 491 501 512 522 533 544 555 565 576 Verified sexing rate 59.5 61.23 62.47 65.18 66.42 67.16 68.89 70.62 71.60 71.85 Wavelength 587 598 608 620 630 640 651 662 679 687 Verified sexing rate 73.58 69.63 68.14 64.19 62.96 62.22 61.48 60.98 60.98 60.49

[0055] Acquisitions with several combinations were also carried out, each combination based on a core wavelength of 587 nm and other complementary wavelengths. For example, by choosing one acquisition at a wavelength of 587 nm and another at a different wavelength such as 533 nm or 555 nm, a level of accuracy of 80% is obtained, very close to that obtained by performing acquisitions at twenty distinct wavelengths. In other words, it is possible to limit oneself to the choice of a few relevant wavelengths to obtain a sufficient level of accuracy.

[0056] For example, the acquisition can be limited to three spectral observation bands containing the wavelengths 533nm, 555nm and 587nm with a bandwidth of lOnm. Spectral normalization

[0057] In addition to image acquisitions on the spectral observation bands, according to the principles described above, the invention also consists of carrying out at least one image acquisition on at least one other spectral band, called the normalization spectral band.

[0058] This spectral band is used to normalize the bands containing the cardiovascular system. Normalization thus reduces the presence of artifacts (such as shell stains, dirt, etc.) and, at the same time, standardizes the measurement between several eggs of different sizes (and therefore with different absorption levels). Indeed, the spectral absorption of an element through the egg is proportional to the volume through which the light passes. However, the volume ratios (and therefore the absorption ratios) of the elements constituting the egg remain independent of size. For example, if the egg as a whole is twice as large, the size of the yolk and the white are also twice as large and absorb twice as much light. Nevertheless, the volume ratios, and therefore the absorption ratios, remain unchanged.Normalization is thus implemented to normalize the images acquired on the selected spectral observation bands. Once this normalization process is completed, sexing is performed on the images. the basis of the normalized image, from which the defects described above have been eliminated, and of the MOD predictive model.

[0059] Figure 6 gives examples of possible spectral normalizations for a brown egg, with an observation spectral band at 580 nm and different normalization bands (from 593 nm to 808 nm). It can be seen that in brown eggs, not all spectral normalization bands are equally relevant, both in terms of contrast between the different components and in terms of their ability to correct shell defects (speckles). Two spectral normalization bands are particularly relevant: the one between 593 and 604 nm and the one between 639 and 647 nm.

[0060] The second spectral normalization band around 642 nm is the most relevant, as it provides both excellent contrast and very good image resolution. At the 642 nm wavelength, there is no longer any signal related to blood absorption, unlike around 596 nm. Figure 7 clearly illustrates this phenomenon, where the embryo's heart is still visible at 596 nm. It is also observed that the normalization quality is better at 642 nm than at 596 nm, with better suppression of protoporphyrin speckles.

[0061] The most relevant normalization spectral bands are those corresponding to the absorption of protoporphyrin pigments present in the shell, namely 539, 589, and 642 nm. The 642 nm normalization spectral band proves to be the most effective, as it is the band where absorption by protoporphyrin is strongest. Figure 4B clearly illustrates a reduction in transmittance around 642 nm due to absorption by protoporphyrin in brown eggs.

[0062] The principle of normalization is therefore all the more relevant in the characterization of brown eggs, due to their color and the presence of speckles linked to the presence of protoporphyrin. In the case of white eggs, normalization can be carried out by choosing a spectral band that allows the presence of speckles to be distinguished only. Many normalization bands are thus possible with the same quality (see [Fig. 8]). To obtain a single normalization for both white and brown eggs, the 642 nm spectral normalization band is preferentially chosen.

[0063] Artifact removal and measurement standardization through spectral normalization improve the visualization of the cardiovascular system in the egg, thereby increasing the accuracy of the predictive model. Several wavelengths can be used for this normalization, but a wavelength that no longer carries information about the cardiovascular system is preferred; therefore, a wavelength greater than 630 nm, and preferably 642 nm, which is compatible with both white and brown eggs.

[0064] In summary, the removal of artifacts and the standardization of the measurement by spectral normalization makes it possible to improve the visualization of the cardiovascular system in the egg and thus to increase the accuracy of the models. Multi-angle acquisition

[0065] Optionally, but still advantageously, it is possible to acquire images of the egg from several distinct angles. Ideally, these acquisitions are performed from several angles around the longitudinal axis of the egg, by rotating the egg about its axis (the simplest solution) and / or by rotating the acquisition system (source + camera). This multi-angle acquisition makes it possible to multiply the measurements on the same egg and thus improve the prediction using the predictive model. Additional information on the development of the cardiovascular system is also integrated by making visible portions of the cardiovascular system that might otherwise have remained hidden. In the case of egg rotation, a low-acceleration movement is preferable to maintain the positioning of the cardiovascular system on the top of the egg when it is placed flat.

[0066] The rotation of the egg around its axis can be implemented using a diabolo type support 40 (see [Fig.9]). Functional imaging system

[0067] The general principle of the multi-band imaging system for visualizing the cardiovascular system for in-ovo sexing purposes in ducks and chickens is presented in [Fig.2] and has already been mentioned above.

[0068] As indicated above, the multi-band imaging system consists mainly of: A light source E emitting a luminous flux F, A support for egg 4, A multi-band imaging device, A processing unit CU. light source

[0069] The light source E is, for example, made up of one or more light-emitting diodes, positioned to illuminate the egg O. The light source E is advantageously positioned to illuminate the egg O from below, and the image acquisition device C is advantageously placed above it, along the same axis, in order to perform a transmission acquisition. In this case, it should be noted that the support 4 of the egg O must be chosen to allow the passage of the luminous flux F emitted by the light source. It can thus be chosen to be transparent to allow, for example, at least 90% of the luminous flux F to pass through, with a minimum of diffusion, and / or, for example with an opening through which the light flux is emitted, and / or having at least one grid-shaped part intended to be traversed by the light flux.

[0070] The light source is chosen to emit in the visible range with a fairly high power in the wavelength range of 500nm to 700nm. Egg stand

[0071] A support 4 is chosen to place the egg O, advantageously in a lying position.

[0072] It should be noted that placing the O egg in a horizontal position optimizes lighting and provides the best possible positioning of the embryo and its cardiovascular system relative to the camera, the cardiovascular system generally floating near the highest point of the egg. Indeed, in this configuration, the light captured by the camera positioned above is very homogeneous because all the rays that reach it have passed through a roughly equivalent portion of the egg (with the exception of the egg's geometry). All the rays also pass through the same components of the egg (albumen, yolk, shell).

[0073] If necessary, the support 4 can integrate means 3 for moving (rotating, translating) the egg for repeating the measurement or extending the measurement area.

[0074] When acquiring data from multiple angles (see above), the support can be chosen to allow the egg to be rotated around its longitudinal axis. By performing this multi-angle acquisition, certain variations in the positioning of the cardiovascular system can be compensated for, thus increasing the number of treatable eggs. It would also be possible to incorporate a translational movement of the egg along its longitudinal axis.

[0075] To rotate the egg around its axis, a support in the form of two diabolos 40 ([Fig.9]) can be used, thus allowing the rotation to be carried out while keeping a space to ensure lighting from below. Multi-band imaging device

[0076] In the system, a multi-band imaging device allows image acquisition on one or more spectral bands in the wavelength range of 500 nm to 700 nm (from 500 nm to 630 nm for the spectral bands used to observe the cardiovascular system and from 630 to 700 nm for the normalization spectral band). The device may advantageously consist of a conventional monochrome camera C (sensitive over the range of 400 to 1000 nm) and a filter wheel forming the filtering assembly 5 described above, the number of filters depending on the number of spectral bands used for observation and acquisition. The filter wheel is rotated so as to position one of its filters between the light source E and the camera C to filter the luminous flux F emitted by the light source E onto the desired spectral band.

[0077] It should be noted that it may be relevant to use other parameters during image acquisition, to enrich the predictive model and thus improve the accuracy of the sexing carried out subsequently.

[0078] It is particularly relevant to take into account the temporal data of the egg: date of laying, date and time of incubation, date and time of acquisition of each image (and possibly a tracing of the egg with its history / origin and other metadata).

[0079] This temporal metadata allows for better control of image acquisition at the same developmental stage across different eggs, reducing observation variability and improving the accuracy of the predictive model. Furthermore, in addition to image data, this metadata can complement the predictive model to increase its accuracy. For example, in ducks and chickens, metadata (laying date, incubation date and time, acquisition date and time) resulted in an almost 5% improvement in accuracy.

[0080] According to an advantageous configuration, the different aspects of the system and the process are as follows: - Filtering around the wavelength of 580nm is optimal for observing the cardiovascular system by combining maximum absorption of the cardiovascular system with good transmission of light flux through the egg; - Other spectral observation bands are chosen in the 500-630nm range to obtain spectral signatures of the different egg components (blood, yolk, or white). For sufficient spectral richness in the 500-630nm range, we recommend selecting one or two filters before 580nm, one filter at 580nm, and one filter after 580nm. Spectral normalization of images optimizes the detectability of the cardiovascular system. The best normalization bands produce very high-quality images in both ducks and chickens. These optimal spectral normalization bands are the protoporphyrin absorption bands, specifically 598 nm and 642 nm. The 642 nm spectral normalization band is preferred because it contains no blood absorption information and corresponds to the maximum protoporphyrin absorption, thus best correcting any defects related to this molecule. - An advantageous combination is formed of filters with a bandwidth of lOnm: Spectral observation bands centered on 530nm, 550nm, 580nm and 600nm and spectral normalization band centered on 642nm. - Optional multi-angle acquisition. - Temporal tracking using metadata such as laying date, incubation date and time, and acquisition date and time. This allows for data acquisition on eggs at the same stage of cardiovascular system development and the creation of more efficient multimodal models (integrating images and metadata from each egg). Operating principle

[0081] The principle of the invention is thus: - Place the egg O on its support 4 advantageously in a horizontal position to allow the migration of the cardiovascular system towards the upper part of the egg. - Perform several image acquisitions of egg O using the multi-band imaging system, on at least three distinct spectral bands, called observation spectral bands, between 500nm and 630nm, and on a spectral band called normalization between 630nm and 700nm, - The observation spectral bands are chosen centered on 530nm, 550nm, 580nm and 600nm and the normalization spectral band is chosen centered on 642nm, - Processing of acquired images to generate a normalized image, - Processing of the normalized image using the predictive model (MOD) for determine the gender of the embryo in the egg.

[0082] The MOD predictive model can be trained on images acquired by the multi-band imaging device described above, possibly in connection with the metadata, in particular temporal, defined above.

[0083] Thanks to the principles of the invention, the quality (of the spatial / spectral information) of the images obtained from the cardiovascular system has enabled the implementation of high-performance models for sexing and in-ovo analysis of duck and chicken eggs, allowing sexing with accuracy levels exceeding 95%.

Claims

Demands

1. A method for determining the gender of the embryo of an egg (0), said method being characterized in that it comprises the steps of: - Placing the egg (0) in a horizontal position on a support (4), the longitudinal axis (X) of the egg being parallel to said support on which it rests, - Emitting, using a light source, a luminous flux (F) in the visible range to the egg, in a direction transverse to the egg (0), - Acquiring images of the egg, on at least three distinct spectral bands, called observation spectral bands, between 500nm and 630nm, and on a spectral band called normalization band between 630nm and 700nm, - Processing the acquired images to generate a normalized image, - Processing the normalized image using a predictive model (MOD) to determine the gender of the embryo of the egg.

2. Method according to claim 1, characterized in that the acquisition of images on a first spectral observation band is implemented on a spectral band centered on 580nm.

3. Method according to claim 1 or 2, characterized in that image acquisition on the spectral observation bands is implemented on spectral bands centered on wavelengths equal to 530nm or 550nm, 580nm and 600nm.

4. A method according to any one of claims 1 to 3, characterized in that image acquisition on the normalization spectral band is implemented on a spectral band centered on 642nm.

5. A method according to any one of claims 1 to 4, characterized in that the acquisition of images of the egg is carried out at several angles around the longitudinal axis of the egg.

6. Method according to claim 5, characterized in that the acquisition of images of the egg from several angles is carried out by rotating the egg (0) on itself around its longitudinal axis (X).

7. A method according to any one of claims 1 to 6, characterized in that image acquisition is carried out using a monochrome camera (C).

8. A method according to any one of claims 1 to 7, characterized in that the predictive model (MOD) is developed by learning, and in that it incorporates spectral images of eggs.

9. A method according to any one of claims 1 to 8, characterized in that the predictive model includes metadata, including time data, said time data being chosen from one or more of the following: the date of laying of the egg, the date and time of incubation, the date and time of acquisition of each image.

10. A multi-band imaging system used for determining the gender of the embryo in an egg (0), said system comprising: - A support (4) adapted to receive the egg (0) in a horizontal position, - A light source (E) controlled to emit, towards the egg, a luminous flux (F) in the visible, in a direction transverse to the egg (0), - Means for acquiring images of the egg, on at least three distinct spectral bands, called observation spectral bands, between 500nm and 630nm, and on a spectral band called normalization band between 630nm and 700nm, - A unit for processing the acquired images, configured to generate a normalized image and to process said normalized image using a predictive model (MOD) in order to determine the gender of the embryo in the egg.

11. System according to claim 10, characterized in that the acquisition means comprise a camera (C).

12. System according to claim 10 or 11, characterized in that the acquisition means comprise a filtering assembly, adapted to filter the luminous flux emitted by the light source according to said spectral observation bands and said spectral normalization band.

13. System according to any one of claims 10 to 12, characterized in that a first spectral band of observation is centered on 580nm.

14. System according to claim 13, characterized in that the spectral bands of observation are centered on wavelengths equal to 530nm or 550nm, 580nm and 600nm.

15. System according to any one of claims 10 to 14, characterized in that the normalization spectral band is centered on 642nm.

Images