US 2020/0348248 A1 · Automated Noninvasive Determining the Fertility of a Bird's Egg

Abstract

Shown herein is a method of automated noninvasive determining the fertility of a bird's egg (14), comprising the following steps: conveying a plurality of bird eggs (14) sequentially or in parallel into an NMR apparatus (18), subjecting the bird eggs (14) to an NMR measurement, such as to generate a 3-D NMR image of at least a part of each of said eggs (14), said 3-D NMR image having a spatial resolution in at least one dimension of 1.0 mm or less, preferably of 0.50 mm or less, wherein said part of the egg (14) includes the germinal disc of the respective egg (14), determining a prediction of the fertility according to at least one of the following two procedures: (i) deriving at least one feature from each of said 3-D NMR images, and employing said at least one feature in a feature-based classifier for determining a prediction of the fertility, and (ii) using a deep learning algorithm, and in particular a deep learning algorithm based on convolutional neural networks, generative adversarial networks, recurrent neural networks or long short-term memory networks.

Claims27

Dependent claims

A method of automated noninvasive determining the fertility of a bird's egg, comprising the following steps:

conveying a plurality of bird eggs sequentially or in parallel into an NMR apparatus,
subjecting the bird eggs to an NMR measurement and generating a 3-D NMR image of at least a part of each of said eggs, prior to incubation, said 3-D NMR image having a spatial resolution in at least one dimension of 1.0 mm or less, preferably of 0.50 mm or less, wherein said part of the egg includes the germinal disc of the respective egg, and
determining a prediction of the fertility by deriving at least one feature from each of said 3-D NMR images, and employing said at least one feature in a feature-based classifier for determining a prediction of the fertility,
wherein said at least one feature is chosen from the group consisting of a diameter of the germinal disc, the volume of the germinal disc, the shape of the germinal disc, the texture of the germinal disc, the location of the germinal disc in the egg, and a ratio between the volumes or surfaces of the germinal disc and one of the yolk, the latebra, and the albumen.

1 more element

A method of automated noninvasive determining the fertility of a bird's egg comprising the following steps:

conveying a plurality of bird eggs sequentially or in parallel into an NMR apparatus, subjected the bird eggs to an NMR measurement and generating a 3-D NMR image of at least a part of each of said eggs, prior to incubation, said 3-D NMR image having a spatial resolution in at least one dimension of 1.0 mm or less, preferably of 0.50 mm or less, wherein said part of the egg includes the germinal disc of the respective egg, and wherein said 3-D NMR images allows for discerning at least one features chosen from the group consisting of a diameter of the germinal disc, the volume of the germinal disc, the shape of the germinal disc, the texture of the germinal disc, the location of the germinal disc in the egg, and a ratio between the volumes or surfaces of the germinal disc and one of the yolk, the latebra, and the albumen, said method further comprising a step of:
determining a prediction of the fertility by using a deep learning algorithm on said 3-D NMR image.

An apparatus for automated noninvasive determining the fertility of a bird's egg said apparatus comprising:

an NMR apparatus,
a conveying device for conveying a plurality of bird eggs sequentially or in parallel into said NMR apparatus and out of said NMR apparatus,
wherein said NMR apparatus is configured for subjecting the bird eggs to an NMR measurement,
wherein said apparatus further comprises a classification module and an egg sorting device for sorting the eggs according to the egg fertility prediction provided by said classification module, wherein said NMR apparatus is configured for generating a 3-D NMR image of at least a part of each of said eggs, said 3-D NMR image having a spatial resolution in at least one dimension of 1.0 mm or less, preferably of 0.50 mm or less, wherein said part of the egg includes the germinal disc of the respective egg, and wherein said classification module is configured for determining a prediction of the fertility by deriving at least one feature from each of said 3-D NMR images, and employing said at least one feature in a feature-based classifier for determining a prediction of the fertility, wherein said at least one feature is chosen from the group consisting of a diameter of the germinal disc, the volume of the germinal disc, the shape of the germinal disc, the texture of the germinal disc, the location of the germinal disc in the egg, and a ratio between the volumes or surfaces of the germinal disc and one of the yolk, the latebra, and the albumen.

1 more element

An apparatus for automated noninvasive determining the fertility of a bird's egg said apparatus comprising:

an NMR apparatus,
a conveying device for conveying a plurality of bird eggs sequentially or in parallel into said NMR apparatus and out of said NMR apparatus,
wherein said NMR apparatus is configured for subjecting the bird eggs to an NMR measurement,
wherein said apparatus further comprises a classification module and
an egg sorting device for sorting the eggs according to the egg property prediction provided by said classification module, wherein said NMR apparatus is configured for subjecting the bird eggs to an NMR measurement and generating a 3-D NMR image of at least a part of each of said eggs, said 3-D NMR image having a spatial resolution in at least one dimension of 1.0 mm or less, preferably of 0.50 mm or less, wherein said part of the egg includes the germinal disc of the respective egg, and wherein said 3-D NMR image allows for discerning at least one feature chosen from the group consisting of a diameter of the germinal disc, the volume of the germinal disc, the shape of the germinal disc, the texture of the germinal disc, the location of the germinal disc in the egg, and a ratio between the volumes or surfaces of the germinal disc and one of the volk, the latebra, and the albumen, and wherein said classification module is configured for determining a prediction of the fertility by using a deep learning algorithm on said 3-D NMR image.

2 more elements

Dependencies are inferred from the claim text.

Automated Noninvasive Determining the Fertility of a Bird's Egg

Life of this patent

Automated Noninvasive Determining the Fertility of a Bird's Egg

Life of this patent

Abstract

Claims27