Method for classifying plant embryos using Raman spectroscopy
    2.
    发明申请
    Method for classifying plant embryos using Raman spectroscopy 审中-公开
    使用拉曼光谱分类植物胚胎的方法

    公开(公告)号:US20060160065A1

    公开(公告)日:2006-07-20

    申请号:US11323404

    申请日:2005-12-29

    IPC分类号: C12Q1/00

    摘要: A three-step method for classifying plant embryo quality using Raman spectroscopy is provided. First, a classification model is developed based on Raman spectral data of reference samples of plant embryos or any portions of plant embryos of known embryo quality. The embryo quality may be known based on a comparison to a normal zygotic embryo or on actual planting of the embryo to observe its germination and subsequent growth. Then, a data analysis is carried out by applying one or more classification algorithms to the acquired Raman spectral data to develop a classification model. Second, Raman spectral data of a plant embryo or any portion of a plant embryo of unknown embryo quality are obtained. Third, the classification model developed in the first step is applied to the Raman spectral data obtained from the embryo (or any portions thereof) of unknown quality to classify the quality of this plant embryo.

    摘要翻译: 提供了使用拉曼光谱分类植物胚胎质量的三步法。 首先,基于植物胚胎的参考样品或已知胚胎质量的植物胚胎的任何部分的拉曼光谱数据开发分类模型。 胚胎质量可以基于与正常合子胚胎的比较或胚胎的实际种植来观察其发芽和随后的生长而已知。 然后,通过对获取的拉曼光谱数据应用一个或多个分类算法来开发分类模型来进行数据分析。 第二,获得植物胚胎或未知胚胎质量的植物胚胎的任何部分的拉曼光谱数据。 第三,将第一步开发的分类模型应用于从未知质量的胚胎(或其任何部分)获得的拉曼光谱数据,以对该植物胚胎的质量进行分类。

    METHODS FOR CLASSIFICATION OF SOMATIC EMBRYOS
    4.
    发明申请
    METHODS FOR CLASSIFICATION OF SOMATIC EMBRYOS 审中-公开
    SOMATIC EMBRYOS分类方法

    公开(公告)号:US20080052056A1

    公开(公告)日:2008-02-28

    申请号:US11861213

    申请日:2007-09-25

    IPC分类号: G06G7/48

    摘要: The present invention is directed towards methods for the classification of plant embryos by the application of one or more classification algorithms to analyze digitized images and absorption, transmittance, or reflectance spectra. The methods are generally applicable and emphasize the importance of acquiring and using as much image and absorption, transmittance, or reflectance spectral information as possible, based on objective criteria. The present invention allows automated selection of embryos most suitable for further culture and rejection of those seen as less suitable.

    摘要翻译: 本发明涉及通过应用一种或多种分类算法来分析数字化图像和吸收,透射率或反射光谱来分类植物胚胎的方法。 这些方法通常是适用的,并强调基于客观标准获取和使用尽可能多的图像和吸收,透射率或反射光谱信息的重要性。 本发明允许自动选择最适合进一步培养和排除那些被认为不太适合的胚胎。

    METHODS FOR CLASSIFICATION OF SOMATIC EMBRYOS
    5.
    发明申请
    METHODS FOR CLASSIFICATION OF SOMATIC EMBRYOS 审中-公开
    SOMATIC EMBRYOS分类方法

    公开(公告)号:US20070276640A1

    公开(公告)日:2007-11-29

    申请号:US11836095

    申请日:2007-08-08

    IPC分类号: A01H7/00 G06G7/58

    摘要: The present invention is directed towards methods for the classification of plant embryos by the application of one or more classification algorithms to analyze digitized images and absorption, transmittance, or reflectance spectra. The methods are generally applicable and emphasize the importance of acquiring and using as much image and absorption, transmittance, or reflectance spectral information as possible, based on objective criteria. The present invention allows automated selection of embryos most suitable for further culture and rejection of those seen as less suitable.

    摘要翻译: 本发明涉及通过应用一种或多种分类算法来分析数字化图像和吸收,透射率或反射光谱来分类植物胚胎的方法。 这些方法通常是适用的,并强调基于客观标准获取和使用尽可能多的图像和吸收,透射率或反射光谱信息的重要性。 本发明允许自动选择最适合进一步培养和排除那些被认为不太适合的胚胎。

    Methods for processing spectral data for enhanced embryo classification
    6.
    发明授权
    Methods for processing spectral data for enhanced embryo classification 有权
    用于处理增强胚胎分类的光谱数据的方法

    公开(公告)号:US07610155B2

    公开(公告)日:2009-10-27

    申请号:US11297919

    申请日:2005-12-08

    IPC分类号: G01N33/48 G01N33/50

    CPC分类号: G06K9/0014 G06K9/00147

    摘要: A method is disclosed for classifying plant embryos according to their quality using a logistic regression model. First, sets of image or spectral data are acquired from plant embryos of known quality, respectively. Second, each of the acquired sets of image or spectral data is associated with one of multiple class labels according to the corresponding embryo's known quality. Third the sets of image or spectral data values are filtered to provide filtered image or spectral data values. Fourth, a classification algorithm, e.g., a logistic regression analysis is applied to the filtered data values and their corresponding class labels to develop a classification model. Fifth, image or spectral data are acquired from a plant embryo of unknown quality, and filtered data values are derived therefrom. Sixth, the classification model is applied to the filtered data values for the plant embryo of unknown quality to classify the same.

    摘要翻译: 公开了一种使用逻辑回归模型根据其质量对植物胚胎进行分类的方法。 首先,分别从已知质量的植物胚胎获取图像或光谱数据集。 其次,根据相应的胚胎的已知质量,获得的图像或光谱数据集合中的每一个与多个类别标签之一相关联。 第三,对图像或光谱数据值集合进行滤波以提供滤波图像或光谱数据值。 第四,将分类算法,例如逻辑回归分析应用于过滤的数据值及其对应的类标签,以开发分类模型。 第五,从未知质量的植物胚胎获取图像或光谱数据,并从其中导出滤波数据值。 第六,将分类模型应用于未知质量的植物胚胎的过滤数据值进行分类。

    Automated system and method for harvesting and multi-stage screening of plant embryos
    9.
    发明授权
    Automated system and method for harvesting and multi-stage screening of plant embryos 有权
    用于植物胚胎收获和多期筛选的自动化系统和方法

    公开(公告)号:US07685767B2

    公开(公告)日:2010-03-30

    申请号:US11778766

    申请日:2007-07-17

    IPC分类号: A01C1/06 A01C21/00

    摘要: A method and system for automatically harvesting and screening plant embryos in multiple stages to identify those embryos that are suited for incorporation into manufactured seeds are provided. The method includes generally three steps. First, plant embryos are automatically sorted according to their rough size/shape and also singulated into discrete embryo units, for example by vibrational sieving. Second, the sorted and singulated plant embryos are classified using a first classification method. For example, each embryo may be imaged by a camera and the image is used to ascertain the embryo's more precise size/shape. Third, for those embryos that have passed the first classification method, a second classification method is applied. For example, a pre-developed classification algorithm to classify embryos according to their putative germination vigor may be applied to the same image used in the first classification method, to identify those embryos that are likely to germinate.

    摘要翻译: 提供了一种用于自动收获和筛选多个阶段的植物胚胎的方法和系统,以鉴定适合于掺入生产的种子的那些胚胎。 该方法通常包括三个步骤。 首先,植物胚胎根据其粗糙尺寸/形状自动分类,并且通过振动筛选也分离成离散的胚胎单位。 第二,使用第一种分类方法分类和分割的植物胚胎。 例如,可以通过照相机对每个胚胎进行成像,并且使用该图像来确定胚胎更精确的尺寸/形状。 第三,对于已经通过第一种分类方法的那些胚胎,应用第二种分类方法。 例如,可以将根据其推定的发芽活力对胚胎进行分类的预先开发的分类算法应用于在第一种分类方法中使用的相同图像,以鉴定可能发芽的胚胎。

    Automated system and method for harvesting and multi-stage screening of plant embryos
    10.
    发明授权
    Automated system and method for harvesting and multi-stage screening of plant embryos 有权
    用于植物胚胎收获和多期筛选的自动化系统和方法

    公开(公告)号:US07530197B2

    公开(公告)日:2009-05-12

    申请号:US10853491

    申请日:2004-05-24

    摘要: A method and system for automatically harvesting and screening plant embryos in multiple stages to identify those embryos that are suited for incorporation into manufactured seeds are provided. The method includes generally three steps. First, plant embryos are automatically sorted according to their rough size/shape and also singulated into discrete embryo units, for example by vibrational sieving. Second, the sorted and singulated plant embryos are classified using a first classification method. For example, each embryo may be imaged by a camera and the image is used to ascertain the embryo's more precise size/shape. Third, for those embryos that have passed the first classification method, a second classification method is applied. For example, a pre-developed classification algorithm to classify embryos according to their putative germination vigor may be applied to the same image used in the first classification method, to identify those embryos that are likely to germinate.

    摘要翻译: 提供了一种用于自动收获和筛选多个阶段的植物胚胎的方法和系统,以鉴定适合于掺入生产的种子的那些胚胎。 该方法通常包括三个步骤。 首先,植物胚胎根据其粗糙尺寸/形状自动分类,并且通过振动筛选也分离成离散的胚胎单位。 第二,使用第一种分类方法分类和分割的植物胚胎。 例如,可以通过照相机对每个胚胎进行成像,并且使用图像来确定胚胎更精确的大小/形状。 第三,对于已经通过第一种分类方法的那些胚胎,应用第二种分类方法。 例如,可以将根据其推定的发芽活力对胚胎进行分类的预先开发的分类算法应用于在第一种分类方法中使用的相同图像,以鉴定可能发芽的胚胎。