US 2006/0068372 A1 · Method of classifying plant embryos using penalized logistic regression

Abstract

A method is disclosed for classifying plant embryos according to their quality using a penalized logistic regression (PLR) 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, sets of metrics are calculated based on the acquired sets of image or spectral data, respectively. Fourth, a penalized logistic regression (PLR) analysis is applied to the sets of metrics and their corresponding class labels to develop a PLR-based classification model. Fifth, image or spectral data are acquired from a plant embryo of unknown quality, and metrics are calculated based therefrom. Sixth, the PLR-based classification model is applied to the metrics calculated for the plant embryo of unknown quality to classify the same.

Claims20

Dependent claims

A method of classifying plant embryos according to their quality, comprising the steps of:

(a) acquiring sets of image and/or spectral data from plant embryos of known quality, respectively;
(b) associating each of the acquired sets of image and/or spectral data acquired from a plant embryo with one of multiple class labels corresponding to the embryos' known quality;
(c) calculating a set of metrics based on each of the acquired sets of image and/or spectral data, wherein each set of metrics is associated with a class label corresponding to the quality of the embryo based on which the set of metrics is calculated;
(d) applying a penalized logistic regression (PLR) analysis to the sets of metrics and their corresponding class labels to develop a PLR-based classification model;
(e) acquiring image and/or spectral data from a plant embryo of unknown quality and calculating metrics based on the acquired image and/or spectral data of the plant embryo of unknown quality;
and
(f) applying the PLR-based classification model to the metrics calculated for the plant embryo of unknown quality to classify the same.

4 more elements

Dependencies are inferred from the claim text.

Method of classifying plant embryos using penalized logistic regression

Life of this patent

Method of classifying plant embryos using penalized logistic regression

Life of this patent

Abstract

Claims20