Weyerhaeuser Nr Company

Mitchell R Toland

Roger Timmis

William C Carlson

James A Grob

Timnit Ghermay

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.

Image classification of germination potential of somatic embryos

A method of classifying plant embryos according to their quality based on a general form of Lorenz-Bayes classifier is disclosed. First, image or spectral data of plant embryos of known quality are acquired, and the data are divided into two classes according to the embryos' known quality. Second, metrics are calculated from the acquired image or spectral data in each class. Third, multi-dimensional histograms of multiple metrics are prepared for both classes. Fourth, the difference or some other measure of comparison between the two multi-dimensional histograms is obtained. Fifth, image or spectral data of a plant embryo of unknown quality are obtained and metrics are calculated therefrom. Sixth, the embryo of unknown quality is assigned to a class based on its calculated metrics and the result of the comparison as calculated in the fourth step above.

General method of classifying plant embryos using a generalized Lorenz-Bayes classifier

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.

Growing community of inventors

Puyallup, WA, United States of America

Mitchell R Toland