Appeal 2007-0862
Application 10/680,675
plant embryos. That is, the known samples are used to train a computer to
recognize embryos having similar characteristic(s). (Specification 8: 24-26
(“The classification model is deduced from a ‘training’ data set of multiple
images of plant embryos or plant embryo organs acquired from embryos
having known embryo quality.”)).
After a classification model has been generated based on known
samples, it is applied to digital images of a plant embryo of unknown
characteristics, in order to classify the unknown embryo “according to its
presumed quantifiable characteristics”; i.e., the unknown embryo is
classified as similar to or dissimilar from the embryos in the training set.
(Specification 8: 30-31 (“Unclassified embryos are classified as acceptable
or not based on how close images of the unclassified embryos fit to the
classification model developed from the training set groups.”)).
Claim 14 specifies that the “quantifiable characteristics” can be
conversion potential (i.e., likelihood to germinate; Specification 7: 13-15);
resistance to pathogens, drought, heat, or cold; salt tolerance; preference for
light quality; or suitability to long-term storage (i.e., storage of the embryos
themselves; Specification 7: 15-18). These characteristics are referred to
generically as “plant embryo quality” in the Specification (id. at 7: 5-19).
2. WRITTEN DESCRIPTION
Claims 1-14 stand rejected under 35 U.S.C. § 112, first paragraph, as
lacking an adequate written description in the Specification. The Examiner
finds that the Specification describes the claimed method only as applied to
selecting embryos for their germination potential, and not with respect to
other quantifiable characteristics:
4
Page: Previous 1 2 3 4 5 6 7 8 9 10 11 12 Next
Last modified: September 9, 2013