Back to results
US 2019/0197332 A1Published application
Method and system for aligning and classifying images
AssigneeChristopher L. Kavanau
InventorsChristopher L. Kavanau, Luisa Montesano
Life of this patent
Estimating the term…
Abstract
In one embodiment, L dimensional images are trained, mapped, and aligned to an M dimensional topology to obtain azimuthal angles. The aligned L dimensional images are then trained and mapped to an N dimensional topology to obtain 2N vertex classifications. The azimuthal angles and the 2N vertex classifications are used to map L dimensional images into 0 dimensional images.
Claims26
1-20. (canceled)
A system for aligning and classifying images of an object, comprising:
- a computer processor configured to:
- train and map a set of input 2-dimensional images to an O-dimensional cylindrical topology or geometry to obtain azimuthal angles with respect to the set of 2-dimensional images.
A computer-implemented method for aligning and classifying images of an object, comprising:
- training and mapping a set of input 2-dimensional images to an O-dimensional cylindrical topology or geometry to obtain azimuthal angles with respect to the set of 2-dimensional images.
Dependencies are inferred from the claim text.