Emily Donahue

Title: Emily Donahue: Innovator in Digital Image Segmentation

Introduction

Emily Donahue is a prominent inventor based in Albuquerque, NM (US). She has made significant contributions to the field of digital image segmentation, holding 2 patents that showcase her innovative approach to technology.

Latest Patents

One of her latest patents is titled "Uncertainty-refined image segmentation under domain shift." This patent describes a method for digital image segmentation that involves training a neural network with a labeled training dataset from a first domain. During training, a subset of nodes in the neural network is dropped out. The neural network then processes image data from a second, different domain. For each image element, a vector of N values that sum to 1 is calculated, with each value representing an image segmentation class. A label is assigned to each image element based on the class with the highest value in the vector. The method includes performing multiple inferences with active dropout layers for each image element, generating an uncertainty value for each. If an image element's uncertainty exceeds a predefined threshold, its label is replaced with a new label corresponding to the class with the next highest value.

Career Highlights

Emily Donahue works at National Technology & Engineering Solutions of Sandia, LLC, where she applies her expertise in digital image processing. Her work has been instrumental in advancing the capabilities of image segmentation technologies.

Collaborations

Some of her notable coworkers include Carianne Martinez and Kevin Matthew Potter, who contribute to the innovative environment at Sandia.

Conclusion

Emily Donahue is a trailblazer in the field of digital image segmentation, with her patents reflecting her commitment to advancing technology. Her work continues to influence the industry and inspire future innovations.