Xiao Li

US Patent:

20110182517, Jul 28, 2011

Filed:

Jan 20, 2011

Appl. No.:

13/010448

Inventors:

Stephanie J. Chiu - Durham NC, US
Cynthia A. Toth - Chapel Hill NC, US
Joseph A. Izatt - Raleigh NC, US
Xiao T. Li - Cumming GA, US
Peter Christopher Nicholas - Durham NC, US

Assignee:

DUKE UNIVERSITY - Durham NC

International Classification:

G06K 9/66

US Classification:

382190

Abstract:

Disclosed herein are systems and method for segmentation and identification of structured features in images. According to an aspect, a method may include representing an image as a graph of nodes connected together by edges. For example, the image may be an ocular image showing layered structures or other features of the retina. The method may also include adding, to the graph, nodes adjacent to nodes along first and second sides of the graph. The added nodes may have edge weights less than the nodes along the first and second sides of the graph. Further, the method may include assigning start and end points to any of the added nodes along the first and second sides, respectively. The method may also include graph cutting between the start and end points for identifying a feature in the image.

US Patent:

20210014477, Jan 14, 2021

Filed:

Jul 10, 2020

Appl. No.:

16/926570

Inventors:

- Plantation FL, US
Jeffrey Todd Daiker - Lafayette CO, US
Tim Ellis - Plantation FL, US
Xiao Li - Cooper City FL, US
Jeremy A. Grata - Coral Springs FL, US

Assignee:

Magic Leap, Inc. - Plantation FL

International Classification:

H04N 17/00
G06T 7/80
G06T 7/90
G06T 7/60
G06T 7/70

Abstract:

Embodiments provide a camera design (e.g., an eyeball camera) that mimics a human eye in geometry, optical performance and/or motion. The eyeball camera adopts the same cornea and pupil geometry from the human eye, and has the iris and pupil configured with multiple texture, color or diameter options. The resolution of the eyeball camera is designed to match the acuity of typical 20/20 human vision, and focus is adjusted from 0 to 4 diopters. A pair of eyeball cameras are mounted independently on two hexapods to simulate the human eye gaze and vergence. The perceived virtual and real world are calibrated and evaluated based on eye conditions like pupil location and gaze using the eyeball cameras. The eyeball camera serves as a bridge to combine the data from spatial computing like eye tracking, 3D geometry of the digital world, display color accuracy/uniformity, and display optical quality (sharpness, contrast, etc.).

US Patent:

20170140544, May 18, 2017

Filed:

Jan 31, 2017

Appl. No.:

15/421247

Inventors:

- Durham NC, US
Stephanie J. Chiu - Durham NC, US
Cynthia A. Toth - Chapel Hill NC, US
Joseph A. Izatt - Raleigh NC, US
Xiao T. Li - Cumming GA, US
Peter Christopher Nicholas - Durham NC, US

International Classification:

G06T 7/11
A61B 5/00
A61B 3/00
A61B 3/10
G06T 7/00
G06T 7/162

Abstract:

Disclosed herein are systems and method for segmentation and identification of structured features in images. According to an aspect, a method may include representing an image as a graph of nodes connected together by edges. For example, the image may be an ocular image showing layered structures or other features of the retina. The method may also include adding, to the graph, nodes adjacent to nodes along first and second sides of the graph. The added nodes may have edge weights less than the nodes along the first and second sides of the graph. Further, the method may include assigning start and end points to any of the added nodes along the first and second sides, respectively. The method may also include graph cutting between the start and end points for identifying a feature in the image.

US Patent:

20160171688, Jun 16, 2016

Filed:

Feb 21, 2016

Appl. No.:

15/049103

Inventors:

- Durham NC, US
Stephanie J. Chiu - Durham NC, US
Cynthia A. Toth - Chapel Hill NC, US
Josheph A. Izatt - Raleigh NC, US
Xiao T. Li - Cumming GA, US
Peter Christopher Nicholas - Durham NC, US

International Classification:

G06T 7/00
A61B 3/10
A61B 3/00

Abstract:

Disclosed herein are systems and method for segmentation and identification of structured features in images. According to an aspect, a method may include representing an image as a graph of nodes connected together by edges. For example, the image may be an ocular image showing layered structures or other features of the retina. The method may also include adding, to the graph, nodes adjacent to nodes along first and second sides of the graph. The added nodes may have edge weights less than the nodes along the first and second sides of the graph. Further, the method may include assigning start and end points to any of the added nodes along the first and second sides, respectively. The method may also include graph cutting between the start and end points for identifying a feature in the image.

US Patent:

20140334703, Nov 13, 2014

Filed:

Jul 21, 2014

Appl. No.:

14/337215

Inventors:

- Durham NC, US
Stephanie J. Chiu - Durham NC, US
Cynthia A. Toth - Chapel Hill NC, US
Joseph A. Izatt - Raleigh NC, US
Xiao T. Li - Cumming GA, US
Peter Christopher Nicholas - Durham NC, US

International Classification:

G06T 7/00
A61B 5/00

US Classification:

382131

Abstract:

Disclosed herein are systems and method for segmentation and identification of structured features in images. According to an aspect, a method may include representing an image as a graph of nodes connected together by edges. For example, the image may be an ocular image showing layered structures or other features of the retina. The method may also include adding, to the graph, nodes adjacent to nodes along first and second sides of the graph. The added nodes may have edge weights less than the nodes along the first and second sides of the graph. Further, the method may include assigning start and end points to any of the added nodes along the first and second sides, respectively. The method may also include graph cutting between the start and end points for identifying a feature in the image.