Automated landmark extraction from three-dimensional whole body scanned data
First Claim
1. A method for automated landmark extraction from three-dimensional whole body scanned data, the method comprising:
- using a computer to perform the steps of;
extracting feature points as landmarks on the human body;
directly extracting intersection of neck and shoulder, acromion, chest line, hip line, and rearmost of hip based on three-dimensional changes in shape of the body without premarking landmarks prior to scanning;
utilizing silhouette analysis by projecting the three-dimensional whole body scanned data onto a coronal plane to extract an intersection of the neck and shoulder by locating locally minimum points on silhouette curves; and
extracting the intersection of the neck and shoulder at a point between a neck top and the acromion with a maximum vertical distance to a line connected by the neck top and the acromion.
1 Assignment
0 Petitions
Accused Products
Abstract
A method for automated landmark extraction from three-dimensional whole body scanned data extracts feature points as landmarks from a plurality of point clouds obtained from a three-dimensional whole body scanner, without pre-making the landmarks on a human body before scanning. The system includes: (1) Silhouette analysis, which projects three-dimensional body scanned data onto a two-dimensional surface and observes the variations in curvature and depth; (2) Minimum circumference, which uses the variations of the circumference of body parts to define the locations of the landmarks and feature lines; (3) Gray-scale detection, which converts the color information of human body from RGB values into gray-scale values to locate the landmarks with greater variations in brightness; and (4) Human-body contour plot, which simulates the sense of touch to locate landmarks by finding the prominent and concave parts on the human body.
27 Citations
11 Claims
-
1. A method for automated landmark extraction from three-dimensional whole body scanned data, the method comprising:
using a computer to perform the steps of; extracting feature points as landmarks on the human body; directly extracting intersection of neck and shoulder, acromion, chest line, hip line, and rearmost of hip based on three-dimensional changes in shape of the body without premarking landmarks prior to scanning; utilizing silhouette analysis by projecting the three-dimensional whole body scanned data onto a coronal plane to extract an intersection of the neck and shoulder by locating locally minimum points on silhouette curves; and extracting the intersection of the neck and shoulder at a point between a neck top and the acromion with a maximum vertical distance to a line connected by the neck top and the acromion. - View Dependent Claims (2, 3, 4)
-
5. A method for automated landmark extraction from three-dimensional whole body scanned data, the method comprising:
using a computer to perform the steps of; extracting feature points as landmarks on a human body; directly extracting a wrist and waist line based on three-dimensional changes in shape of the human body without premarking landmarks before scanning; and using a minimum circumference scanned from a thinnest part on the human body for extracting the wrist and the waist line.
-
6. A method for automated landmark extraction from three-dimensional whole body scanned data, the method comprising:
using a computer to perform the steps of; extracting feature points as landmarks on a human body; directly extracting bust points based on three-dimensional changes in shape of the human body without premarking landmarks before scanning; converting color information of the human body from RGB values into gray-scale values; and locating visually darker parts to find parts with noticeable variations in brightness to extract bust points for male subjects by filtering out the points with smaller gray-scale values. - View Dependent Claims (7)
-
8. A method for automated landmark extraction from three-dimensional whole body scanned data, the method comprising:
using a computer to perform the steps of; extracting feature points as landmarks on a human body; and directly extracting an armpit based on three-dimensional changes in shape of the human body without premarking landmarks before scanning; projecting the three-dimensional body scanned data onto a coronal plane; and extracting approximate locations of armpits by locating locally maximum points on silhouette curves of the intersection of torso and arms by using silhouette analysis. - View Dependent Claims (9)
-
10. A method for automated landmark extraction from three-dimensional whole body scanned data, the method comprising:
using a computer to perform the steps of; extracting feature points as landmarks on a human body; and directly extracting a seventh cervical point, an inferior angle of scapula, a patella, a lateral malleolus, an elbow, a suprasternale, and a navel based on three-dimensional changes in shape of the human body without premarking landmarks before scanning; utilizing human body contour plots for extraction; simulating a sense of touch; and locating prominent parts of a human body to extract locations of the seventh cervical point the inferior angle of scapula, the patella, the lateral malleolus, and the elbow. - View Dependent Claims (11)
Specification