Method for automatic screening of abnormalities
First Claim
Patent Images
1. A method of detecting abnormalities in n-dimensional data comprising:
- a learning phase including;
obtaining a first series of n-dimensional data;
determining a first statistical quantity and a second statistical quantity based on said first series of n-dimensional data;
obtaining a second series of n-dimensional data;
estimating a respective bimodal distribution for a plurality of n-dimensional points in each of said second series of n-dimensional data;
generating a reference template in response to said first statistical quantity, said second statistical quantity and said respective bimodal distributions;
an inspection phase including;
obtaining n-dimensional test data to be inspected for abnormalities; and
comparing said test data to said reference template to detect abnormalities.
1 Assignment
0 Petitions
Accused Products
Abstract
A method of detecting abnormalities including a learning phase and an inspection phase. In the learning phase, a first statistical quantity and a second statistical quantity are determined based on a first set of n-dimensional data. A second set of n-dimensional data is obtained and a bimodal distribution for a plurality of n-dimensional points in each of the second set of n-dimensional data is determined. A reference template is generated in response to the first statistical quantity, second statistical quantity and bimodal distribution. In the inspection phase, n-dimensional test data to be inspected for abnormalities is obtained and compared to the reference template to detect abnormalities.
74 Citations
20 Claims
-
1. A method of detecting abnormalities in n-dimensional data comprising:
-
a learning phase including;
obtaining a first series of n-dimensional data;
determining a first statistical quantity and a second statistical quantity based on said first series of n-dimensional data;
obtaining a second series of n-dimensional data;
estimating a respective bimodal distribution for a plurality of n-dimensional points in each of said second series of n-dimensional data;
generating a reference template in response to said first statistical quantity, said second statistical quantity and said respective bimodal distributions;
an inspection phase including;
obtaining n-dimensional test data to be inspected for abnormalities; and
comparing said test data to said reference template to detect abnormalities. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
determining a normalized deviation for a plurality of n-dimensional points in said test data; and
comparing said normalized deviation to a first threshold to detect abnormal points.
-
-
10. The method of claim 9 wherein said comparing further comprises:
-
counting a number of abnormal points;
comparing the number of abnormal points to a second threshold; and
classifying said test data as containing an abnormality if the number of abnormal points exceeds said second threshold.
-
-
11. A storage medium encoded with machine-readable computer program code for modeling an object comprising instructions for causing a computer to implement a method comprising:
-
a learning phase including;
obtaining a first series of n-dimensional data;
determining a first statistical quantity and a second statistical quantity based on said first series of n-dimensional data;
obtaining a second series of n-dimensional data;
estimating a respective bimodal distribution for a plurality of n-dimensional points in each of said second series of n-dimensional data;
generating a reference template in response to said first statistical quantity, said second statistical quantity and said respective bimodal distributions;
an inspection phase including;
obtaining n-dimensional test data to be inspected for abnormalities; and
comparing said test data to said reference template to detect abnormalities. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19, 20)
determining a normalized deviation for a plurality of n-dimensional points in said test data; and
comparing said normalized deviation to a first threshold to detect abnormal points.
-
-
20. The storage medium of claim 19 wherein said comparing further comprises:
-
counting a number of abnormal points;
comparing the number of abnormal points to a second threshold; and
classifying said test data as containing an abnormality if the number of abnormal points exceeds said second threshold.
-
Specification
-
- Resources
Litigation Campaign Assessment
Thank you for your request. You will receive a custom alert email when the Litigation Campaign Assessment is available.
×
-
Current AssigneeGeneral Electric Company
-
Original AssigneeGeneral Electric Company
-
InventorsNguyen, Van-Duc, Mundy, Joseph Leagrand
-
Primary Examiner(s)Wachsman, Hal
-
Assistant Examiner(s)DUONG, KHOI H
-
Application NumberUS09/263,348Time in Patent Office1,033 DaysField of Search702/33-36, 702/40, 702/56, 702/81-84, 702/179-181, 702/182-183, 702/155, 702/159, 702/189, 702/65, 702/150-151, 702/FOR.103, 702/104, 702/110, 702/123, 702/124, 702/131, 702/134, 702/135, 702/149, 702/165, 382/133, 382/110, 382/129, 382/276, 382/134, 382/165, 706/20, 706/25, 706/924, 700/17, 700/124, 700/223, 345/419, 367/68, 340/658US Class Current702/179CPC Class CodesG06F 18/28 Determining representative ...G06T 2207/10116 X-ray imageG06T 2207/30164 Workpiece; Machine componentG06T 7/001 using an image reference ap...
