-
公开(公告)号：US10114135B2
公开(公告)日：2018-10-30
申请号：US14985860
申请日：2015-12-31
Inventor： Xiaojie Huang , Ali Can , Erhan Bas , Weina Ge , Shubao Liu , Mark W. Dobin , Mary Johns
Abstract: A method includes accessing a seismic image comprising a plurality of features of interest. The method also includes defining a plurality of configuration files for a plurality of graphical models. The method further includes applying the plurality of graphical models to the seismic image. The method also includes generating a plurality of scores for each feature of interest, wherein each graphical model generates a score for each feature of interest. The method further includes combining the plurality of scores for each feature of interest into a plurality of combined scores, wherein each feature of interest has a combined score.
-
公开(公告)号：US20180122082A1
公开(公告)日：2018-05-03
申请号：US15367275
申请日：2016-12-02
Applicant: GENERAL ELECTRIC COMPANY
Inventor： Suvadip Mukherjee , Roshni Bhagalia , Xiaojie Huang
CPC classification number: G06T7/143 , G06N3/04 , G06N3/0454 , G06N3/0472 , G06N3/08 , G06N7/005 , G06T5/002 , G06T7/11 , G06T7/12 , G06T7/136 , G06T7/162 , G06T7/194 , G06T2207/10072 , G06T2207/10081 , G06T2207/10136 , G06T2207/20076 , G06T2207/20081 , G06T2207/20084 , G06T2207/20161 , G06T2207/30064 , G06T2207/30096 , G06T2207/30101
Abstract: Embodiments described herein provide a hybrid technique which incorporates learned pulmonary nodule features in a model based energy minimization segmentation using graph cuts. Features are extracted from training samples using a convolutional neural network, and the segmentation cost function is augmented via the deep learned energy. The system and method improves segmentation performance and more robust initialization.
-
公开(公告)号：US20170193647A1
公开(公告)日：2017-07-06
申请号：US14985901
申请日：2015-12-31
Inventor： Xiaojie Huang , Ali Can , Shubao Liu , Mark W. Dobin , Mary Johns , Leslie A. Wahrmund
CPC classification number: G06T7/0004 , G01V1/28 , G01V1/301 , G01V2210/64 , G06T7/187 , G06T2207/20076 , G06T2207/30181
Abstract: A method for identifying a plurality of features of interest in a seismic image includes ranking each feature of interest. The method also includes modeling a relationship between the rank of each feature of interest and a user rating of the feature of interest. The method further includes updating the ranking of the plurality of features of interest, including (1) receiving a user rating for one feature of interest that has not been previously rated by a user; (2) updating the model of the relationship between the rank of each feature of interest and the user rating of the feature of interest based on the user rating; (3) applying the model to the ranking of the plurality of features of interest; and (4) repeating steps (1)-(3) until a termination criterion is met.
-
Patent Agency Ranking
公开(公告)号：US20170192114A1
公开(公告)日：2017-07-06
申请号：US14985860
申请日：2015-12-31
Inventor： Xiaojie Huang , Ali Can , Erhan Bas , Weina Ge , Shubao Liu , Mark W. Dobin , Mary Johns
Abstract: A method includes accessing a seismic image comprising a plurality of features of interest. The method also includes defining a plurality of configuration files for a plurality of graphical models. The method further includes applying the plurality of graphical models to the seismic image. The method also includes generating a plurality of scores for each feature of interest, wherein each graphical model generates a score for each feature of interest. The method further includes combining the plurality of scores for each feature of interest into a plurality of combined scores, wherein each feature of interest has a combined score.
-
公开(公告)号：US10677948B2
公开(公告)日：2020-06-09
申请号：US15265495
申请日：2016-09-14
Inventor： Ali Can , Erhan Bas , Weina Ge , Shubao Liu , Xiaojie Huang , Mary Katherine Johns , Mark Wayne Dobin
Abstract: A method of identifying bounded hydrocarbon formations of interest in a seismic data set includes obtaining a seismic data set, pre-processing the seismic data set, inputting the plurality of graphical model inputs and one or more rules to a graphical model, wherein the rules define a relationship between a plurality of attributes of a bounded hydrocarbon formation, running a graphical model on the graphical model inputs, post-processing the graphical model outputs, and displaying the ranked clusters in order of rank.
-
公开(公告)号：US10453200B2
公开(公告)日：2019-10-22
申请号：US15367275
申请日：2016-12-02
Applicant: GENERAL ELECTRIC COMPANY
Inventor： Suvadip Mukherjee , Roshni Bhagalia , Xiaojie Huang
IPC: G06T7/143 , G06N3/08 , G06N3/04 , G06N7/00 , G06T7/194 , G06T5/00 , G06T7/11 , G06T7/12 , G06T7/162 , G06T7/136
Abstract: Embodiments described herein provide a hybrid technique which incorporates learned pulmonary nodule features in a model based energy minimization segmentation using graph cuts. Features are extracted from training samples using a convolutional neural network, and the segmentation cost function is augmented via the deep learned energy. The system and method improves segmentation performance and more robust initialization.
-
公开(公告)号：US10147173B2
公开(公告)日：2018-12-04
申请号：US14985901
申请日：2015-12-31
Inventor： Xiaojie Huang , Ali Can , Shubao Liu , Mark W. Dobin , Mary Johns , Leslie A. Wahrmund
Abstract: A method for identifying a plurality of features of interest in a seismic image includes ranking each feature of interest. The method also includes modeling a relationship between the rank of each feature of interest and a user rating of the feature of interest. The method further includes updating the ranking of the plurality of features of interest, including (1) receiving a user rating for one feature of interest that has not been previously rated by a user; (2) updating the model of the relationship between the rank of each feature of interest and the user rating of the feature of interest based on the user rating; (3) applying the model to the ranking of the plurality of features of interest; and (4) repeating steps (1)-(3) until a termination criterion is met.
-
公开(公告)号：US20170254911A1
公开(公告)日：2017-09-07
申请号：US15265495
申请日：2016-09-14
Inventor： Ali Can , Erhan Bas , Weina Ge , Shubao Liu , Xiaojie Huang , Mary Katherine Johns , Mark Wayne Dobin
Abstract: A method of identifying bounded hydrocarbon formations of interest in a seismic data set includes obtaining a seismic data set, pre-processing the seismic data set, inputting the plurality of graphical model inputs and one or more rules to a graphical model, wherein the rules define a relationship between a plurality of attributes of a bounded hydrocarbon formation, running a graphical model on the graphical model inputs, post-processing the graphical model outputs, and displaying the ranked clusters in order of rank.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.021 seconds)
