Invention Grant
US08588519B2 Method and system for training a landmark detector using multiple instance learning
有权
使用多实例学习训练地标探测器的方法和系统
- Patent Title: Method and system for training a landmark detector using multiple instance learning
- Patent Title (中): 使用多实例学习训练地标探测器的方法和系统
-
Application No.: US13228509Application Date: 2011-09-09
-
Publication No.: US08588519B2Publication Date: 2013-11-19
- Inventor: David Liu , Shaohua Kevin Zhou , Paul Swoboda , Dorin Comaniciu , Christian Tietjen
- Applicant: David Liu , Shaohua Kevin Zhou , Paul Swoboda , Dorin Comaniciu , Christian Tietjen
- Applicant Address: DE Munich
- Assignee: Siemens Aktiengesellschaft
- Current Assignee: Siemens Aktiengesellschaft
- Current Assignee Address: DE Munich
- Main IPC: G06K9/52
- IPC: G06K9/52

Abstract:
An apparatus and method for training a landmark detector receives training data which includes a plurality of positive training bags, each including a plurality of positively annotated instances, and a plurality of negative training bags, each including at least one negatively annotated instance. Classification function is initialized by training a first weak classifier based on the positive training bags and the negative training bags. All training instances are evaluated using the classification function. For each of a plurality of remaining classifiers, a cost value gradient is calculated based on spatial context information of each instance in each positive bag evaluated by the classification function. A gradient value associated with each of the remaining weak classifiers is calculated based on the cost value gradients, and a weak classifier is selected which has a lowest associated gradient value and given a weighting parameter and added to the classification function.
Public/Granted literature
- US20120070074A1 Method and System for Training a Landmark Detector using Multiple Instance Learning Public/Granted day:2012-03-22
Information query