公开(公告)号：US06018728A

公开(公告)日：2000-01-25

申请号：US797497

申请日：1997-02-07

申请人： Clay Douglas Spence ,  John Carr Pearson ,  Paul Sajda

发明人： Clay Douglas Spence ,  John Carr Pearson ,  Paul Sajda

IPC分类号： G06F15/18 ,  G06K9/46 ,  G06K9/66 ,  G06N3/04 ,  G06N3/08 ,  G06Q50/00 ,  G06T1/00 ,  G06T7/00

CPC分类号： G06K9/3233 ,  G06K9/4609 ,  G06K9/4628 ,  G06K9/66 ,  G06N3/0472 ,  G06N3/082 ,  G06T7/0012 ,  G06K2209/05

摘要： A signal processing apparatus and concomitant method for learning and integrating features from multiple resolutions for detecting and/or classifying objects are presented. Neural networks in a pattern tree structure with tree-structured descriptions of objects in terms of simple sub-patterns, are grown and trained to detect and integrate the sub-patterns. A plurality of objective functions and their approximations are presented to train the neural networks to detect sub-patterns of features of some class of objects. Objective functions for training neural networks to detect objects whose positions in the training data are uncertain and for addressing supervised learning where there are potential errors in the training data are also presented.

摘要翻译： 提出了用于学习和整合用于检测和/或分类对象的多个分辨率的特征的信号处理装置和并发方法。 生长和训练具有根据简单子模式的对象的树结构描述的模式树结构中的神经网络以检测和集成子模式。 提出了多个目标函数及其近似来训练神经网络以检测某些类别对象的特征的子模式。 还提出了用于训练神经网络以检测训练数据中的位置不确定以及训练数据中存在潜在错误的监督学习的目标函数。