Title:
【発明の名称】不確定の訓練データを用いてオブジェクトを検出及び分類するようにニューラルネットワークを訓練する方法及び装置
Document Type and Number:
Japanese Patent JP2000506642
Kind Code:
A
Abstract:
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.
Inventors:
Spence, Clay, Douglas
Pearson, John, Kerr
Sajida, Paul
Pearson, John, Kerr
Sajida, Paul
Application Number:
JP52875397A
Publication Date:
May 30, 2000
Filing Date:
February 07, 1997
Export Citation:
Assignee:
Sarnoff Corporation
International Classes:
G06F15/18; G06N3/04; G06N3/08; G06Q50/00; G06T1/00; G06T7/00; G06V10/25; G06V30/194; (IPC1-7): G06F15/18; G06F19/00; G06T1/00; G06T7/00
Attorney, Agent or Firm:
Yoshiki Hasegawa (3 outside)