Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
OBJECT DETECTING DEVICE AND ITS LEARNING DEVICE
Document Type and Number:
WIPO Patent Application WO/2006/134981
Kind Code:
A1
Abstract:
An object detecting device and its learning device the processing load of which is prevented from increasing and which has a high accuracy. The object detecting device comprises an image window extracting section (210) for extracting image windows from an inputted image which are partial regions of the inputted image and a network identifier (590) for detecting an object from the extracted image windows through a node network where nodes having an identifier for identifying an object stored in a storage section (502) are interconnected.

Inventors:
WARAGAI KATSUNORI
KAWAI FUMI
HENG CHER KENG
Application Number:
PCT/JP2006/311953
Publication Date:
December 21, 2006
Filing Date:
June 14, 2006
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
MATSUSHITA ELECTRIC IND CO LTD (JP)
WARAGAI KATSUNORI
KAWAI FUMI
HENG CHER KENG
International Classes:
G06T7/00; G06N3/00; G06N20/00; G06V10/84
Foreign References:
JP2005044330A2005-02-17
US20020102024A12002-08-01
US20020102024A12002-08-01
JP2005175356A2005-06-30
Other References:
YOAV FREUND; ROBERT E. SCHAPIRE: "Computational Learning Theory", 1995, EUROCOLT '95, SPRINGER-VERLAG, article "A decision-theoretic generalization of on-line learning and an application to boosting", pages: 23 - 37
PAUL VIOLA; MICHAEL JONES: "Rapid Object Detection Using a Boosted Cascade of Simple Features", IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR, vol. 1, 2001, pages 511 - 518
H. ROWLEY; S. BALUJA; T. KANADE: "Neural Network-Based Face Detection", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (PAMI, vol. 20, January 1998 (1998-01-01), pages 23 - 28
BERNHARD FROBA; ANDREAS ERNST: "Face Detection with the Modified Census Transform", PROCEEDINGS FOR SIXTH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (AFGR, May 2004 (2004-05-01), pages 91 - 96
JIN R. ET AL.: "A New Boosting Algorithm Using Input Dependent Regularizer", 20TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING (ICML '03, 21 August 2003 (2003-08-21)
See also references of EP 1892669A4
Attorney, Agent or Firm:
Takamatsu, Takeshi (7-13 Nishi-Shimbashi 1-chome, Minato-k, Tokyo 03, JP)
Download PDF: