Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
A METHOD AND A SYSTEM FOR CLASSIFYING OBJECTS IN IMAGES
Document Type and Number:
WIPO Patent Application WO/2017/079972
Kind Code:
A1
Abstract:
Disclosed is a method for classifying objects in images, comprising: obtaining at least one candidate bounding box for each of the images, wherein each candidate bounding box contains one object to be classified; extracting appearance features from the each candidate bounding box; calculating n-classifying scores for each candidate box based on the extracted appearance features; and classifying objects in each candidate bounding box into one of n classes, where n is integer greater than 1.

Inventors:
WANG XIAOGANG (CN)
ZENG XINGYU (CN)
OUYANG WANLI (CN)
Application Number:
PCT/CN2015/094572
Publication Date:
May 18, 2017
Filing Date:
November 13, 2015
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
WANG XIAOGANG (CN)
International Classes:
G06V10/25
Foreign References:
US20140126773A12014-05-08
CN103093214A2013-05-08
CN101701916A2010-05-05
US20140241623A12014-08-28
CN103824054A2014-05-28
CN103824049A2014-05-28
Other References:
ERJIN ZHOU ET AL.: "Extensive Facial Landmark Localization with Coarse-to-fine Convolutional Network Cascade", 2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS, 31 December 2013 (2013-12-31), pages 386 - 391, XP032575659
DE CHENG ET AL.: "Cascade Object Detection with Complementary Features and Algorithms", PROCEEDINGS OF THE 2015 IEEE 9TH INTERNATIONAL CONFERENCE ON SEMANTIC COMPUTING ( IEEE ICSC 2015, 9 February 2015 (2015-02-09), pages 32 - 39, XP055380695
Attorney, Agent or Firm:
INSIGHT INTELLECTUAL PROPERTY LIMITED (CN)
Download PDF: