Title:
AN APPARATUS AND A METHOD FOR SEMANTIC IMAGE LABELING
Document Type and Number:
WIPO Patent Application WO/2017/004803
Kind Code:
A1
Abstract:
Disclosed is a method for generating a semantic image labeling model, comprising: forming a first CNN and a second CNN, respectively; randomly initializing the first CNN; inputting a raw image and a plurality of predetermined label ground truth annotations to the first CNN to iteratively update weights of the first CNN so that a category label probability for the raw image, which is output from the first CNN, approaches the predetermined label ground truth annotations; randomly initializing the second CNN; inputting the category label probability to the second CNN to correct the input category label probability so as to determine classification errors of the category label probabilities; updating the second CNN by back-propagating the classification errors; concatenating the updated first CNN and the updated second CNN; classifying each pixel in the raw image into one of a plurality of general object categories; and back-propagating classification errors through the concatenated CNN to update weights of the concatenated CNN until the classification errors less than a predetermined threshold.
Inventors:
TANG XIAOOU (CN)
LIU ZIWEI (CN)
LI XIAOXIAO (CN)
LUO PING (CN)
LOY CHEN CHANGE (CN)
LIU ZIWEI (CN)
LI XIAOXIAO (CN)
LUO PING (CN)
LOY CHEN CHANGE (CN)
Application Number:
PCT/CN2015/083537
Publication Date:
January 12, 2017
Filing Date:
July 08, 2015
Export Citation:
Assignee:
TANG XIAOOU (CN)
International Classes:
G06V30/194
Foreign References:
US20150139485A1 | 2015-05-21 | |||
CN104616032A | 2015-05-13 | |||
CN104732243A | 2015-06-24 |
Other References:
KHALIL-HANI, MOHAMED ET AL.: "A Convolutional Neural Network Approach for Face Verification", HIGH PERFORMANCE COMPUTING & SIMULATION (HPCS), 2014 INTERNATIONAL CONFERENCE ON, 25 August 2014 (2014-08-25), XP032646463
VERMA, ANKIT ET AL.: "Using Convolutional Neural Networks to Discover cognitively Validated Features for Gender Classification", SOFT COMPUTING AND MACHINE INTELLIGENCE (ISCMI), 2014 INTERNATIONAL CONFERENCE ON, 27 September 2014 (2014-09-27), XP032759959
MENOTTI, D. ET AL.: "Vehicle License Plate Recognition With Random Convolutional Networks", GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 2014 27TH SIBGRAPI CONFERENCE ON, 30 August 2014 (2014-08-30), XP032653567
VERMA, ANKIT ET AL.: "Using Convolutional Neural Networks to Discover cognitively Validated Features for Gender Classification", SOFT COMPUTING AND MACHINE INTELLIGENCE (ISCMI), 2014 INTERNATIONAL CONFERENCE ON, 27 September 2014 (2014-09-27), XP032759959
MENOTTI, D. ET AL.: "Vehicle License Plate Recognition With Random Convolutional Networks", GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 2014 27TH SIBGRAPI CONFERENCE ON, 30 August 2014 (2014-08-30), XP032653567
Attorney, Agent or Firm:
INSIGHT INTELLECTUAL PROPERTY LIMITED (CN)
Download PDF:
Previous Patent: TREE PLANTING VEHICLE
Next Patent: MECHANICAL SHOCK-TYPE ULTRAFINE PULVERIZER AND PULVERIZING PAIR
Next Patent: MECHANICAL SHOCK-TYPE ULTRAFINE PULVERIZER AND PULVERIZING PAIR