STATISTICAL PART-BASED MODELS FOR OBJECT CATEGORY RECOGNITION

被引：0
|
作者：
Xia, Xiao-Zhen [1 ]
Zhang, Shu-Wu [1 ]
机构：
[1] Chinese Acad Sci, Digital Content Technol Res Ctr, Inst Automat, Beijing, Peoples R China
来源：
PROCEEDINGS OF 2009 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-6 | 2009年
关键词：
Object categorization; Part-based recognition; Statistical models; HOG descriptor;
D O I：
10.1109/ICMLC.2009.5212299
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, we present a new method to learn statistical part-based structure models for object category recognition in a supervised manner. The method learns both a model of local part appearance and a model of the spatial relations between those parts. By using Histograms of Oriented Gradient (HOG) features to describe local part appearance within an image, we investigate whether richer appearance model is helpful in improving recognition performance. We learn the model parameters from training examples using maximum likelihood estimation. In detection, these models are used in a probabilistic way to classify and localize the objects in the images. The experimental results on a variety of categories demonstrate that our method provides both successful classification and localization of the object within the image.
引用
收藏
页码：1846 / 1850
页数：5
相关论文
共 50 条
  • [1] Part-based statistical models for object classification and detection
    Bernstein, EJ
    Amit, Y
    [J]. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2005, : 734 - 740
  • [2] Spatial priors for part-based recognition using statistical models
    Crandall, D
    Felzenszwalb, P
    Huttenlocher, D
    [J]. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol 1, Proceedings, 2005, : 10 - 17
  • [3] Scene Recognition and Weakly Supervised Object Localization with Deformable Part-Based Models
    Pandey, Megha
    Lazebnik, Svetlana
    [J]. 2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2011, : 1307 - 1314
  • [4] Weakly supervised learning of part-based spatial models for visual object recognition
    Crandall, David J.
    Huttenlocher, Daniel P.
    [J]. COMPUTER VISION - ECCV 2006 , PT 1, PROCEEDINGS, 2006, 3951 : 16 - 29
  • [5] Object Tracking with Gradient Part-based Models
    Li, Yang
    Wang, Jiabao
    Lu, Jianjiang
    Miao, Zhuang
    Fang, Pengfei
    [J]. MECHATRONICS AND INTELLIGENT MATERIALS II, PTS 1-6, 2012, 490-495 : 905 - 909
  • [6] The development of part-based and configural object recognition in adolescence
    Juettner, M.
    Petters, D.
    Wakui, E.
    Davidoff, J.
    [J]. PERCEPTION, 2009, 38 : 165 - 165
  • [7] Object class recognition by boosting a part-based model
    Bar-Hillel, A
    Hertz, T
    Weinshall, D
    [J]. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, : 702 - 709
  • [8] Trajectories of part-based and configural object recognition in adolescence
    Juettner, M.
    Petters, D.
    Kaur, S.
    Wakui, E.
    Davidoff, J.
    [J]. PERCEPTION, 2011, 40 : 72 - 72
  • [9] OBJECT TRACKING WITH PART-BASED DISCRIMINATIVE CONTEXT MODELS
    Zhu, Guibo
    Wang, Jinqiao
    Lu, Hanqing
    [J]. 2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 4932 - 4936
  • [10] Object Detection with Discriminatively Trained Part-Based Models
    Forsyth, David
    [J]. COMPUTER, 2014, 47 (02) : 6 - 7
12345