Rotation invariant HOG for object localization in web images

被引：7
|
作者：
Vashaee, Ali [1 ]
Jafari, Reza [1 ]
Ziou, Djemel [1 ]
Rashidi, Mohammad Mehdi [2 ,3 ]
机构：
[1] Univ Sherbrooke, Dept Informat, Sherbrooke, PQ J1K 2R1, Canada
[2] Tongji Univ, Shanghai Key Lab Vehicle Aerodynam & Vehicle Ther, 4800 Cao An Rd, Shanghai 201804, Peoples R China
[3] ENN Tongji Clean Energy Inst Adv Studies, Shanghai, Peoples R China
来源：
SIGNAL PROCESSING | 2016年 / 125卷
关键词：
Rotation invariant HOG; Object localization; Top-Down searching;
D O I：
10.1016/j.sigpro.2016.01.016
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
To localize objects in Web images using an invariant descriptor is crucial. The HOG (histogram of oriented gradients) descriptor is used to increase the accuracy of localization. It is a shape descriptor that considers frequencies of gradient orientation in localized portions of an image. This well known descriptor does not cover rotation variations of an object in images. This paper introduces a rotation invariant feature descriptor based on HOG. The proposed descriptor is used in a top-down searching technique that covers the scale variation of the objects in images. The efficiency of this method is validated by comparing the performance with existing research in a similar domain on the Caltech-256 Web dataset. The proposed method not only provides robustness against geometrical transformations of objects but also is computationally more efficient. (C) 2016 Elsevier B.V. All rights reserved.
引用
收藏
页码：304 / 314
页数：11
相关论文
共 50 条
  • [1] CIRCULAR FOURIER-HOG FEATURES FOR ROTATION INVARIANT OBJECT DETECTION IN BIOMEDICAL IMAGES
    Skibbe, Henrik
    Reisert, Marco
    2012 9TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2012, : 450 - 453
  • [2] Object detection in VHR optical remote sensing images via learning rotation-invariant HOG feature
    Cheng, Gong
    Zhou, Peicheng
    Yao, Xiwen
    Yao, Chao
    Zhang, Yanbang
    Han, Junwei
    2016 4RTH INTERNATIONAL WORKSHOP ON EARTH OBSERVATION AND REMOTE SENSING APPLICATIONS (EORSA), 2016,
  • [3] Ship Detection based on Rotation-invariant HOG Descriptors for Airborne Infrared Images
    Xu, Guojing
    Wang, Jinyan
    Qi, Shengxiang
    MIPPR 2017: PATTERN RECOGNITION AND COMPUTER VISION, 2017, 10609
  • [4] Rotation-invariant object detection using Sector-ring HOG and boosted random ferns
    Baozhen Liu
    Hang Wu
    Weihua Su
    Wenchang Zhang
    Jinggong Sun
    The Visual Computer, 2018, 34 : 707 - 719
  • [5] Rotation-invariant object detection using Sector-ring HOG and boosted random ferns
    Liu, Baozhen
    Wu, Hang
    Su, Weihua
    Zhang, Wenchang
    Sun, Jinggong
    VISUAL COMPUTER, 2018, 34 (05): : 707 - 719
  • [6] DIGITAL SYSTEM INVARIANT TO POSITION AND ROTATION TO OBJECT RECOGNITION IN IMAGES BY INTENSITY PROFILES
    Solorza, S.
    Alvarez-Borrego, J.
    REVISTA CUBANA DE FISICA, 2014, 31 (01): : 18 - 19
  • [7] An Imaging Algorithm for Rotation Invariant Automated Macula Localization in Digital Fundus Images
    Bhattacharya, Sayantan
    Sehgal, Jai
    Sengar, Namita
    Dutta, Malay Kishore
    Travieso-Gonzalez, Carlos M.
    APPLICATIONS OF INTELLIGENT SYSTEMS, 2018, 310 : 345 - 352
  • [8] MIRROR REFLECTION INVARIANT HOG DESCRIPTORS FOR OBJECT DETECTION
    Kanezaki, Asako
    Mukuta, Yusuke
    Harada, Tatsuya
    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 1594 - 1598
  • [9] Object Classification of Remote Sensing Images Based on Rotation-Invariant Discrete Hashing
    Xu, Hui
    Liu, Yazhou
    Sun, Quansen
    ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2017, PT II, 2018, 10736 : 264 - 274
  • [10] A ROTATION INVARIANT HOG DESCRIPTOR FOR TIRE PATTERN IMAGE CLASSIFICATION
    Liu, Ying
    Ge, Yuxiang
    Wang, Fuping
    Liu, Qiqi
    Lei, Yanbo
    Zhang, Dengsheng
    Lu, Guojun
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 2412 - 2416
12345