ROTATION-INVARIANT OBJECT DETECTION USING COMPLEX MATCHED FILTERS AND SECOND ORDER VECTOR FIELDS

被引：0
作者：
Pudzs, Mihails [1 ]
Greitans, Modris [1 ]
机构：
[1] Inst Elect & Comp Sci, Riga, Latvia
来源：
2014 PROCEEDINGS OF THE 22ND EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO) | 2014年
关键词：
image processing; matched filters; vector fields; angular invariance; object detection;
D O I：
暂无
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：
In this paper we introduce two concepts: second order vector fields that describe line-like objects in images and rotation-invariant Complex Matched Filter kernels that can be used to detect object with almost any complexity. We present the theoretical grounds for kernel derivation, object matching using sets of subresponses, object's rotation angle and active area determination. The work of the proposed algorithms is demonstrated on images of an occluded and rotated object.
引用
收藏
页码：1312 / 1316
页数：5
相关论文
共 13 条
  • [1] [Anonymous], 18 INT C SYST SIGN I
  • [2] Arodz T, 2005, COMPUT INFORM, V24, P183
  • [3] Histograms of oriented gradients for human detection
    Dalal, N
    Triggs, B
    [J]. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, : 886 - 893
  • [4] Kingsbury N. G., 2006, P EUR C SIGN PROC SE
  • [5] Liu K, 2012, PROC CVPR IEEE, P917, DOI 10.1109/CVPR.2012.6247766
  • [6] Lowe D. G., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1150, DOI 10.1109/ICCV.1999.790410
  • [7] Pudzs M., 2013, Patent No. [WO 2013/147574 A1, 2013147574]
  • [8] Pudzs M, 2011, EUR SIGNAL PR CONF, P41
  • [9] Rotation invariant neural network-based face detection
    Rowley, HA
    Baluja, S
    Kanade, T
    [J]. 1998 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1998, : 38 - 44
  • [10] Skibbe H, 2012, 2012 9TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), P450, DOI 10.1109/ISBI.2012.6235581
12