Optimal training set design for 3D object recognition

被引：0
|
作者：
Takacs, B [1 ]
Sadovnik, L [1 ]
Wechsler, H [1 ]
机构：
[1] WaveBand Corp, Torrance, CA 90501 USA
来源：
FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2 | 1998年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We describe a general approach for the representation and recognition of 3D objects. The method is based on a novel view selection mechanism that develops "visual filters" responsive to specific object classes to encode the complete viewing sphere with a small number of prototypical examples. The optimal set of visual filters is found via a cross-validation-like data reduction algorithm used to train banks of back propagation (BP) neural networks. Experimental results on real-world imagery demonstrate the feasibility of our approach.
引用
收藏
页码：558 / 560
页数：3
相关论文
共 50 条
  • [1] Learning 3D object recognition from an unlabelled and unordered training set
    Leitner, Raimund
    ADVANCES IN VISUAL COMPUTING, PT I, 2007, 4841 : 644 - 651
  • [2] OVPT: Optimal Viewset Pooling Transformer for 3D Object Recognition
    Wang, Wenju
    Chen, Gang
    Zhou, Haoran
    Wang, Xiaolin
    COMPUTER VISION - ACCV 2022, PT I, 2023, 13841 : 486 - 503
  • [3] A local approach for 3D object recognition through a set of size functions
    Mhamdi, Mohammed Ayoub Alaoui
    Ziou, Djemel
    IMAGE AND VISION COMPUTING, 2014, 32 (12) : 1030 - 1044
  • [4] Probabilistic 3D object recognition
    Shimshoni, I
    Ponce, J
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2000, 36 (01) : 51 - 70
  • [5] 3D object indexing and recognition
    Aouat, Saliha
    Laiche, Nacera
    Souami, Feryel
    Larabi, Slimane
    APPLIED MATHEMATICS AND COMPUTATION, 2008, 196 (01) : 318 - 332
  • [6] Probabilistic 3D Object Recognition
    Ilan Shimshoni
    Jean Ponce
    International Journal of Computer Vision, 2000, 36 : 51 - 70
  • [7] Training-based Object Recognition in Cluttered 3D Point Clouds
    Pang, Guan
    Neumann, Ulrich
    2013 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2013), 2013, : 87 - 94
  • [8] Combining 3D Shape and Color for 3D Object Recognition
    Brandao, Susana
    Costeira, Joao P.
    Veloso, Manuela
    IMAGE ANALYSIS AND RECOGNITION (ICIAR 2016), 2016, 9730 : 481 - 489
  • [9] Trains of keypoints for 3D object recognition
    Arnaud, Elise
    Delponte, Elisabetta
    Odone, Francesca
    Verri, Alessandro
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2006, : 1014 - +
  • [10] A new method for recognition of 3D object
    Sun, Jian
    Zhou, Fengqi
    Zhou, Jun
    ISSCAA 2006: 1ST INTERNATIONAL SYMPOSIUM ON SYSTEMS AND CONTROL IN AEROSPACE AND ASTRONAUTICS, VOLS 1AND 2, 2006, : 475 - +
12345