Illumination Robust Template Matching based on Nearest-Neighbor

被引:0
|
作者
Zhang, Yi [1 ]
Zhang, Chao [2 ]
Akashi, Takuya [3 ]
机构
[1] Iwate Univ, Grad Sch Engn, Morioka, Iwate, Japan
[2] Univ Fukui, Fac Engn, Fukui, Japan
[3] Iwate Univ, Fac Sci & Engn, Morioka, Iwate, Japan
关键词
template matching; object detection; illumination change; similarity measure;
D O I
10.1117/12.2590778
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a novel method for the illumination robust template matching in unconstrained environments, named illumination robust template matching (IRTM). IRTM is based on the patch diversity of the Nearest-Neighbor. A core component is to calculate the similarity between patch pairs. Without illumination change, the Euclidean distance of appearance and geometric features jointly measure the similarity well. However, the illumination change will significantly affect the confidence of measure. In this paper, based on the relative pixel values that do not change with illumination, we define an illumination-robust distance function. With experiments, IRTM is shown to be a well-performing similarity measure against illumination changes, non-rigid geometric deformations, as well as background clutter, and occlusions.
引用
收藏
页数:6
相关论文
共 50 条
  • [31] Derivation of nearest-neighbor properties from oligomers: Consequences of nearest-neighbor absences and treatment of ends.
    Gray, DM
    BIOPHYSICAL JOURNAL, 1997, 72 (02) : WP412 - WP412
  • [32] INFLUENCES OF ILLUMINATION INTENSITY ON THE NEAREST-NEIGHBOR DISTANCE IN COHO SALMON ONCORHYNCHUS-KISUTCH
    AZUMA, T
    IWATA, M
    JOURNAL OF FISH BIOLOGY, 1994, 45 (06) : 1113 - 1118
  • [33] Prototype optimization for nearest-neighbor classification
    Huang, YS
    Chiang, CC
    Shieh, JW
    Grimson, E
    PATTERN RECOGNITION, 2002, 35 (06) : 1237 - 1245
  • [34] Limitations of nearest-neighbor quantum networks
    Hahn, F.
    Dahlberg, A.
    Eisert, J.
    Pappa, A.
    PHYSICAL REVIEW A, 2022, 106 (01)
  • [35] EXPERIMENT WITH EDITED NEAREST-NEIGHBOR RULE
    TOMEK, I
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1976, 6 (06): : 448 - 452
  • [36] NEAREST-NEIGHBOR ELECTRON SCATTERING IN SILICON
    TAUB, H
    STERN, RM
    APPLIED PHYSICS LETTERS, 1966, 9 (07) : 261 - &
  • [37] NOTE ON RABINS NEAREST-NEIGHBOR ALGORITHM
    FORTUNE, S
    HOPCROFT, J
    INFORMATION PROCESSING LETTERS, 1979, 8 (01) : 20 - 23
  • [38] A simple nearest-neighbor flocking rule
    Di Franco, A
    Narendra, KS
    2005 IEEE Swarm Intelligence Symposium, 2005, : 409 - 411
  • [39] Effective Nearest-Neighbor Music Recommendations
    Ludewig, Malte
    Kamehkhosh, Iman
    Landia, Nick
    Jannach, Dietmar
    RECSYS CHALLENGE'18: PROCEEDINGS OF THE ACM RECOMMENDER SYSTEMS CHALLENGE 2018, 2018,
  • [40] Evolutionary learning of nearest-neighbor MLP
    Univ of Aizu, Aizu-Wakamatsu City, Japan
    IEEE Trans Neural Networks, 3 (762-767):