Constraints in distortion-invariant target recognition system simulation

被引:0
作者
Iftekharuddin, KM [1 ]
Razzaque, MA [1 ]
机构
[1] N Dakota State Univ, Dept Comp Sci, Fargo, ND 58105 USA
来源
PHOTONIC DEVICES AND ALGORITHMS FOR COMPUTING II | 2000年 / 4114卷
关键词
automatic target recognition (ATR); linear Vector Quantization (LVQ); neural network (NN); clustering; MSTAR images; feature extraction;
D O I
10.1117/12.408559
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Automatic target recognition (ATR) is a mature but active research area. In an earlier paper, we proposed a novel ATR approach for recognition of targets varying in fine details, rotation, and translation using a Learning Vector Quantization (LVQ) Neural Network (NN)(4). The proposed approach performed segmentation of multiple objects and the identification of the objects using LVQNN. In this current paper, we extend the previous approach for recognition of targets varying in rotation, translation, scale, and combination of all three distortions. We obtain the analytical results of the system level design to show that the approach performs well with some constraints. The first constraint determines the size of the input images and input filters. The second constraint shows the limits on amount of rotation, translation, and scale of input objects for system implementation. The second constraint also derives the combined constraints on translation and scale of input objects. We present the simulation verification of the constraints using DARPA's Moving and Stationary Target Recognition (MSTAR) images with different depression and pose angles. The simulation results using MSTAR images verify the analytical constraints of the system level design.
引用
收藏
页码:20 / 31
页数:12
相关论文
共 13 条
[1]   GEOMETRICAL TRANSFORMATIONS IN OPTICS [J].
BRYNGDAHL, O .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA, 1974, 64 (08) :1092-1099
[2]   POSITION, ROTATION, AND SCALE INVARIANT OPTICAL CORRELATION [J].
CASASENT, D ;
PSALTIS, D .
APPLIED OPTICS, 1976, 15 (07) :1795-1799
[3]   COMPUTER-GENERATED HOLOGRAMS FOR GEOMETRIC TRANSFORMATIONS [J].
CEDERQUIST, J ;
TAI, AM .
APPLIED OPTICS, 1984, 23 (18) :3099-3104
[4]   Feature evaluation and selection based on an entropy measure with data clustering [J].
Chi, ZR ;
Yan, H .
OPTICAL ENGINEERING, 1995, 34 (12) :3514-3519
[5]  
DENNEMEYR R, 1968, INTRO PARTIAL DIFFER
[6]   Multiobject detection of targets with fine details, scale and translation variations [J].
Diab, SL ;
Karim, MA ;
Iftekharuddin, KM .
OPTICAL ENGINEERING, 1998, 37 (03) :876-883
[7]   Optimization of amplitude-modulated inverse filter [J].
Iftekharuddin, KM ;
Karim, MA ;
Awwal, AAS .
MATHEMATICAL AND COMPUTER MODELLING, 1996, 24 (09) :103-112
[8]   Wavelet preprocessed amplitude-modulated phase-only filter for recognition applications [J].
Iftekharuddin, KM ;
Tuthill, TA ;
Karim, MA ;
Jemili, K .
OPTICAL ENGINEERING, 1996, 35 (07) :2088-2093
[9]   Rotation-invariant target recognition using an amplitude-coupled minimum-average correlation-energy filter [J].
Iftekharuddin, KM ;
Ahmed, F ;
Karim, MA .
OPTICAL ENGINEERING, 1996, 35 (04) :1009-1014
[10]  
IFTEKHARUDDIN KM, 1995, OPT ENG, V35, P3143