Study about the binary differential joint transform correlator used in pattern recognition
-
摘要: 为了克服二元联合变换相关器的取阈和实时性问题,采用微分运算与二元联合变换相关器结合的方法.联合功率谱中,由于干扰项随频率的变化率比需要的信息量随频率的变化率慢得多,因此可以采用微分方式削弱干扰项,增强互相关信号,对微分后的功率谱再进行二值化非线性处理得到优化功率谱,然后对优化功率谱进行傅里叶逆变换,得到目标和图像的相关输出.模拟实验结果表明,所提出的相关器能很好地抑制自相关峰,增强互相关峰,具有更强的鲁棒性.而且该方法在处理过程中,不需选择阈值,简单的微分及二值化操作使之具有更强的实时性.Abstract: New binary joint transform correlator(BJTC) based on differential operation was proposed.It can well resolve the disadvantages about the bottleneck of real-time processing and thresholding selection in BJTC.The unwanted term in joint power spectrum(JPS) varies slowly compared with wanted term.It is reasonable to use differential operation to improve JTC's contrast by depressing the auto-correlate peak and enhancing the cross-correlate peak.Then the differential JPS was binarized to only two values at Fourier plane before inverse Fourier transform.Then higher cross-correlate output between references and object image can be obtained.Simulation results show the proposed JTC can well weakens auto-correlation peak and enhances cross-correlation peak.It also has better robustness.The proposed method can avoid computing or pre-setup threshold.Furthermore,it's quite simple differential operation and binarization require far fewer digital computations than does the BJTC.
-
-
[1] LEI F,ITON M,YATAGAI T.Adaptive binary joint transform correlator for image recognition[J].Appl Opt,2002,41(35):7416 ～7421.
[2] MELA C L,IEMMI C C.A distortion-tolerant photorefractive joint transform correlator[J].J Optics A:Pureand Applied Optics,2004,6(9):894～899.
[3] SHABTAY G,MENDLOVID D,ZALEVKY Z.Joint transform correlator for optical temporal signals[J].Appl Opt,2000,39(45):6556～6560.
[4] LIU D M,SHEN J Y,WANG L J.Application of the wavelet transform to pattern correlator recognition[J].Laser technology,2004,28(6):641～644(in Chinese).
[5] JAVIDI B,LI J,AMIR H F et al.Binary nonlinear joint transform correlator performance with different thresholding methods under unknown illumination conditions[J].Appl Opt,1995,34(5):886～896.
[6] ZHAO J L,XU Q T,YANG D X et al.Optimized threshold of the binary joint transform correlator[J].Acta Photonica Sinica,2002,31 (9):1101～1104(in Chinese).
[7] BUTT J A,WILKINSON T D.Binary phase only reference for invariant pattern recognition with the joint transform correlator[J].Proc SPIE,2006,6234:62340J-1～62340J-11.
[8] JULIC P T,JUVELIS L,MARIO M U et al.Reduction of the effect of aberrations in a joint-transform correlator[J].Appl Opt,2004,43(4):841～849.
[9] VICTOR D R H,KOBER V,JOSUE A B.Pattern recognition with an adaptive joint transform correlator[J].Appl Opt,2006,45(23):5929～5941.
[10] ZHONG Sh,JIANG J X,LIU Sh T et al.Binary joint transform correlator based on differential processing of joint transform power spectrum[J].Appl Opt,1997,36(8):1776～1780.
[11] WANG H X,ZHAO W,LI Y X.Multi-object recognition using power spectrum optimized joint transform correlator[J].Optical Technique,2006,32(2):190～195(in Chinese).
-
期刊类型引用(3)
1. 吴剑威，王继尧，郑健，赵鹏越，高席丰，温众普. 真空气体静压轴承研究进展. 机械工程学报. 2025(05): 13-25 . 
百度学术
2. 金茜茜，陈虹枢，汪雪锋. 融合社会资本与知识存量的合作创新网络演化机制研究. 图书情报工作. 2024(06): 93-103 . 百度学术
3. 余江，陈凤，郭玥. 现代化产业体系中科技创新与产业创新的深度融合：全球新一代光刻系统的启示. 中国科学院院刊. 2024(07): 1141-1152 . 百度学术
其他类型引用(5)
计量
- 文章访问数: 1
- HTML全文浏览量: 0
- PDF下载量: 5
- 被引次数: 8
下载: