Cross-correlation peak optimization on joint transform correlators

Chen, Chulung; Fang, Jian‐Shuen

doi:10.1016/s0030-4018(00)00683-0

Cited by 33 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This disadvantage is primarily due to the existence of the zero-order spectra. The power spectrum subtraction technique can be used to remove the zero-order diffraction [18,19] and the output of JTC can be shown as [6,17] g(a, f)= h(x, y)® f* (x, y)* 5(y -2ao )+ h* (x, y)® f(x,y)* S(y + 2ao),…”

Section: H* = A-'f*[ft A-if*iicmentioning

confidence: 99%

“…In contrast to other methods, seal imprint recognition can be achieved with the optical correlator, for which two widely used schemes have been the VanderLugt optical correlator [3,4] and the joint transform correlator (JTC) [5]. Since its introduction by Vanderlugt, optical correlation has been one of the most effective methods for optical pattern recognition [6,7]. Optical recognition methods based on the Fourier transform, such as the Vanderlugt correlator, or the joint transform correlator offer advantages such as parallel processing and large-volume databases [8].…”

Section: Introductionmentioning

confidence: 99%

“…Although an optical system can be designed to perform specific tasks, it cannot be used where more adaptability is required. A second drawback is that optical systems by themselves can not be used to make decisions as some electronic counter parts can [16,17]. To overcome the problem, optical system and electronic system can cooperate together.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

<title>Chinese seal recognition using a hybrid electro-optical filter</title>

Fang

Chen

Wang

2000

Optical Storage and Optical Information Processing

Self Cite

View full text Add to dashboard Cite

We present a new technique for Chinese seal recognition using constrained energy minimization joint transform correlator (CEMJTC). Either optical or digital correlation is one of the most powerful operations for detecting the presence/absence of the seal image. The CEMJTC is proposed to improve the discrimination capability for shift-invariance and rotational-invariant seal recognition. By minimizing the average correlation energy with respect to all training seal images, while constraining the correlation peak value to a constant, a filter function is constructed. The main emphasis is to design a filter for good discriminate ability. Numerical results are presented to demonstrate the improvements. Furthermore, experimental results show the sharp correlation output profile when the seal image is correct, otherwise the correlation peak will be obviously reduced. The new technique for seal recognition shows a significant increase in high speed and detection ability.

show abstract

Section: H* = A-'f*[ft A-if*iicmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

<title>Chinese seal recognition using a hybrid electro-optical filter</title>

Fang

Chen

Wang

2000

Optical Storage and Optical Information Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The proposed system has some advantages, such as ease of optical implementation and robustness in terms of system alignment. Recently, Wu et al [11] proposed a novel method based on the nonzero-order JTC (NOJTC) system [12][13][14] to improve the performance of distortion-invariant color pattern recognition. In this paper, the FR system is based on the NOJTC configuration.…”

Section: Introductionmentioning

confidence: 99%

Color face‐image recognition with liquid‐crystal spatial light modulators

Chen¹,

Chen²,

Lee³

et al. 2004

Micro & Optical Tech Letters

Self Cite

View full text Add to dashboard Cite

In this paper, for color face‐image recognition, we adopt a system based on the nonzero‐order joint‐transform correlator and use the method of Lagrange multipliers to design the reference functions. Some different facial expressions are utilized as test images to study the discrimination capability. Additionally, random noise is added to the test images in order to investigate the effectiveness of the proposed technique. © 2004 Wiley Periodicals, Inc. Microwave Opt Technol Lett 42: 234–237, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.20262

show abstract

“…But owing to the heavy dc content of the input target, it also produces relatively broad correlation profiles, which hinder its application to multitarget detection. To improve this, Chen et al [6,7] designed a reference function that can produce sharp correlation peaks for distortion invariant pattern recognition.…”

Section: Introductionmentioning

confidence: 99%