2008
DOI: 10.1016/j.optlaseng.2007.07.006
|View full text |Cite
|
Sign up to set email alerts
|

Log-polar transform-based wavelet-modified maximum average correlation height filter for distortion-invariant target recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2010
2010
2023
2023

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 11 publications
(4 citation statements)
references
References 18 publications
0
4
0
Order By: Relevance
“…The dataset was divided into two classes: true class (car1) and false class (car2 and car3) images, as shown in Figure 1i-iii. We implemented the synthesized WEMACH in a hybrid optical-correlator scheme [10,11,[18][19][20][21]. In this geometry, the target image is Fourier-transformed and multiplied with the pre-synthesized filter, which is referred to as a product function.…”
Section: Simulation Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…The dataset was divided into two classes: true class (car1) and false class (car2 and car3) images, as shown in Figure 1i-iii. We implemented the synthesized WEMACH in a hybrid optical-correlator scheme [10,11,[18][19][20][21]. In this geometry, the target image is Fourier-transformed and multiplied with the pre-synthesized filter, which is referred to as a product function.…”
Section: Simulation Resultsmentioning
confidence: 99%
“…In this geometry, the target image is Fourier-transformed and multiplied with the pre-synthesized filter, which is referred to as a product function. The Fourier We implemented the synthesized WEMACH in a hybrid optical-correlator scheme [10,11,[18][19][20][21]. In this geometry, the target image is Fourier-transformed and multiplied with the pre-synthesized filter, which is referred to as a product function.…”
Section: Simulation Resultsmentioning
confidence: 99%
“…The transformation given in (26) amounts to subtraction of a blurred version of the image from a less blurred version of the same. Both blurred versions are acquired as an outcome of convolution process involving the original grey-scale image and Gaussian kernels with different standard deviations.…”
Section: Preprocessing Stage A: Dog-based Enhancementmentioning
confidence: 99%
“…Since then multiple variants including extended MACH (EMACH) [21] and eigen-EMACH (E 2 MACH) [22] have been proposed with respective improvements as well as trade-offs [23]. Most recently some hybrid filtering strategies based on wavelets (WMACH) [24,25] and logarithmic mapping transformations [logarithmically MACH (LMACH)/LEMACH] [26][27][28] have also been proposed to cater for additional problems of in-plane and out-of-plane rotations as well as scale variations.…”
Section: Introductionmentioning
confidence: 99%