Fast and accurate method for high order Zernike moments computation

Singh, Chandan; Upneja, Rahul

doi:10.1016/j.amc.2012.01.040

Cited by 37 publications

(13 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The difference in CPU elapse time is more apparent for large images. Although in our experiments we adopt the fast computation of ZMs [22][23][24][25], ART has speed advantage over ZMs due to its low computation complexity, thus providing minimum CPU elapse time for all images. The proposed ZM-UNLM-based approach with order of moment p max = 4 uses only nine moments which are sufficient to represent the useful characteristics of an image, whereas the existing DCT-UNLM approach uses 15 DCT coefficients extracted in a zig-zag manner.…”

Section: Speed Analysismentioning

confidence: 99%

Invariant moments and transform-based unbiased nonlocal means for denoising of MR images

Singh

Ranade

Singh

2016

Biomedical Signal Processing and Control

Self Cite

View full text Add to dashboard Cite

Section: Speed Analysismentioning

confidence: 99%

Invariant moments and transform-based unbiased nonlocal means for denoising of MR images

Singh

Ranade

Singh

2016

Biomedical Signal Processing and Control

Self Cite

View full text Add to dashboard Cite

“…There are two solutions to this discrepancy: one is based on resampling images into polar coordinates while the other is based on transforming Zernike moments into Cartesian coordinates. Although the first method is computationally efficient [26][27], it is impractical since all images need to be resampled, which is difficult and tedious operation for large image databases. The second approach does not suffer from that kind of problem and therefore is more practical [1].…”

Section: Introductionmentioning

confidence: 99%

Improving stability and invariance of Cartesian Zernike moments

Zhao

Belkasim

2012

2012 IEEE Southwest Symposium on Image Analysis and Interpretation

View full text Add to dashboard Cite

Zernike moments are widely used in shape retrieval, recognition and classification. The rotational invariance property of Zernike moments is very simple to achieve, due to their separable magnitude-phase property. However, Zernike moments are not directly invariant to scale and translation. Recently Cartesian Zernike moments invariants (CZMI) were introduced to directly make Zernike moments invariant under translation and scale. Although CZMI reduced scale error considerably, they are inconsistent and scale error increases for high aspect ratio images. In this paper, we propose a new scale invariance parameter, which reduces scale errors, improves the stability of scale invariance and is more consistent and stable for processing all images including the ones with large aspect ratios.

show abstract

“…Recently, Singh and Upneja [24] and Singh et al [25] have developed methods for the accurate and fast computation of ZMs which alleviate all these problems and facilitate their use for high‐capacity image watermarking. The accuracy in ZMs computation is achieved by using high‐order numerical integration instead of zeroth‐order approximation (ZOA) adopted by existing methods.…”

Section: Introductionmentioning

confidence: 99%

“…The accuracy in ZMs computation is achieved by using high‐order numerical integration instead of zeroth‐order approximation (ZOA) adopted by existing methods. The two errors prevalent in the computation of ZMs – geometric error and numerical integration error – are reduced simultaneously by proposing an accurate computational framework [24]. Better speed and numerically stability is achieved by using recursive algorithms for the computation of high‐order moments.…”

Section: Introductionmentioning

confidence: 99%