Invariant nonlinear correlation and spectral index for diatoms recognition

Fimbres-Castro, Claudia; Álvarez-Borrego, Josué; Bueno-Ibarra, Mario Alonso

doi:10.1117/1.oe.51.4.047201

Cited by 10 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comparison of the digital system in Figure 5 (Fourier masks), Figure 9 (Bessel masks) and that developed by Fimbres-Castro, et al [15] is presented. Also, the vectorial signatures digital system was tested using the database image in Figure 6.…”

Section: Comparison Analysismentioning

confidence: 98%

“…The algorithms by Fouriers masks (Figure 5), Bessels masks ( Figure 9) and the vectorial signatures [15] were tested using problem images altered with eight different types of non-homogeneous illumination, Figure 12 images ( Figure 6) were rotated one degree by one degree (until complete the circle) and all of them were altered using the eight different types of non-homogeneous illumination. Hence, the algorithms were proved with 60,480 problem images with different illuminations.…”

Section: Illuminationmentioning

confidence: 99%

“…Section 3 presents the digital system by the Bessel binary rings masks. Section 4 shows the comparison analysis of the methodologies in Sections 2 and 3, and that given in [15] called vectorial signatures. The confidence level of each of those methodologies, the computational time, noise and the non-homogeneous illumination analysis are presented.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Position and rotation-invariant pattern recognition system by binary rings masks

Solorza

Álvarez-Borrego

2015

Journal of Modern Optics

View full text Add to dashboard Cite

In this paper, algorithms invariant to position, rotation, noise and non-homogeneous illumination are presented. Here, several manners are studied to generate binary rings mask filters and the corresponding signatures associated to each image. Also, in this work it is shown that digital systems, which are based on the k-law non-linear correlation, are k-invariant for 0 < k < 1. The methodologies are tested using greyscale fossil diatoms digital images (real images), and considering the great similarity between those images the results obtained are excellent. The box plot statistical analysis and the computational cost times yield that the Bessel rings masks are the best option when the images contain a homogeneous illumination and the Fourier masks digital system is the right selection when the non-homogeneous illumination and noise is presented in the images.

show abstract

Section: Comparison Analysismentioning

confidence: 98%

Section: Illuminationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Position and rotation-invariant pattern recognition system by binary rings masks

Solorza

Álvarez-Borrego

2015

Journal of Modern Optics

View full text Add to dashboard Cite

show abstract

“…Unfortunately, these filters are specialized to solve specific problems, for example one filter could has an excellent performance in the discrimination step and the signal-to-noise ratio but a low e ciency under non-homogeneous illumination [2][3][4] . Although composite filters has been used, the problem of the invariant to rotation, scale and translation (RST) correlator image descriptor is an active field of study due to its intrinsic complexity [5][6][7][8][9][10][11] .…”

Section: Introductionmentioning

confidence: 99%

Pattern recognition descriptor using the Z-Fisher transform

2015

View full text Add to dashboard Cite

In this work is presented a pattern recognition image descriptor invariant to rotation, scale and translation (RST), which classify images using the Z-Fisher transform. A binary rings mask is generated using the Fourier transform. The normalized analytic Fourier-Mellin amplitude spectrum is filtered with that mask to build 1D signature. The signatures comparison of the problem image and the target are done by the Pearson correlation coe cient (PCC). In general, those PCC values do not satisfy a normal distribution, hence the Fisher's Z distribution is employed to determine the confidence level of the RST invariant descriptor. The descriptor presents a confidence level of 95%.

show abstract

“…Their specific forms vary from a classic filter [1] to multiple filters suggested in contemporary optics. In particular, image correlation analysis has been successfully used in engineering [2][3][4], identification of marine species [5][6][7][8][9], inclusion bodies [10], carcinogenic spots on the skin [11], etc.…”

Section: Introductionmentioning

confidence: 99%

Identification of phytoplankton species using Hermite transform

Castro-Valdez¹,

Álvarez-Borrego²

2018

Ukr. J. Phys. Opt.

View full text Add to dashboard Cite

Abstract. We apply a Hermite transform joint with a classical correlation analysis to successfully recognize phytoplankton species even in such complicated cases when the relevant images reveal the patterns of inhomogeneous illumination and natural distortions. The images of phytoplankton species are divided into two groups consisting of 30 samples each. Those belonging to the first group are the images with neither inhomogeneous illumination nor noise, while the second one embraces the images with the background noise, inhomogeneous illumination and real distortions. We find the optimal Hermite-transform order to be used in finding correlations among the images. It is given by a so-called 'peak correlation energy' metric. Using the images modified by the Hermite transform with a classical Vander-Lugt filter, we are able to distinguish all the phytoplankton species in the test images. A classical composite filter is also applied to the two groups of images. For the first group, the composite filter is created using different patterns of illumination of the same species. In the second group, this filter is composed using various specimens of the same species in order to identify a specific species. In the both cases, the Hermite transform joined with the classical correlation analysis can distinguish all the phytoplankton species.

show abstract

Invariant nonlinear correlation and spectral index for diatoms recognition

Cited by 10 publications

References 16 publications

Position and rotation-invariant pattern recognition system by binary rings masks

Position and rotation-invariant pattern recognition system by binary rings masks

Pattern recognition descriptor using the Z-Fisher transform

Identification of phytoplankton species using Hermite transform

Contact Info

Product

Resources

About