Investigation and classification of fibre deformation using interferometric and machine learning techniques

Omar, E.Z.

doi:10.1007/s00340-020-7399-1

Cited by 13 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here,

E ((), x, y)

presents the illumination of the background,

D ((), x, y)

refers to the demodulated amplitude,

u_{o}

is the carrier frequency,

∆ ψ ((), x, y)

is the desired phase object, and

μ ((), x, y)

presents the additive noise that formed in the microinterferogram. The computational phase‐shifting interferometric method using a single‐shot microinterferogram technique that proposed in References (Omar, 2020a; Omar, 2020b) are considered to yield three daughter microinterferograms, with accurately known phase shift (π/2) rad between them, from the captured microinterferogram in Equation (1) as given in the following equations

h_{2} ((), x, y) = E ((), x, y) + D ((), x, y) \cos ([], 2 π u_{o} x + ∆ ψ ((), x, y) + \frac{π}{2}) + μ ((), x, y)

h_{3} ((), x, y) = E ((), x, y) + D ((), x, y) \cos ([], 2 π u_{o} x + ∆ ψ ((), x, y) + π) + μ ((), x, y)

h_{4} ((), x, y) = E ((), x, y) + D ((), x, y) \cos ([], 2 π u_{o} x + ∆ ψ ((), x, y) + \frac{3 π}{2}) + μ ((), x, y)

Before demodulating the phase object via the four‐frame phase shifting algorithm, the noisy microinterferograms in Equations (…”

Section: The Suggested Methodsmentioning

confidence: 99%

“…Convolution neural networks (CNNs) are subtypes of deep neural network (DNN) that applied to perform significant tasks such as images classification, natural language processing, segmentation, and image reconstruction (Karim et al, 2018; LeCun, Bengio, & Hinton, 2015; Omar, 2020a; Omar, 2020b; Omar et al, 2020). Generally, the structure of the CNN includes three layers; input layer, multiple convolutional layers (hidden layers), and output layer (LeCun et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

“…Also, these types of networks need to set the filters and the hidden layers numbers according to the size of the established data set. On the other hand, the pre‐trained networks can be performed accurate training using a small‐scale data set ∼ several hundreds or thousands of images (Omar, 2020a; Omar, 2020b; Omar et al, 2020). The most common pre‐trained convolution neural networks include GoogleNet, VGG‐19, VGG‐16, and Alexnet (Rawat & Wang, 2017).…”

Section: Introductionmentioning

confidence: 99%

“…Generally, the structure of the CNN includes three layers; input layer, multiple convolutional layers (hidden layers), and output layer (LeCun et al, 2015). These networks are characterized by its ability to retrieve the features of the input images without human intervention (Omar, 2020a;Omar, 2020b). There are two kinds for the training process in the CNNs; the training using the pre-trained convolution neural networks (transfer learning), and the training from scratch (Rawat & Wang, 2017).…”

mentioning

confidence: 99%

See 3 more Smart Citations

Adaptive investigation of the optical properties of polymer fibers from mixing noisy phase shifting microinterferograms using deep learning algorithms

Abo-Lila

Sokkar

Seisa

et al. 2021

Microscopy Res & Technique

View full text Add to dashboard Cite

In this article, an adaptive denoising method is suggested to accurate investigate the optical and structural features of polymeric fibers from noisy phase shifting microinterferograms. The mixed class of noise that may produce in the phase‐shifting interferometric techniques is established. To our knowledge, this is an early study considered the mixing noises that may occur in microinterferograms. The suggested method utilized the convolution neural networks to detect the noise class and then denoising, it according to its class. Four convolution neural networks (Googlenet, VGG‐19, Alexnet, and Alexnet–SVM) are refined to perform the automatic classification process for the noise class in the established data set. The network with the highest validation and testing accuracy of these networks is considered to apply the suggested method on realistic noisy microinterferograms for polymeric fibers, polypropylene and antimicrobial polyethylene terephthalate)/titanium dioxide, recoded using interference microscope. Also, the suggested method is applied on noisy microinterferograms include crazing and nanocomposite material. The demodulated phase maps and the three‐dimensional birefringence profiles are calculated for tested fibers according to the suggested method. The obtained results are compared with the published data for these fibers and found to be in good agreements.

show abstract

“…Here,

E ((), x, y)

presents the illumination of the background,

D ((), x, y)

refers to the demodulated amplitude,

u_{o}

is the carrier frequency,

∆ ψ ((), x, y)

is the desired phase object, and

μ ((), x, y)

h_{2} ((), x, y) = E ((), x, y) + D ((), x, y) \cos ([], 2 π u_{o} x + ∆ ψ ((), x, y) + \frac{π}{2}) + μ ((), x, y)

h_{3} ((), x, y) = E ((), x, y) + D ((), x, y) \cos ([], 2 π u_{o} x + ∆ ψ ((), x, y) + π) + μ ((), x, y)

h_{4} ((), x, y) = E ((), x, y) + D ((), x, y) \cos ([], 2 π u_{o} x + ∆ ψ ((), x, y) + \frac{3 π}{2}) + μ ((), x, y)

Before demodulating the phase object via the four‐frame phase shifting algorithm, the noisy microinterferograms in Equations (…”

Section: The Suggested Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Adaptive investigation of the optical properties of polymer fibers from mixing noisy phase shifting microinterferograms using deep learning algorithms

Abo-Lila

Sokkar

Seisa

et al. 2021

Microscopy Res & Technique

View full text Add to dashboard Cite

show abstract

“…One of them is captured at the focus plane and the other two intensity images are captured at defined defocus planes [ 11 , 12 ]. The demodulated phase object via the TIE technique has worthy information such as surface profile, refractive index, degree of crystallinity, and polarizability [ 10 , 13 ]. The TIE technique has many unique advantages such as stability in measurements, simple optical setup (does not need reference beam), produce directly absolute phase map, capabilities to work with partially coherent source, and does not need iterations (simple calculations) [ 10 , 12 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

Investigation of the opto-thermo-mechanical properties of antimicrobial PET/TiO2 fiber using the transport of intensity equation technique

et al. 2022

Self Cite

View full text Add to dashboard Cite

The transport of intensity equation (TIE) technique is used to investigate the effect of stretching and annealing conditions on the optical features and antimicrobial activity of polyethylene terephthalate (PET) fibers treated with TiO 2 nanoparticles. The main core of this paper gets the most preferable optical and mechanical properties for PET/TiO 2 fiber which maintains its antibacterial activity. The variation of the refractive index of untreated PET/TiO 2 fiber along its axis is studied. The computed tomography technique is used to investigate the morphology of the tested fiber and the distribution of TiO 2 nanoparticles inside the fiber. The effect of stretching on the refractive index and the density of TiO 2 nanoparticles of drawn PET/TiO 2 fibers are carried out. The antimicrobial activity of the PET/TiO 2 fibers are evaluated before and after stretching. The PET/TiO 2 fibers are annealed at different temperatures and durations. The influence of annealing on the variation of the refractive index of PET/TiO 2 fiber along its axis and the distribution of TiO 2 is investigated.

show abstract

Generating planar distributions of soot particles from luminosity images in turbulent flames using deep learning

et al. 2021

View full text Add to dashboard Cite

Investigation and classification of fibre deformation using interferometric and machine learning techniques

Cited by 13 publications

References 24 publications

Adaptive investigation of the optical properties of polymer fibers from mixing noisy phase shifting microinterferograms using deep learning algorithms

Adaptive investigation of the optical properties of polymer fibers from mixing noisy phase shifting microinterferograms using deep learning algorithms

Investigation of the opto-thermo-mechanical properties of antimicrobial PET/TiO2 fiber using the transport of intensity equation technique

Generating planar distributions of soot particles from luminosity images in turbulent flames using deep learning

Contact Info

Product

Resources

About