Virtual unrolling technology based on terahertz computed tomography

Wang, Tianyi; Wang, Kejia; Zou, Kaigang; Shen, Sishi; Yang, Yongqiang; Zhang, Mengting; Yang, Zhengang; Liu, Jinsong

doi:10.1016/j.optlaseng.2021.106924

Cited by 10 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The content and style representations can be well separated in the convolutional neural network used in this paper's algorithm, so that the two representations can be processed independently to produce new perceptually meaningful images [12]. The following is an image of the effect of the oil painting implemented according to the coding, where we combine different representations of the image content with multiple stylistic representations of the oil painting artwork.…”

Section: Resultsmentioning

confidence: 99%

Subdivision of Artistic Objectives of Oil Painting Creation under the Evaluation of Deep Learning Model

2022

Journal of Sensors

View full text Add to dashboard Cite

In order to fully segment and classify the artistic objectives of painting and realise the needs of automatic classification and retrieval of painting by computer, this paper proposes to establish convolution neural network with dual core compression activation module and deep separation convolution. The DKSE module is constructed based on the structural features of SKNet. SKNet extracts the overall image and detail features, SENet enhances the channel features. Using DKSE module and depth separable convolution, a convolution neural network is established to classify paintings. DKSE module can effectively improve the classification performance of the model, fully extract the overall and local detail features of oil painting images, and provide better classification accuracy than the traditional network model.

show abstract

Section: Resultsmentioning

confidence: 99%

Subdivision of Artistic Objectives of Oil Painting Creation under the Evaluation of Deep Learning Model

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…In IV-A we introduce the concept of simulating a wide Gaussian beam as a combination of multiple infinitesimal thin elementary beams. We do so by defining a maximum width at the start position w max = w(−x bound ), which can be calculated following (11), where 2•x bound is the width of the imaging scene. Elementary rays ⃗…”

Section: Appendixmentioning

confidence: 99%

“…Typical applications in an industrial context are nondestructive layer thickness determination and defect detection using volumetric imaging [6], [7], [8], [9], [10]. Materials of interest range from ceramics, glass-fiber reinforced composites [2] and plastics [6] over paints and coatings [9] to paper [11] and wood [12].…”

Section: Introductionmentioning

confidence: 99%

A Priori Information and Off-Axis Measurements in Terahertz Tomography

et al. 2023

View full text Add to dashboard Cite

Terahertz tomography is a non-contact inspection technique to image objects from multiple angles and reconstruct their 3D volume from intensity and time-of-flight transmission data, without the need for radiation protection measures. Unlike X-rays, terahertz radiation is subject to strong diffraction and refraction when propagating through dielectric materials, which often deteriorate the image reconstruction quality. Our solution to this problem applies ray tracing, considering the beam shape and an a priori model of the sample under investigation to predict the beam paths of the terahertz radiation. We present two reconstruction methods based on the resulting beam path predictions yielding higher image quality. Method 1 filters out beams deviating strongly, thus removing induced artifacts and errors from the reconstruction image. Method 2 employs off-axis measurements that acquire data along the full detection plane and in this way detect even strongly deflected beams. Considering these beams and the information they carry in the reconstruction enhances the image quality. Applying these methods to terahertz tomography, even complicated structures can be imaged. We display the significant enhancements achieved with the two methods by comparing the reconstruction results of different polymeric samples.INDEX TERMS Terahertz radiation, computed tomography, non-destructive testing, a priori information, off-axis measurement, reconstruction algorithms, imaging, time-of-flight, conjugate gradient least square (CGLS).

show abstract

“…we introduce the concept of simulating a wide Gaussian beam as a combination of multiple infinitesimal thin elementary beams. We do so by defining a maximum width at the start position 𝑤 𝑚𝑎𝑥 = 𝑤(−𝑥 𝑏𝑜𝑢𝑛𝑑 ), which can be calculated following (11), where 2 ⋅ 𝑥 𝑏𝑜𝑢𝑛𝑑 is the width of the imaging scene. Elementary rays 𝑥 ⃗ 𝑖,𝜃 are considered for the reconstruction, if the distance 𝑑 = ห𝑥 ⃗ 0,0 𝑖,𝜃 − y 0 (𝑠)ห ≤ 𝑤 𝑚𝑎𝑥 .…”

Section: Appendixmentioning

confidence: 99%

“…In the industrial context, non-destructive testing (NDT), such as layer thickness determination and defect detection by imaging are of particular interest [6]- [10]. Among others, materials of interest range from ceramics, glass-fiber reinforced composites [2] and plastics [6] over paints and coatings [9] to paper [11] and wood [12]. Many imaging geometries, in the literature referred to as tomography, create a volumetric scan of the sample under test (SUT) by measuring in a reflection setup with only single-sided access to the sample.…”

Section: Introductionmentioning

confidence: 99%

A Priori Information and Off-Axis Measurements in Terahertz Tomography

May¹,

Keil²,

Freymann³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>Terahertz tomography is a non-contact inspection technique to image objects from multiple angles and reconstruct their 3D volume from intensity and time-of-flight transmission data, without the need for radiation protection measures. Unlike X-rays, terahertz radiation is subject to strong diffraction and refraction as it propagates through dielectric materials, which can deteriorate the image reconstruction quality. Our solution to this problem applies ray tracing, considering the beam shape and an <em>a priori</em> model of the SUT to obtain high-quality image data. We present two reconstruction methods based on the resulting beam path predictions. Method 1 filters out strongly deviated beams, and thus removes the induced artifacts and errors from the reconstruction image. Method 2 employs off-axis measurements, acquiring data along the whole detection plane and this way detecting even strongly deviated beams. Considering these beams and the information they carry in the reconstruction enhances the image quality. Applying these methods to terahertz tomography, even complicated structures can be imaged, provided their feature size is above the diffraction limit. We display the significant enhancements achieved with the two methods by comparing the reconstruction results of different polymeric samples. </p>

show abstract

Virtual unrolling technology based on terahertz computed tomography

Cited by 10 publications

References 43 publications

Subdivision of Artistic Objectives of Oil Painting Creation under the Evaluation of Deep Learning Model

Subdivision of Artistic Objectives of Oil Painting Creation under the Evaluation of Deep Learning Model

A Priori Information and Off-Axis Measurements in Terahertz Tomography

A Priori Information and Off-Axis Measurements in Terahertz Tomography

Contact Info

Product

Resources

About