Search results

The purpose of this paper is to view the flow concentration of the flowing material in a pipeline conveyor.

Optical tomography provides a method to view the cross sectional image of flowing materials in a pipeline conveyor. Important flow information such as flow concentration profile, flow velocity and mass flow rate can be obtained without the need to invade the process vessel. The utilization of powerful computer together with expensive data acquisition system (DAQ) as the processing device in optical tomography systems has always been a norm. However, the advancements in silicon fabrication technology nowadays allow the fabrication of powerful digital signal processors (DSP) at reasonable cost. This allows the technology to be applied in optical tomography system to reduce or even eliminate the need of personal computer and the DAQ. The DSP system was customized to control the data acquisition of 16 × 16 optical sensors (arranged in orthogonal projection) and 23 × 23 optical sensors (arranged in rectilinear projections). The data collected were used to reconstruct the cross sectional image of flowing materials inside the pipeline. In the developed system, the accuracy of the image reconstruction was increased by 12.5 per cent by using new hybrid image reconstruction algorithm.

The results proved that the data acquisition and image reconstruction algorithm is capable of acquiring accurate data to reconstruct cross sectional images with only little error compared to the expected measurements.

The DSP system was customized to control the data acquisition of 16 × 16 optical sensors (arranged in orthogonal projection) and 23 × 23 optical sensors (arranged in rectilinear projections).

The purpose of this paper is to calculate the two‐dimensional (2D) centre position of objects with known shapes based on the reconstruction image of a square sensing area estimated with simulated and measured data by using electrical capacitance tomography (ECT).

A 2D electrostatic finite element model is used to calculate the capacitances between electrode pairs. A reconstruction algorithm with low computation time provides suitable images for subsequent image processing techniques. The results based on numerical data are verified by measurements.

It is possible to calculate the centre position of up to four rods (cross‐sectional area about 5 per cent of the measuring area) with an accuracy of 3 per cent in both coordinate directions related to the dimensions of the measuring area.

The paper presents an efficient method for position determination of several objects with known shape and uniform permittivity distribution by using ECT measurements with low‐cost electronic for industrial application.

The defect detection problem of color-patterned fabric is still a huge challenge due to the lack of manual defect labeling samples. Recently, many fabric defect detection algorithms based on feature engineering and deep learning have been proposed, but these methods have overdetection or miss-detection problems because they cannot adapt to the complex patterns of color-patterned fabrics. The purpose of this paper is to propose a defect detection framework based on unsupervised adversarial learning for image reconstruction to solve the above problems.

The proposed framework consists of three parts: a generator, a discriminator and an image postprocessing module. The generator is able to extract the features of the image and then reconstruct the image. The discriminator can supervise the generator to repair defects in the samples to improve the quality of image reconstruction. The multidifference image postprocessing module is used to obtain the final detection results of color-patterned fabric defects.

The proposed framework is compared with state-of-the-art methods on the public dataset YDFID-1(Yarn-Dyed Fabric Image Dataset-version1). The proposed framework is also validated on several classes in the MvTec AD dataset. The experimental results of various patterns/classes on YDFID-1 and MvTecAD demonstrate the effectiveness and superiority of this method in fabric defect detection.

It provides an automatic defect detection solution that is convenient for engineering applications for the inspection process of the color-patterned fabric manufacturing industry. A public dataset is provided for academia.

This paper sets out to give an overview about state‐of‐the‐art optical tomographic image reconstruction algorithms that are based on the equation of radiative transfer (ERT).

An objective function, which describes the discrepancy between measured and numerically predicted light intensity data on the tissue surface, is iteratively minimized to find the unknown spatial distribution of the optical parameters or sources. At each iteration step, the predicted partial current is calculated by a forward model for light propagation based on the ERT. The equation of radiative is solved with either finite difference or finite volume methods.

Tomographic reconstruction algorithms based on the ERT accurately recover the spatial distribution of optical tissue properties and light sources in biological tissue. These tissues either can have small geometries/large absorption coefficients, or can contain void‐like inclusions.

These image reconstruction methods can be employed in small animal imaging for monitoring blood oxygenation, in imaging of tumor growth, in molecular imaging of fluorescent and bioluminescent probes, in imaging of human finger joints for early diagnosis of rheumatoid arthritis, and in functional brain imaging.

This paper aims to address three major issues in the development of a vision‐based navigation system for small unmanned aerial vehicles (UAVs) which can be characterized as follows: technical constraints, robust image feature matching and an efficient and precise method for visual navigation.

The authors present and evaluate methods for their solution such as wireless networked control, highly distinctive feature descriptors (HDF) and a visual odometry system.

Proposed feature descriptors achieve significant improvements in computation time by detaching the explicit scale invariance of the widely used scale invariant feature transform. The feasibility of wireless networked real‐time control for vision‐based navigation is evaluated in terms of latency and data throughput. The visual odometry system uses a single camera to reconstruct the camera path and the structure of the environment, and achieved and error of 1.65 percent w.r.t total path length on a circular trajectory of 9.43 m.

The originality/value lies in the contribution of the presented work to the solution of visual odometry for small unmanned aerial vehicles.

The purpose of this paper is to reduce the artifacts in fast Bayesian reconstruction images in electrical tomography. This is in particular important with respect to object detection in electrical tomography applications.

The authors suggest to apply the Box-Cox transformation in Bayesian linear minimum mean square error (BMMSE) reconstruction to better accommodate the non-linear relation between the capacitance matrix and the permittivity distribution. The authors compare the results of the original algorithm with the modified algorithm and with the ground truth in both, simulation and experiments.

The results show a reduction of 50 percent of the mean square error caused by artifacts in low permittivity regions. Furthermore, the algorithm does not increase the computational complexity significantly such that the hard real time constraints can still be met. The authors demonstrate that the algorithm also works with limited observations angles. This allows for object detection in real time, e.g., in robot collision avoidance.

This paper shows that the extension of BMMSE by applying the Box-Cox transformation leads to a significant improvement of the quality of the reconstruction image while hard real time constraints are still met.

Multiresolution representations of data are classical tools in image processing applications. The purpose of this paper is to discuss a particular problem, obtaining good reconstructions of noise images.

A nonlinear multiresolution scheme within Harten's framework corresponding to a nonlinear cell‐average technique is used for color image denoising.

This paper finds it is possible, for example, to apply the theoretical framework to case studies in internationally operating companies delivering a mix of goods and services.

The present study provides a starting point for further research in the denoising problems using nonlinear techniques.

Moreover, the proposed framework has proven to be useful in improving the classical linear multiresolution approaches.

The purpose of this paper is to generate facsimiled rapid prototyping (RP) models for medical analysis that demands an answer about the accuracy of medical models.

The RP technology for anatomical biomodeling is the accurate RP procedure of milling and joining, a method that is used to produce high accurate functional prototypes. To fabricate medical prototypes with RP, there is a need to get appropriate data information. Along that process, image data will be taken by computer‐tomography (CT) images as data basis. The key process is to generate a digital three‐dimensional (3D) model that represents the original object as best as possible. To be able to make a statement about the accuracy of such a model the necessary parameters run along a CT scan are of interest.

A case study using a generated test model is presented in order to show the process accuracy in relation to the chosen scan parameters. The quality of editing CT images for a 3D‐reconstruction as a necessary pre‐process for RP is, to an important degree, based on the used scan parameters.

This paper represents a cutting‐edge analysis that gives answers about the constrictive accuracy that is achievable for medical RP models.

Electrical properties of biological tissues are known to be sensitive to physiological and pathological conditions of living organisms. For instance, human breast cancer or liver tumor cells have a significantly higher electrical conductivity than a healthy tissue. The paper aims to the new recently developed magnetoacoustic tomography with magnetic induction (MAT-MI) which can be deployed for electrical conductivity imaging of low-conductivity objects. Solving a test problem by using an analytical method is a useful exercise to check the validity of the more complex numerical finite element models. Such test problems are discussed in Chapter 3. The detailed analysis of an electromagnetic induction in low-conductivity objects is very important for the next steps in the tomographic process of image reconstruction. Finally, the image reconstruction examples for object’s complex shapes’ have been analyzed. The Lorentz force divergence reconstruction has been achieved with the help of time reversal algorithm.

In given arrangements the magnetic field and eddy current vectors satisfy the Maxwell partial differential equations. Applying the separation of variables method analytical solutions are obtained for an infinitely long conducting cylindrical segment in transient magnetic field. A special case for such a configuration is an infinitely long cylinder with longitudinal crack. The analytical solutions are compared with those obtained by using numerical procedures. For complex shapes of the object, the MAT-MI images have been calculated with the help of the finite element method and time reversal algorithm.

The finite element model developed for a MAT-MI forward problem has been validated by analytical formulas. Based on such a confirmation, the MAT-MI complex model has been defined and solved. The conditions allowing successful MAT-MI image reconstruction have been provided taking into account different conductivity distribution. For given object’s parameters, the minimum number of measuring points allowing successful reconstruction has been determined.

A simple test example has been proposed for MAT-MI forward problem. Analytical closed-form solutions have been used to check the validity of the made in-house finite element software. More complex forward and inverse problems have been solved using the software.

Nowadays, artificial intelligence (AI) technology has demonstrated extensive applications in the field of art design. Attribute editing is an important means to realize clothing style and color design via computer language, which aims to edit and control the garment image based on the specified target attributes while preserving other details from the original image. The current image attribute editing model often generates images containing missing or redundant attributes. To address the problem, this paper aims for a novel design method utilizing the Fashion-attribute generative adversarial network (AttGAN) model was proposed for image attribute editing specifically tailored to women’s blouses.

The proposed design method primarily focuses on optimizing the feature extraction network and loss function. To enhance the feature extraction capability of the model, an increase in the number of layers in the feature extraction network was implemented, and the structure similarity index measure (SSIM) loss function was employed to ensure the independent attributes of the original image were consistent. The characteristic-preserving virtual try-on network (CP_VTON) dataset was used for train-ing to enable the editing of sleeve length and color specifically for women’s blouse.

The experimental results demonstrate that the optimization model’s generated outputs have significantly reduced problems related to missing attributes or visual redundancy. Through a comparative analysis of the numerical changes in the SSIM and peak signal-to-noise ratio (PSNR) before and after the model refinement, it was observed that the improved SSIM increased substantially by 27.4%, and the PSNR increased by 2.8%, serving as empirical evidence of the effectiveness of incorporating the SSIM loss function.

The proposed algorithm provides a promising tool for precise image editing of women’s blouses based on the GAN. This introduces a new approach to eliminate semantic expression errors in image editing, thereby contributing to the development of AI in clothing design.