Geometric Distortion Research Articles

In-process dimensional and geometrical characterization of laser-powder bed fusion lattice structures through high-resolution optical tomography

Additive Manufacturing (AM) technologies, i.e. Laser-Powder Bed Fusion (l-PBF), have made possible the fabrication of complex and lightweight components not feasible with conventional manufacturing processes. Lattice structures are one of the most representative examples and they have many advantages (high mechanical properties, thermal insulation and good energy absorption ability, etc.) which are limited by internal defects, poor surface quality and dimensional accuracy. In this context, X-ray-based Computed Tomography (XCT) is, currently, the only way for quality assessment of these structures, thanks to its capability to see also internal features, while optical scanning techniques can reconstruct only external surfaces. In this work, an innovative and cost-effective optical layerwise monitoring technique, for dimensional and geometrical characterization of lattice structures realized by l-PBF, was proposed. It exploited the high-resolution optical tomography (HR-OT) and it had a double purpose: it was used as a layerwise in-process monitoring method, able to detect timely and effectively the onset of geometric distortions and, in addition, it provided, at the end of the manufacturing process, a 3D reconstruction of the fabricated structure, comprising external and internal features, suitable for post-process quality assessment.This article is among the first to show a monitoring methodology suitable for lattice structures realized by l-PBF technologies.

An aberration correction approach for single and dual aperture ultrasound imaging of the abdomen

Abdominal ultrasound image quality is hampered by phase aberration, that is mainly caused by the large speed-of-sound (SoS) differences between fat and muscle tissue in the abdominal wall. The mismatch between the assumed and actual SoS distribution introduces general blurring of the ultrasound images, and acoustic refraction can lead to geometric distortion of the imaged features. Large aperture imaging or dual-transducer imaging can improve abdominal imaging at deep locations by providing increased contrast and resolution. However, aberration effects for large aperture imaging can be even more severe, which limits its full potential. In this study, a model-based aberration correction method for arbitrary acquisition schemes is introduced for delay-and-sum (DAS) beamforming and its performance was analyzed for both single- and dual-transducer ultrasound imaging. The method employs aberration corrected wavefront arrival times, using manually assigned local SoS values. Two wavefront models were compared. The first model is based on a straight ray approximation, and the second model on the Eikonal equation, which is solved by a multi-stencils fast marching method. Their accuracy for abdominal imaging was evaluated in acoustic simulations and phantom experiments involving tissue-mimicking and porcine material with large SoS contrast (∼100 m/s). The lateral resolution was improved by up to 90% in simulations and up to 65% in experiments compared to standard DAS, in which the use of Eikonal beamforming generally outperformed straight ray beamforming. Moreover, geometric distortions were mitigated in multi-aperture imaging, leading to a reduction in position error of around 80%. A study on the sensitivity of the aberration correction to shape and SoS of aberrating layers was performed, showing that even with imperfect segmentations or SoS values, aberration correction still outperforms standard DAS.

Stress relief heat treatment and mechanical properties of laser powder bed fusion built 21-6-9 stainless steel

In this work, the effectiveness of residual stress relief annealing on a laser powder bed fusion (L-PBF) manufactured austenitic stainless steel, alloy 21-6-9 was investigated. Residual stress levels were gauged using geometrical distortion and relaxation testing results. In the investigated temperature interval (600–850 °C), shape stability was reached after subjecting the as-built material to an annealing temperature of 850 °C for 1 h. Microstructural characterization and tensile testing were also performed for each annealing temperature to evaluate the alloy's thermal stability and the resulting tensile properties. In the as-built state, a yield strength (YS) of 640 MPa, ultimate tensile strength (UTS) of 810 MPa and 4D elongation of 47% were measured. Annealing at 850 °C for 1 h had little measurable effect on ductility (48% 4D elongation) while still having a softening effect (UTS = 775 MPa, YS = 540 MPa). From the microstructural characterization, cell-like features were observed sporadically in the annealed condition and appeared stable up until 800 °C after which gradual dissolution began, with the last remnants disappearing after subjecting the material to 900 °C for 1 h.

Fluorination-Induced Asymmetry in Vacancy-Ordered Brownmillerite: Route to Multiferroic Behavior

Four distinct classes of multiferroics are usually being discussed in the literature, in which ferroelectricity is respectively driven by electronic lone pairs, geometry, charge ordering, and magnetism. Each class has its own shortcomings for technological applications. Here, through a combined experimental and theoretical investigation, we propose a mechanism to achieve multiferroicity in a single phase by engineering the anionic network and creating local geometric distortions in fluorinated, vacancy-ordered brownmillerite Ca2Mn2O5–xFy. The system exhibits both ferroelectricity and an antiferromagnetic order above room temperature, pointing toward a novel route to multiferroicity by anion mixing.

GraphSKT: Graph-guided Structured Knowledge Transfer for Domain Adaptive Lesion Detection.

Adversarial-based adaptation has dominated the area of domain adaptive detection over the past few years. Despite their general efficacy for various tasks, the learned representations may not capture the intrinsic topological structures of the whole images and thus are vulnerable to distributional shifts especially in real-world applications, such as geometric distortions across imaging devices in medical images. In this case, forcefully matching data distributions across domains cannot ensure precise knowledge transfer and are prone to result in the negative transfer. In this paper, we explore the problem of domain adaptive lesion detection from the perspective of relational reasoning, and propose a Graph-Structured Knowledge Transfer (GraphSKT) framework to perform hierarchical reasoning by modeling both the intra- and inter-domain topological structures. To be specific, we utilize cross-domain correspondence to mine meaningful foreground regions for representing graph nodes and explicitly endow each node with contextual information. Then, the intra- and inter-domain graphs are built on the top of instance-level features to achieve a high-level understanding of the lesion and whole medical image, and transfer the structured knowledge from source to target domains. The contextual and semantic information is propagated through graph nodes methodically, enhancing the expressive power of learned features for the lesion detection tasks. Extensive experiments on two types of challenging datasets demonstrate that the proposed GraphSKT significantly outperforms the state-of-the-art approaches for detection of polyps in colonoscopy images and of mass in mammographic images.

Combining Feature Correspondence With Parametric Chamfer Alignment: Hybrid Two-Stage Registration for Ultra-Widefield Retinal Images.

We propose a novel hybrid framework for registering retinal images in the presence of extreme geometric distortions that are commonly encountered in ultra-widefield (UWF) fluorescein angiography. Our approach consists of two stages: a feature-based global registration and a vessel-based local refinement. For the global registration, we introduce a modified RANSAC (random sample and consensus) that jointly identifies robust matches between feature keypoints in reference and target images and estimates a polynomial geometric transformation consistent with the identified correspondences. Our RANSAC modification particularly improves feature point matching and the registration in peripheral regions that are most severely impacted by the geometric distortions. The second local refinement stage is formulated in our framework as a parametric chamfer alignment for vessel maps obtained using a deep neural network. Because the complete vessel maps contribute to the chamfer alignment, this approach not only improves registration accuracy but also aligns with clinical practice, where vessels are typically a key focus of examinations. We validate the effectiveness of the proposed framework on a new UWF fluorescein angiography (FA) dataset and on the existing narrow-field FIRE (fundus image registration) dataset and demonstrate that it significantly outperforms prior retinal image registration methods in accuracy. The proposed approach enhances the utility of large sets of longitudinal UWF images by enabling: (a) automatic computation of vessel change metrics such as vessel density and caliber, and (b) standardized and co-registered examination that can better highlight changes of clinical interest to physicians.

Combination of Dynamical Movement Primitives With Trajectory Segmentation and Node Mapping for Robot Machining Motion Learning

Movement primitive (MP) is proposed to model the robot skills with the idea of reusing basic behavior units. By learning the demonstrations, the MP can be modeled and utilized to generate similar motions to adapt to slightly changed scenarios. However, many kinds of MP models do not consider the geometric shape constraints and the trajectory execution accuracy, which will bring the shape distortion and contour error when task generalization. Traditional MP models are mainly studied for imitating human-like operating skills and have not been applied in industrial scenarios such as robot machining. In this article, a framework based on the combination of dynamical movement primitives (CDMP) with trajectory segmentation and node mapping methods is proposed to realize the imitation of robot machining motion. The demonstration machining trajectory is segmented first according to the kinematic features, and the shape features are extracted and stored by the node mapping policy. Then, the CDMP model is built for describing a complicated machining motion with many component DMPs. The parameters preferences associated with the model performance of CDMP are analyzed in the simulation. At last, a robot grinding experiment is conducted to show that the proposed framework can successfully imitate the machining motion with low geometric distortion, contour error, and computation cost, which also obtain a good surface quality and can significantly improve the intelligence level of robot machining.

Image retargeting quality assessment: A survey

With the increasing variety of display devices, image retargeting has become an indispensable technology for adjusting the aspect ratio of images to adapt to different display terminals. Since the retargeting operation would cause geometric distortion and content loss of the image, the image retargeting quality assessment (IRQA) is necessary to guide the retargeting algorithm’s optimization, selection, and design. Our paper mainly works for systematically reviewing the state-of-the-art technologies in IRQA. And then, this paper further discusses image registration algorithms for matching the original image and the retargeted image. Next, we investigate the feature measurement methods for image retargeting quality evaluation. To facilitate the quantitative assessment of the IRQA methods, this paper gives a list of publicly open datasets and the performance of the mainstream methods. Finally, some promising research directions towards IRQA are pointed out. From this survey, engineers from the industry may find skills to improve their image retargeting systems, and researchers from academia may find ideas to conduct some innovative work.

Feasibility of Simultaneous Multislice Acceleration Technique in Readout-Segmented Echo-Planar Diffusion-Weighted Imaging for Assessing Rectal Cancer.

Readout-segmented echo-planar imaging (rs-EPI) with simultaneous multislice (SMS) technology has been successfully applied to tumor research in many organs, but no feasibility study in rectal cancer has been reported, and the optimal acceleration of SMS with rs-EPI in rectal cancer has not been well determined yet. To investigate the feasibility of SMS rs-EPI of rectal cancer with different acceleration factors (AFs) and its influence on image quality, acquisition time and apparent diffusion coefficients (ADCs) in comparison to conventional sequences. All patients underwent rs-EPI and SMS rs-EPI with AFs of 2 and 3 (2 × SMS rs-EPI and 3 × SMS rs-EPI, respectively) using a 3T scanner. Acquisition times of the three rs-EPI sequences were measured. Image qualitative parameters (5-point Likert scale), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), geometric distortion, and apparent diffusion coefficient (ADC) values of the three sequences were compared. A total of eighty-three patients were enrolled in our study. rs-EPI and 2 × SMS rs-EPI offered equivalently high overall image quality with a scan time reduction to nearly half (rs-EPI: 137 s, 2 × SM rs-EPI: 60 s). 3 × SMS rs-EPI showed significantly poorer image quality (p < 0.05). ADC values were significantly lower in 3 × SMS rs-EPI compared to rs-EPI in rectal tumors and normal tissue (tumor tissue: rs-EPI 1.19 ± 0.21 × 10-3 mm2/s, 3 × SMS rs-EPI 1.10 ± 0.26 × 10-3 mm2/s, p < 0.001; normal tissue: rs-EPI 1.68 ± 0.13 × 10-3 mm2/s, 3 × SMS rs-EPI 1.54 ± 0.20 × 10-3 mm2/s, p < 0.001). SMS rs-EPI using an AF of 2 is feasible for rectal MRI resulting in substantial reductions in acquisition time while maintaining diagnostic image quality and similar ADC values to those of rs-EPI when the slice distance and number of shots are the same among three rs-EPI sequences.

A novel method for real-time ATR system of AUV based on Attention-MobileNetV3 network and pixel correction algorithm

This paper proposes an Automatic Target Recognition (ATR) system based on the Autonomous Underwater Vehicle (AUV) equipped with side scan sonar for real-time detection and positioning of underwater targets. The system introduces a pre-processing algorithm for the original Side Scan Sonar (SSS) image, which performs pixel-level correction of the image according to the slant range setting of the SSS sensor and the height from the seabed to eliminate the influence of target geometric distortion on the subsequent recognition algorithm and improve the recognition accuracy. At the same time, the attitude angle information of the AUV is obtained to correct the target position, making each pixel of the pre-processed image has underwater positioning (latitude and longitude) information. Since SSS images are seriously disturbed by noise, in order to accurately extract target features in real time, on the basis of selecting the lightweight network MobileNetV3, we introduce attention mechanism and integrated learning to meet the requirements of underwater target recognition accuracy and real-time performance. The multi-classifier ensemble prediction results further reduce the mis-identification rate of submarine targets. The ATR system fuses the prediction results and the submarine target position and sends it to the AUV main control system to guide the AUV how to navigate and plan path at the subsequent. The experimental results show that, we validate that the proposed method matches the state of the art in segmentation accuracy, the ATR system proposed in this paper can be embedded in the underwater unmanned platform, and achieve accurate underwater target detection and positioning, The real-time recognition speed of each picture is about 0.058 s.

Rapid high-fidelity mapping using single-shot overlapping-echo acquisition and deep learning reconstruction.

To develop and evaluate a single-shot quantitative MRI technique called GRE-MOLED (gradient-echo multiple overlapping-echo detachment) for rapid mapping. In GRE-MOLED, multiple echoes with different TEs are generated and captured in a single shot of the k-space through MOLED encoding and EPI readout. A deep neural network, trained by synthetic data, was employed for end-to-end parametric mapping from overlapping-echo signals. GRE-MOLED uses pure GRE acquisition with a single echo train to deliver maps less than 90 ms per slice. The self-registered B0 information modulated in image phase was utilized for distortion-corrected parametric mapping. The proposed method was evaluated in phantoms, healthy volunteers, and task-based FMRI experiments. The quantitative results of GRE-MOLED mapping demonstrated good agreement with those obtained from the multi-echo GRE method (Pearson's correlation coefficient=0.991 and 0.973 for phantom and in vivo brains, respectively). High intrasubject repeatability (coefficient of variation <1.0%) were also achieved in scan-rescan test. Enabled by deep learning reconstruction, GRE-MOLED showed excellent robustness to geometric distortion, noise, and random subject motion. Compared to the conventional FMRI approach, GRE-MOLED also achieved a higher temporal SNRand BOLD sensitivity in task-based FMRI. GRE-MOLED is a new real-time technique for quantification with high efficiency and quality, and it has the potential to be a better quantitative BOLD detection method.

LECA: A learned approach for efficient cover-agnostic watermarking

In this work, we present an efficient multi-bit deep image watermarking method that is cover-agnostic yet also robust to geometric distortions such as translation and scaling as well as other distortions such as JPEG compression and noise. Our design consists of a light-weight watermark encoder jointly trained with a deep neural network based decoder. Such a design allows us to retain the efficiency of the encoder while fully utilizing the power of a deep neural network. Moreover, the watermark encoder is independent of the image content, allowing users to pre-generate the watermarks for further efficiency. To offer robustness towards geometric transformations, we introduced a learned model for predicting the scale and offset of the watermarked images. Moreover, our watermark encoder is independent of the image content, making the generated watermarks universally applicable to different cover images. Experiments show that our method outperforms comparably efficient watermarking methods by a large margin.

The influence of image capture and processing on MTF for end of line test and validation

Slanted edge MTF measurement as per ISO12233 is the defacto standard for measuring camera sharpness at manufacturing end of line. MTF measured by slanted edge has a number of advantages for measuring sharpness, being scale invariant, and relatively robust to geometric distortion. However, slanted edge MTF measurement is known to be affected by image processing algorithms, including demosaic, edge enhancement, and denoise algorithms. To avoid these confounding factors, it is increasingly common to measure MTF directly from the raw sensor image. This approach is logical if you are assessing the optomechanical lens-imager alignment and focus. However, end-of-line production testing has specific requirements, including speed of execution, repeatability and reproducibility. These requirements are typically not considered when configuring a camera for end-of-line MTF measurement. In this study, the execution time, repeatability and reproducibility of MTF measurement for multiple image capture and image processing combinations are examined.

PERFORMANCE EVALUATION OF LEARNING-BASED METHODS FOR MULTISPECTRAL SATELLITE IMAGE MATCHING

Abstract. Multispectral image registration is one of the most critical requirements to achieve reliable remote sensing goals such as change detection, image fusion, etc., due to providing complementary knowledge of the scene. On the one hand, this issue has always been a hot topic of research according to significant appearance differences, including geometric and nonlinear radiometric distortions. On the other hand, developing deep learning methods promises precise results in image processing and, in particular, image registration. It is no longer limited to low-level information structures, such as intensity and gradients. However, it is possible to provide more reliable results by extracting various high-level features and removing feature engineering. Therefore, we need extensive experiments in multispectral image registration to determine an efficient and robust method. To this end, this paper evaluates six well-known recently proposed learning-based feature descriptors, including LOFTR, TFeat, HardNet8, HardNet, SosNet, and HyNet, against geometric distortions within real multispectral images. Evaluations demonstrate the general superiority of the HardNet8 descriptor due to extracting high-level features within eight convolution layers.

Minimizing susceptibility-induced BOLD sensitivity loss in multi-band accelerated fMRI using point spread function mapping and gradient reversal

Objective. Interleaved reverse-gradient fMRI (RG-fMRI) with a point-spread-function (PSF) mapping-based distortion correction scheme has the potential to minimize signal loss in echo-planar-imaging (EPI). In this work, the RG-fMRI is further improved by imaging protocol optimization and application of reverse Fourier acquisition. Approach. Multi-band imaging was adapted for RG-fMRI to improve the temporal and spatial resolution. To better understand signal dropouts in forward and reverse EPIs, a simple theoretical relationship between echo shift and geometric distortion was derived and validated by the reliable measurements using PSF mapping method. After examining practical imaging protocols for RG-fMRI in three subjects on both a conventional whole-body and a high-performance compact 3 T, the results were compared and the feasibility to further improve the RG-fMRI scheme were explored. High-resolution breath-holding RG-fMRI was conducted with nine subjects on the compact 3 T and the fMRI reliability improvement in high susceptibility brain regions was demonstrated. Finally, reverse Fourier acquisition was applied to RG-fMRI, and its benefit was assessed by a simulation study based on the breath-holding RG-fMRI data. Main results. The temporal and spatial resolution of the multi-band RG-fMRI became feasible for whole-brain fMRI. Echo shift measurements from PSF mapping well estimated signal dropout effects in the EPI pair and were useful to further improve the RG-fMRI scheme. Breath-holding RG-fMRI demonstrated improved fMRI reliability in high susceptibility brain regions. Reverse partial Fourier acquisition omitting the late echoes could further improve the temporal or spatial resolution for RG-fMRI without noticeable signal degradation and spatial resolution loss. Significance. With the improved imaging scheme, RG-fMRI could reliably investigate the functional mechanisms of the human brain in the temporal and frontal areas suffering from susceptibility-induced functional sensitivity loss.

Adaptive dewarping of severely warped camera-captured document images based on document map generation.

Automated dewarping of camera-captured handwritten documents is a challenging research problem in Computer Vision and Pattern Recognition. Most available systems assume the shape of the camera-captured image boundaries to be anywhere between trapezoidal and octahedral, with linear distortion in areas between the boundaries for dewarping. The majority of the state-of-the-art applications successfully dewarp the simple-to-medium range geometrical distortions with partial selection of control points by a user. The proposed work implements a fully automated technique for control point detection from simple-to-complex geometrical distortions in camera-captured document images. The input image is subject to preprocessing, corner point detection, document map generation, and rendering of the de-warped document image. The proposed algorithm has been tested on five different camera-captured document datasets (one internal and four external publicly available) consisting of 958 images. Both quantitative and qualitative evaluations have been performed to test the efficacy of the proposed system. On the quantitative front, an Intersection Over Union (IoU) score of 0.92, 0.88, and 0.80 for document map generation for low-, medium-, and high-complexity datasets, respectively. Additionally, accuracies of the recognized texts, obtained from a market leading OCR engine, are utilized for quantitative comparative analysis on document images before and after the proposed enhancement. Finally, the qualitative analysis visually establishes the system's reliability by demonstrating improved readability even for severely distorted image samples.

Reconstruction of the Instantaneous Images Distorted by Surface Waves via Helmholtz–Hodge Decomposition

Imaging through water waves will cause complex geometric distortions and motion blur, which seriously affect the correct identification of an airborne scene. The current methods main rely on high-resolution video streams or a template image, which limits their applicability in real-time observation scenarios. In this paper, a novel recovery method for the instantaneous images distorted by surface waves is proposed. The method first actively projects an adaptive and adjustable structured light pattern onto the water surface for which random fluctuation will cause the image to degrade. Then, the displacement field of the feature points in the structured light image is used to estimate the motion vector field of the corresponding sampling points in the scene image. Finally, from the perspective of fluid mechanics, the distortion-free scene image is reconstructed based on the Helmholtz-Hodge Decomposition (HHD) theory. Experimental results show that our method not only effectively reduces the distortion to the image, but also significantly outperforms state-of-the-art methods in terms of computational efficiency. Moreover, we tested the real-scene sequences of a certain length to verify the stability of the algorithm.

Study on Room-Temperature Wet Oxidation of Silicon Catalyzed by Copper.

The anomalously fast growth of the silicon oxide layer at room temperature has been reported for the Cu/Si system. However, the systematical exploration of such a reaction under humidity conditions has not yet been carried out. Through one combination of the experiments and first-principle density functional theory (DFT) simulations, here, we investigate the influence of the imparted Cu atoms in Cu/Si on the oxidation of Si with the presence of H2O. The Cu addition causes the geometric distortion of the Si lattice, which alters the charge transfer to absorbed H2O and decreases its dissociation energy. This results in the experimental formation of much defective SiOx for the Cu/Si system than bare Si under humidity conditions. Furthermore, the presence of such an oxide structure and the catalytic effect of Cu provide the suitable diffusion channels and adsorption sites for the H2O transport and its dissociation. This enhances the oxidation rate of Si consequently and results in the fast growth of the oxide layer on Cu/Si at room temperature.

Geometry-Injected Image-Based Point Cloud Semantic Segmentation

Image-based methods have replicated the success from 2D domain to 3D point cloud semantic segmentation. However, when we directly apply 2D techniques to the projected pseudo-image, inherent differences between the point cloud and the image cause geometric distortion. This paper analyzes the geometric distortion between the point cloud and the pseudo-image, including truncation, dislocation, and hole. To ensure geometric fidelity, we propose the Geometry-injected Image-based point cloud semantic segmentation Network (GINet). We design a Cyclic Convolution to optimize the convolution operation, dealing with truncation. For dislocation and hole, we propose Dual Geometric Constraints, including Local Spatial Attention and Local Affinity Regularization, to incorporate the geometric information into semantic feature learning. Local Spatial Attention generates an attention map from the point coordinates to modulate the feature map before convolution. Local Affinity Regularization supervises the semantic similarity of pixels in the convolution kernel range. GINet rectifies the geometric distortion with these mechanisms while taking advantage of the successful 2D semantic segmentation methods. Quantitative and qualitative experiments on SemanticKITTI and SemanticPOSS demonstrate the effectiveness of GINet.

Diffusion-weighted Imaging of the Abdomen during a Single Breath-hold Using Simultaneous-multislice Echo-planar Imaging.

This multi-scanner study aimed to investigate the validity of single breath-hold (BH) diffusion-weighted imaging (DWI) using simultaneous-multislice (SMS) echo-planar imaging in multiple abdominal organs to enable faster acquisition and reliable quantification of apparent diffusion coefficient (ADC). SNR, geometric distortion (GD), and ADC in a phantom; the ADC in the liver, renal cortex, paraspinal muscle, spleen, and pancreas; and the signal intensity ratio of the portal vein-to-muscle (SIRPV-M) in healthy volunteers were compared between BH- and respiratory-triggered (RT) DWI with b-values of 0 and 800 s/mm2 in two different MRI scanners. The phantom study showed that the SNR of BH-DWI was significantly lower than that of the RT-DWI (P < 0.05 for both scanners), whereas the GD and ADC of BH-DWI did not differ significantly from those of the RT-DWI (P = 0.09-0.60). In the volunteer study, the scan times were 23 seconds for BH-DWI and 184±33 seconds for RT-DWI, respectively. The ADC of the liver in BH-DWI was significantly lower than that in RT-DWI (P < 0.05 for both scanners), whereas there were no significant differences in the ADCs of the renal cortex, paraspinal muscle, spleen, or pancreas between BH-DWI and RT-DWI (P = 0.07-0.86). The SIRPV-M in BH-DWI was significantly smaller than in RT-DWI (P < 0.05 for both scanners). The proposed method enables the acquisition of abdominal diffusion-weighted images in a single BH.