Image Contour Research Articles

Efficient tooth gingival margin line reconstruction via adversarial learning

Gingival margin morphology plays an important role in the functional and aesthetic restoration of denture. However, this is a challenging task, mainly because there are great differences in the gingival margin morphology between different individuals and different dental positions. To address this problem, we present a deep adversarial network-driven gingival margin line reconstruction (GMLR) framework to automatically obtain the personalized gingival contour for a partially edentulous patient. Specifically, we first establish the training database by a visual distance-based orthogonal projection method to realize the bidirectional reversible mapping between three-dimensional gingival model and two-dimensional depth representation. Then, the GMLR network consists of a dual generator model and a two-scale discriminator model to avoid the loss of the gingival contour details. The proposed generator uses the global-to-local scheme to reconstruct clear gingival contour images in an end-to-end manner, while two-scale discriminator aims to guide the generator to produce a globally consistent gingival contour result with finer details. In addition, a comprehensive loss function is presented to combine gingival contour details, structure and perceptual features. Finally, we propose to reconstruct the personalized gingival line by the polygon-based node insertion and the feature line reconstruction method via the tangent constraint. Experimental results demonstrate that, under the same conditions, the proposed method outperforms recent advances on the real-world dental database. Importantly, the reconstructed missing GMLs are basically harmonious with the adjacent teeth and have enough anatomical morphology.

Internal Similarity Network for Rejoining Oracle Bone Fragment Images

Rejoining oracle bone fragments plays an import role in studying the history and culture of the Shang dynasty by its characters. However, current computer vision technology has a low accuracy in judging whether the texture of oracle bone fragment image pairs can be put back together. When rejoining fragment images, the coordinate sequence and texture features of edge pixels from original and target fragment images form a continuous symmetrical structure, so we put forward an internal similarity network (ISN) to rejoin the fragment image automatically. Firstly, an edge equidistant matching (EEM) algorithm was given to search similar coordinate sequences of edge segment pairs on the fragment image contours and to locally match the edge coordinate sequence of an oracle bone fragment image. Then, a target mask-based method was designed in order to put two images into a whole and to cut a local region image by the local matching edge. Next, we calculated a convolution feature gradient map (CFGM) of the local region image texture, and an internal similarity pooling (ISP) layer was proposed to compute the internal similarity of the convolution feature gradient map. Finally, ISN was contributed in order to evaluate a similarity score of a local region image texture and to determine whether two fragment images are a coherent whole. The experiments show that the correct judgement probability of ISN is higher than 90% in actual rejoining work and that our method searched 37 pairs of correctly rejoined oracle bone fragment images that have not been discovered by archaeologists.

Conventional Algorithms in Sports Training Based on Fractional Differential Equations

Abstract Basketball is one of the sports that people love. This paper uses fractional differential equations to perform shot visual proofreading. At the same time, we propose a visual proofreading method for the optimal shooting angle. We extract the features of the shooting trajectory according to the distribution of corner points and edge contours of the trajectory image. So far, the automatic capture method of basketball shooting trajectory based on the fractional differential equation is completed. We found that the algorithm in this paper greatly improves the player’s shooting technique through experimental simulation research.

Hybrid regularization model combining overlapping group sparse second-order total variation and nonconvex total variation

Restoring the original image from an observed noisy or blurred version is a very important issue in image processing. The variational regularization methods obtained by functional minimizing are popular and widely used for image restoration with promising accuracy, but they may suffer from limited performances due to the presence of the conflict between noise-and-blur-removing and detail-and-texture-preserving. To solve this problem, a hybrid variational regularization model is proposed to effectively reconstruct image textures and details while eliminating noise and blur. The proposed model uses an overlapping group of sparse second-order total variation (TV) as the regularizer to restore image textures and details, whereas the nonconvex TV serves as the other regularizer to preserve image edges and contours. An alternating directional multiplier method algorithm is developed to numerically solve the proposed model, where the majorization–minimization and the iterative reweighted l1 (IRL1) algorithm are used to solve the overlapping group and the nonconvex minimization subproblem, respectively. The numerical experiments validate the proposed model and algorithm. In addition, compared with several state-of-the-art image restoration models, the proposed model shows the competitive performance in terms of PSNR, SSIM, and NIQE values.

Intelligent Correction Method of Shooting Action Based on Computer Vision.

Aiming at the problem that the students' long-term use of nonstandard shooting action leads to poor basketball teaching effect, an intelligent correction method of shooting action based on computer vision is proposed. Combined with the principle of computer vision, the image acquisition model of basketball shooting action is constructed. The edge contour and adaptive feature segmentation of basketball images are detected, and abnormal shooting movements are recognized. The intelligent correction model of shooting action is constructed, and the intelligent correction of shooting action is realized. Finally, through experiments, it is proved that the visual analysis and intelligent correction effect of basketball shooting action are obviously better, and it can correct shooting action in real time and accurately.

A multi-level feature-fusion-based approach to breast histopathological image classification

Previously, convolutional neural networks mostly used deep semantic feature information obtained from several convolutions for image classification. Such deep semantic features have a larger receptive field, and the features extracted are more effective as the number of convolutions increases, which helps in the classification of targets. However, this method tends to lose the shallow local features, such as the spatial connectivity and correlation of tumor region texture and edge contours in breast histopathology images, which leads to its recognition accuracy not being high enough. To address this problem, we propose a multi-level feature fusion method for breast histopathology image classification. First, we fuse shallow features and deep semantic features by attention mechanism and convolutions. Then, a new weighted cross entropy loss function is used to deal with the misjudgment of false negative and false positive. And finally, the correlation of spatial information is used to correct the misjudgment of some patches. We have conducted experiments on our own datasets and compared with the base network Inception-ResNet-v2, which has a high accuracy. The proposed method achieves an accuracy of 99.0% and an AUC of 99.9%.

Simulation of Effect of Airfoil MH32 with Variation Taper Ratio and Angle of Attack Coefficient Lift and Drag Fixed wing Unmanned Aircraft

Nowadays, the aerospace sector is growing very rapidly. One of the newest technologies is unmanned aerial vehicle. This UAV has functions to monitor disaster, mapping, espionage and shooting target. Therefore it needs a plane that can fly fast and agile. To achieve these characteristics, one of the most important things is the design of the wings. Some of the important parameters contained in the wings are the type of airfoil, aspect ratio, wing area, taper ratio, and angle of attack. The article aims to analyze the type of airfoil MH32 as well as the effect of the parameter taper ratio with variations of 0.2, 0.4, 0.6 in variations of angle of attack 0 °, 3 °, 6 °, 12 ° and 15 ° to the value of coefficient of lift and coefficient of drag. The method used in this research is experimental with a computational approach using a computer, the advantage of this method is that it does not need a real plane shape. The type of simulation used is Computational Fluid Dynamic (CFD) found in Ansys Fluent. From the simulation, value of coefficient of lift, coefficient of drag, and image of pressure contour and streamline velocity were obtained. All the data was processed and analyzed, then the result is that the taper ratio 0.4 has the highest lift to drag ratio of 19,417. It means that it has the highest value of the coefficient of lift and has the lowest coefficient of drag. These simulated results are validated with experimental from UIUC (University of Illinois at Urbana-Champaign) 1996. The conclusion of this study is that the smaller the taper ratio, the greater the value of the lift coefficient. Then increase the angle of attack to make the value of the lift coefficient is also getting bigger.

Oil and gas casing 3D visualization technology based on multi-frequency ultrasonic scanning

This technology obtains the casing contour and inner wall information by using multi-frequency ultrasonic scanning with more abundant data than traditional single frequency ultrasonic testing. On the basis of high-precision measurement and imaging obtained by multi-frequency ultrasonic scanning equipment, the casing contour features and image features are combined. The radial damage and axial damage of oil and gas well casing are considered at the same time. It can effectively improve the visualization and identification of casing damage area of oil and gas wells in borehole. Firstly, according to the conventional oil and gas well casing damage characteristics, the mapping relationship between ultrasonic scanning signal and damage characteristics is proposed. Then, based on the oil and gas well casing visualization of profile and surface features, a 3 D visualization model of oil and gas well casing is constructed, and a 3 D reconstruction system of oil and gas well casing is formed with simultaneous consideration of profile features and image features. Finally, through the verification and analysis of the technical method combined with the actual project, the feasibility and intuitiveness of the technology are verified. This technology can greatly improve the detection efficiency and precision of oil and gas well casing in borehole.

DETECTION OF SIGNAL TO NOISE RATIO FROM IMAGE CONTOUR -A MATLAB APPLICATION

Image is a combination of thousand number of pixels which is an integral unit of image , every pixel has three primary colors Red,Green,Blue. Contour means border detection of black and white image. Here in this paper our main aim is to reduce noise from black and white image after converting it from color image. Several noises are there, but we have used only few of them as an application to show you the procedure. Here we have added noise then applied filtering method to generate the contour and compared it with original contour of a normal noise free image. In each case original image has been displayed in result section.]

An ontogenetic study of Eospirigerina putilla (Brachiopoda) surviving the Late Ordovician mass extinction

The ontogeny of the brachiopod can be reflected by the shell outline, size, and their interconnections. As a representative early atrypid brachiopod group of the Edgewood-Cathay Fauna, the genus Eospirigerina survived the Late Ordovician mass extinction (LOME). Abundant E. putilla specimens were collected from the “Wulipo Bed” limestone (upper Hirnantian, Ordovician). As a typical Eospirigerina dominated Edgewood-Cathay Fauna from the upper Hirnantian (Ordovician) of northeastern Yunnan, China, the quantitative ontogenetic study of E. putilla can provide a better understanding of its palaeoecology. Using the image contour recognition, we develop an automated measuring tool, test its robustness, and measure 554 complete and silicified specimens of E. putilla. An abnormal palaeoenvironment that the E. putilla population inhabited in is suggested by the high mortality of small individuals indicated by the size-frequency histogram and survivorship curve. Using quadratic polynomial regression, the negative allometric pattern of the shell length to width in the population is recognized. Using geometric morphometrics with semi-landmarks for 51 specimens from the population, the ontogenic trends are mapped by PCA with thin-plate splines, in which the heterochronic shifts may occur from an elongate shell with relatively larger ventral cardinal area and delthyrium to wider outline and smaller beak. Such heterochronic development is possibly caused by the unstable and stressful environment immediately after the LOME.

Dance Fitness Action Recognition Method Based on Contour Image Spatial Frequency Domain Features and Few-Shot Learning.

In recent years, the research work of artificial intelligence technology has progressed rapidly, and various classic Few-Shot learning models have achieved unprecedented success in many artificial intelligence application fields. These include face recognition, object classification detection and tracking, speech recognition, and natural language processing, which greatly facilitate our lives. This paper aims to identify dance fitness movements based on contour image spatial frequency domain features and Few-Shot learning technology. This paper proposes a Few-Shot learning method based on contrastive average loss for Few-Shot learning. This method makes the learned model more representative by improving the loss function and performing a normalization process, and it proposes a feature extraction algorithm that combines improved LBP and HOG for action recognition technology. The experimental results show that the recognition accuracy of the algorithm in this paper is 93.10%, 90.30%, and 92.70% for walking, opening hands, and running, respectively. This illustrates the effectiveness of the fusion feature algorithm.

Contrast-enhanced CT based radiomics in the preoperative prediction of perineural invasion for patients with gastric cancer

PurposeTo investigate the feasibility and accuracy of radiomics models based on contrast-enhanced CT (CECT) in the prediction of perineural invasion (PNI), so as to stratify high-risk recurrence and improve the management of patients with gastric cancer (GC) preoperatively. MethodsTotal of 154 GC patients underwent D2 lymph node dissection with pathologically confirmed GC and preoperative CECT from an open-label, investigator-sponsored trial (NCT01711242) were enrolled. Radiomics features were extracted from contoured images and selected using Mann-Whitney U test and the least absolute shrinkage and selection operator (LASSO) after inter-class correlation coefficient (ICC) analysis. Models based on radiomics features (R), clinical factors (C) and combined parameters (R + C) were built and evaluated using Support Vector Machine (SVM) and logistic regression to predict the PNI for patients with GC preoperatively. ResultsTotal of 11 radiomics features were selected for final analysis, along with two clinical factors. The area under curve (AUC) of models based on R, C, and R + C with logistic regression and SVM were 0.77 vs. 0.83, 0.71 vs.0.70, 0.86 vs. 0.90, and 0.73 vs.0.80, 0.62 vs. 0.64, 0.77 vs. 0.82 in the training and testing cohorts, respectively. SVM(R + C) achieved a best AUC of 0.82(0.69–0.94) in the test cohorts with a sensitivity, specificity and accuracy of 0.63, 0.91, and 0.77, respectively. ConclusionsThe performance of these models indicates that radiomics features alone or combined with clinical factors provide a feasible way to classify patients preoperatively and improve the management of patients with GC.

Enhancing Precision with an Ensemble Generative Adversarial Network for Steel Surface Defect Detectors (EnsGAN-SDD).

Defects are the primary problem affecting steel product quality in the steel industry. The specific challenges in developing detect defectors involve the vagueness and tiny size of defects. To solve these problems, we propose incorporating super-resolution technique, sequential feature pyramid network, and boundary localization. Initially, the ensemble of enhanced super-resolution generative adversarial networks (ESRGAN) was proposed for the preprocessing stage to generate a more detailed contour of the original steel image. Next, in the detector section, the latest state-of-the-art feature pyramid network, known as De-tectoRS, utilized the recursive feature pyramid network technique to extract deeper multi-scale steel features by learning the feedback from the sequential feature pyramid network. Finally, Side-Aware Boundary Localization was used to precisely generate the output prediction of the defect detectors. We named our approach EnsGAN-SDD. Extensive experimental studies showed that the proposed methods improved the defect detector’s performance, which also surpassed the accuracy of state-of-the-art methods. Moreover, the proposed EnsGAN achieved better performance and effectiveness in processing time compared with the original ESRGAN. We believe our innovation could significantly contribute to improved production quality in the steel industry.

General Image Fast Encryption Algorithm for Deep Learning Compression and Reconstruction

Aiming at the problems of long time-consuming in image compression encryption and color distortion of the decrypted image, a fast and safe general image encryption algorithm is proposed. The compression network uses bilinear interpolation and a fully connected layer for compression preprocessing to prevent the loss of color information. Convolution layer improves compression rate and reduces time complexity in this algorithm. In the encryption part, the chaotic sequence dynamically selects the pixel block and the pixel points in the block combining the XOR operation to perform pixel diffusion, which can improve the randomness of the algorithm. In the improved bilinear convolution neural network, bilinear and convolutional layers are used to obtain the image contour features. And the fully connected layer obtains color information for image reconstruction. This algorithm realizes the integration of compression, encryption, decryption and restoration of grayscale and RGB format color images. The experimental results show that the various encryption indexes of this algorithm are close to ideal values. It has good encryption security and anti-attack ability. Moreover, the encryption time is greatly shortened. On the 500 test set (BSD500) commonly used in image processing, when the sampling rate is 0.25, 0.10, 0.04 and 0.01, the peak signal-to-noise ratio can reach to 29.01 dB, 25.69 dB, 23.75 dB and 21.45 dB, which is better than FCLBCNN. This encryption algorithm effectively solves the color distortion problem of reconstructed images and has better encryption effects and wider applicability.

X-ray Image Enhancement Based on Nonsubsampled Shearlet Transform and Gradient Domain Guided Filtering.

In this paper, we propose an image enhancement algorithm combining non-subsampled shearlet transform and gradient-domain guided filtering to address the problems of low resolution, noise amplification, missing details, and weak edge gradient retention in the X-ray image enhancement process. First, we decompose histogram equalization and nonsubsampled shearlet transform to the original image. We get a low-frequency sub-band and several high-frequency sub-bands. Adaptive gamma correction with weighting distribution is used for the low-frequency sub-band to highlight image contour information and improve the overall contrast of the image. The gradient-domain guided filtering is conducted for the high-frequency sub-bands to suppress image noise and highlight detail and edge information. Finally, we reconstruct all the effectively processed sub-bands by the inverse non-subsampled shearlet transform and obtain the final enhanced image. The experimental results show that the proposed algorithm has good results in X-ray image enhancement, and its objective index also has evident advantages over some classical algorithms.

Deep Learning for Reaction-Diffusion Glioma Growth Modeling: Towards a Fully Personalized Model?

Simple SummaryMathematical tumor growth models have been proposed for decades to capture the growth of gliomas, an aggressive form of brain tumor. However, the estimation of the tumor cell-density distribution at diagnosis and model parameters from partial observations provided by magnetic resonance imaging are ill-posed problems. In this work, we propose a deep learning-based approach to address these problems. 1200 synthetic tumors are first generated using the mathematical model over brain geometries of 6 volunteers. Two deep convolutional neural networks are then trained to (i) reconstruct a whole tumor cell-density distribution and (ii) evaluate the model parameters from partial observations provided in the form of threshold-like imaging contours, with state-of-the-art results. From the estimated cell-density distribution and parameter values, the spatio-temporal evolution of the tumor can ultimately be accurately captured by the mathematical model. Such an approach could be of great interest for glioma characterization and therapy planning.Reaction-diffusion models have been proposed for decades to capture the growth of gliomas, the most common primary brain tumors. However, ill-posedness of the initialization at diagnosis time and parameter estimation of such models have restrained their clinical use as a personalized predictive tool. In this work, we investigate the ability of deep convolutional neural networks (DCNNs) to address commonly encountered pitfalls in the field. Based on 1200 synthetic tumors grown over real brain geometries derived from magnetic resonance (MR) data of six healthy subjects, we demonstrate the ability of DCNNs to reconstruct a whole tumor cell-density distribution from only two imaging contours at a single time point. With an additional imaging contour extracted at a prior time point, we also demonstrate the ability of DCNNs to accurately estimate the individual diffusivity and proliferation parameters of the model. From this knowledge, the spatio-temporal evolution of the tumor cell-density distribution at later time points can ultimately be precisely captured using the model. We finally show the applicability of our approach to MR data of a real glioblastoma patient. This approach may open the perspective of a clinical application of reaction-diffusion growth models for tumor prognosis and treatment planning.

A mathematical model of PCNN for image fusion with non-sampled contourlet transform

Abstract Non-sampled contourlet transform (NSCT) is a kind of non-down sampling image transformation, without spectrum aliasing, and the high-frequency region component can be further decomposed into various direction information, which has a good expression of image details. Therefore, this paper proposes an image fusion technology based on NSCT. Considering the different characteristics of low-frequency and high-frequency region components, the PCNN parallel method and ‘golden section method’ are used as double fusion rules, respectively in high- and low-frequency regions, whichperform the merge operation on the low area component. Experiments show that this algorithm has great advantages in preserving the details of image contour, texture and edge.

Deformable image registration with attention-guided fusion of multi-scale deformation fields

Deformable medical image registration plays a crucial role in theoretical research and clinical application. Traditional methods suffer from low registration accuracy and efficiency. Recent deep learning-based methods have made significant progresses, especially those weakly supervised by anatomical segmentations. However, the performance still needs further improvement, especially for images with large deformations. This work proposes a novel deformable image registration method based on an attention-guided fusion of multi-scale deformation fields. Specifically, we adopt a separately trained segmentation network to segment the regions of interest to remove the interference from the uninterested areas. Then, we construct a novel dense registration network to predict the deformation fields of multiple scales and combine them for final registration through an attention-weighted field fusion process. The proposed contour loss and image structural similarity index (SSIM) based loss further enhance the model training through regularization. Compared to the state-of-the-art methods on three benchmark datasets, our method has achieved significant performance improvement in terms of the average Dice similarity score (DSC), Hausdorff distance (HD), Average symmetric surface distance (ASSD), and Jacobian coefficient (JAC). For example, the improvements on the SHEN dataset are 0.014, 5.134, 0.559, and 359.936, respectively.

A nonconvex hbox{TV}_q-l_1 regularization model and the ADMM based algorithm

The total variation (TV) regularization with l_1 fidelity is a popular method to restore the image contaminated by salt and pepper noise, but it often suffers from limited performance in edge-preserving. To solve this problem, we propose a nonconvex hbox{TV}_q-l_1 regularization model in this paper, which utilizes a nonconvex l_q-norm (0<q<1) defined in total variation (TV) domain (called hbox{TV}_q regularizer) to regularize the restoration, and uses l_1 fidelity to measure the noise. Compared to the traditional TV model, the proposed model can more effectively preserve edges and contours since it provides a more sparse representation of the restoration in TV domain. An alternating direction method of multipliers (ADMM) combining with majorization-minimization (MM) scheme and proximity operator is introduced to numerically solve the proposed model. In particular, a sufficient condition for the convergence of the proposed algorithm is provided. Numerical results validate the proposed model and algorithm, which can effectively remove salt and pepper noise while preserving image edges and contours. In addition, compared with several state-of-the-art variational regularization models, the proposed model shows the best performance in terms of peak signal to noise ratio (PSNR) and mean structural similarity index (MSSIM). We can obtain about 0.5 dB PSNR and 0.06 MSSIM improvements against all compared models.

Determining the limiting conditions of sampling interval and sampling angle for laser reflective tomography imaging in sensing targets with typical shapes

Laser reflective tomography imaging (LRTI) is unique in the remote sensing of space targets because the resolution is independent of the distance. As it is usually difficult to obtain the 360-degree of reflectance projections, the estimation of the proper sampling interval and sampling angle becomes a key problem. In this paper, we conducted an LRTI experiment with a distance of 0.98-km and a wavelength of 1064 nm, and constructed three targets with typical shapes, namely, planar target, plane combination target, and closed-surface target. By comparing the evaluation indexes of retrieved images, the following was found: (1) When the sampling interval exceeds the maximum sampling interval derived by the Nyquist sampling law, the quality of reconstructed images deteriorates rapidly; (2) When the sampling angle is greater than 70 degrees and 90 degrees, the image of planar and plane combination target can be reconstructed excellently, respectively. However, contour image reconstruction requires full angle projection for closed-surface target; (3) When the sampling angle is fixed, the quality of reconstructed image is best for the vertical detection. This paper determines the limiting conditions of the sampling interval and sampling angle, which are of great practical significance in guiding the space-borne LRTI in sensing the space target with a long distance.