Contour-based Method Research Articles

Iterative Low-Poly Building Model Reconstruction from Mesh Soups Based on Contour

Existing contour-based building-reconstruction methods face the challenge of producing low-poly results. In this study, we introduce a novel iterative contour-based method to reconstruct low-poly meshes with only essential details from mesh soups. Our method focuses on two primary targets that determine the quality of the results: reduce the total number of contours, and generate compact surfaces between contours. Specifically, we implemented an iterative pipeline to gradually extract vital contours by loss and topological variance, and potential redundant contours will be removed in a post-processing procedure. Based on these vital contours, we extracted the planar primitives of buildings as references for contour refinement to obtain compact contours. The connection relationships between these contours are recovered for surface generation by a contour graph, which is constructed using multiple bipartite graphs. Then, a low-poly mesh can be generated from the contour graph using our contour-interpolation algorithm based on polyline splitting. The experiments demonstrated that our method produced satisfactory results and outperformed the previous methods.

Deep learning contour-based method for semi-automatic annotation of manufactured objects in electron microscopy images

Deep learning contour-based method for semi-automatic annotation of manufactured objects in electron microscopy images

CNN-BASED UNSUPERVISED REGISTRATION OF TIME-LAPSE MICROSCOPY IMAGE SEQUENCES

Abstract. Image registration is widely used in live cell microscopy image analysis to compensate for the cell motion. It is a challenging task as the cell is not only moving (which causes rotation and translation), but also changes its form in time making the motion non-rigid. To address this, we propose a CNN-based unsupervised method for non-rigid registration of live cell image sequences. Our network predicts both the deformation field between a pair of images of the sequence and an affine transformation matrix for the cell motion compensation. The method can be used alone or in combination with other approaches. The proposed approach was successfully applied to real live cell microscopy image sequences.We conducted an experimental comparison with existing methods including contour-based, intensity-based and a deep learning based joint denoising and registration method. In addition, we analyzed different deformation regularizers and their impact on the alignment results. In combination with contour-based method we outperformed the existing approaches in average registration accuracy for two metrics on the standard evaluation dataset.

BuildMapper: A fully learnable framework for vectorized building contour extraction

Deep learning based methods have significantly boosted the study of automatic building extraction from remote sensing images. However, delineating vectorized and regular building contours like a human does remains very challenging, due to the difficulty of the methodology, the diversity of building structures, and the imperfect imaging conditions. In this paper, we propose the first end-to-end learnable building contour extraction framework, named BuildMapper, which can directly and efficiently delineate building polygons just as a human does. BuildMapper consists of two main components: 1) a contour initialization module that generates initial building contours; and 2) a contour evolution module that performs both contour vertex deformation and reduction, which removes the need for complex empirical post-processing used in existing methods. In both components, we provide new ideas, including a learnable contour initialization method to replace the empirical methods, dynamic predicted and ground truth vertex pairing for the static vertex correspondence problem, and a lightweight encoder for vertex information extraction and aggregation, which benefit a general contour-based method; and a well-designed vertex classification head for building corner vertices detection, which casts light on direct structured building contour extraction. We also built a suitable large-scale building dataset, the WHU-Mix (vector) building dataset, to benefit the study of contour-based building extraction methods. The extensive experiments conducted on the WHU-Mix (vector) dataset, the WHU dataset, and the CrowdAI dataset verified that BuildMapper can achieve a state-of-the-art performance, with a higher mask average precision (AP) and boundary AP than both segmentation-based and contour-based methods. We also confirmed that more than 60.0/50.8% of the building polygons predicted by BuildMapper in the WHU-Mix (vector) test sets I/II, 84.2% in the WHU building test set, and 68.3% in the CrowdAI test set are on par with the manual delineation level.

Implementation of triggered kilovoltage imaging for stereotactic radiotherapy of the spine for patients with spinal fixation hardware.

Mitigation of intrafraction motion (IM) is valuable in stereotactic radiotherapy (SRT) radiotherapy where submillimeter accuracy is desired. The purpose of this study was to investigate the application of triggered kilovoltage (kV) imaging for spine SRT patients with hardware by correlating kV imaging with patient motion and summarizing implications of tolerance for IM based on calculated dose. Ten plans (33 fractions) were studied, correlating kV imaging during treatment with pre- and post-treatment cone beam computed tomography (CBCT). Images were taken at 20-degree gantry angle intervals during the arc-based treatment. The contour of the hardware with a 1mm expansion was displayed at the treatment console to manually pause treatment delivery if the hardware was visually detected outside the contour. The treatment CBCTs were compared using retrospective image registration to assess the validity of contour-based method for pausing treatment. Finally, plans were generated to estimate dose volume objective differences in case of 1mm deviation. When kV imaging during treatment was used with the 1mm contour, 100% of the post-treatment CBCTs reported consistent results. One patient in the cohort exhibited motion greater than 1mm during treatment which allowed intervention and re-setup during treatment. The average translational motion was 0.35mm. Treatment plan comparison at 1mm deviation showed little differences in calculated dose for the target and cord. Utilizing kV imaging during treatment is an effective method of assessing IM for SRT spine patients with hardware without increasing treatment time.

MOJ-DB: A new database of Arabic historical handwriting and a novel approach for subwords extraction

The digitalization of historical documents is vital to preserving their content and the historical memory of nations. Although, the results of historical Arabic handwritten text recognition and word spotting are still unsatisfactory. The increasing research efforts during the last few years are still not sufficient since handwriting recognition systems rely heavily on robust databases. In this paper, we present a new contour-based method of subword extraction from Arabic historical documents and a novel database of Arabic historical subwords MOJ-DB. The proposed method of subword extraction includes a process of touching components resolving. It proved high performance and consistency while tested on different databases and compared with other methods from the literature. The proposed database contains 560000 subwords distributed on 5600 different classes. It was built using 64 pages extracted from 10 books written in the 17th and 16th centuries. MOJ-DB database is divided into three sets; 70%,20%, and 10% for training, testing, and validation, respectively. Ground truth is established iteratively to guarantee minimal error. It includes information about the subword as of the sourcebook and page. We conducted several experiments to verify the robustness of the proposed database as well as the validity of the segmentation process . The database is freely available for the public research community. It can be used for word and subword recognition, word spotting, subword extraction, and database construction.

Evaluation of automated radiostereometric image registration in total knee arthroplasty utilizing a synthetic-based and a CT-based volumetric model.

Radiostereometic analysis (RSA) is an accurate method for rigid body pose (position and orientation) in three-dimensional space. Traditionally, RSA is based on insertion of periprosthetic tantalum markers and manual implant contour selection which limit clinically application. We propose an automated image registration technique utilizing digitally reconstructed radiographs (DRR) of computed tomography (CT) volumetric bone models (autorsa-bone) as a substitute for tantalum markers. Furthermore, an automated synthetic volumetric representation of total knee arthroplasty implant models (autorsa-volume) to improve previous silhouette-projection methods (autorsa-surface). As reference, we investigated the accuracy of implanted tantalum markers (marker) or a conventional manually contour-based method (mbrsa) for the femur and tibia. The data are presented as mean (standard deviation). The autorsa-bone method displayed similar accuracy of -0.013 (0.075) mm compared to the gold standard method (marker) of -0.013 (0.085). The autorsa-volume with 0.034 (0.106) mm did not markedly improve the autorsa-surface with 0.002 (0.129) mm, and none of these reached the mbrsa method of -0.009 (0.094) mm. In conclusion, marker-free RSA is feasible with similar accuracy as gold standard utilizing DRR and CT obtained volumetric bone models. Furthermore, utilizing synthetic generated volumetric implant models could not improve the silhouette-based method. However, with a slight loss of accuracy the autorsa methods provide a feasible automated alternative to the semi-automated method.

Detection of doxorubicin-induced cardiotoxicity using myocardial T1 and T2 relaxation times in childhood acute lymphoblastic leukemia survivors.

Doxorubicin leads to dose-dependent cardiotoxicity in childhood acute lymphoblastic leukemia (ALL) survivors. The first aim was to propose a contour-based estimation of T1 and T2 relaxation times based on the myocardial area, while our second aim was to evaluate native T1, post-gadolinium T1 and T2 relaxation time sensitivity to detect myocardial changes. A total of 84 childhood ALL survivors were stratified in regard to their prognostic risk groups: standard risk (SR), n = 20), high-risk with and without dexrazoxane (HR + DEX, n = 39 and HR, n = 25). Survivors' mean age was of 22.0 ± 6.9years, with a mean age at cancer diagnosis of 8.0 ± 5.2years. CMR acquisitions were performed on a 3T MRI system and included an ECG-gated 3(3)3(3)5 MOLLI sequence for T1 mapping and an ECG-gated T2-prepared TrueFISP sequence for T2 mapping. Myocardial contours were semi-automatically segmented using an interactive implementation of cubic Bezier curves. We found excellent repeatability between operators for native T1 (ICC = 0.91), and good repeatability between operators for post-gadolinium T1 (ICC = 0.84) and T2 (ICC = 0.79). Bland and Altman tests demonstrated a strong agreement between our contour-based method and images analyzed using the CVI42 software on the measure of native T1, post-gadolinium T1, and T2. No significant differences between survivors' prognostic risk groups in native T1 were reported, while we observed significant differences between survivors' prognostic risk groups in post-gadolinium T1 and T2. Significant differences were observed between male and female survivors. Differences between groups were also observed in partition coefficients, but no significant differences were observed between male and female survivors. The use of CMR parameters with native T1, post-gadolinium T1, and T2 allowed to show that survivors at a high-risk prognostic were more exposed to doxorubicin-related cardiotoxicity than those who were at a standard risk prognostic or who received dexrazoxane treatments.

Volumetric tumor response assessment is inefficient without overt clinical benefit compared to conventional, manual veterinary response assessment in canine nasal tumors.

Accurate assessment of tumor response to therapy is critical in guiding management of veterinary oncology patients and is most commonly performed using response evaluation criteria in solid tumors criteria. This process can be time consuming and have high intra- and interobserver variability. The primary aim of this serial measurements, secondary analysis study was to compare manual linear tumor response assessment to semi-automated, contoured response assessment in canine nasal tumors. The secondary objective was to determine if tumor measurements or clinical characteristics, such as stage, would correlate to progression-free interval. Three investigators evaluated paired CT scans of skulls of 22 dogs with nasal tumors obtained prior to and following radiation therapy. The automatically generated tumor volumes were not useful for canine nasal tumors in this study, characterized by poor intraobserver agreement between automatically generated contours and hand-adjusted contours. The radiologist's manual linear method of determining response evaluation criteria in solid tumors categorization and tumor volume is significantly faster (P<.0001) but significantly underestimates nasal tumor volume (P<.05) when compared to a contour-based method. Interobserver agreement was greater for volume determination using the contour-based method when compared to response evaluation criteria in solid tumors categorization utilizing the same method. However, response evaluation criteria in solid tumors categorization and percentage volume change were strongly correlated, providing validity to response evaluation criteria in solid tumors as a rapid method of tumor response assessment for canine nasal tumors. No clinical characteristics or tumor measurements were significantly associated with progression-free interval.

Active Contour-Based Method for Finger-Vein Image Segmentation

Suffering from uneven illumination and variation of finger position, it is still a tough challenge to effectively distinguish the vein networks and nonvenous regions in a finger-vein image. Methods based on active contour have achieved an excellent result in medical image segmentation, despite facing several challenges such as vulnerable to the initial contour and prone to local minimum. In this article, we propose a novel method which is effective for finger-vein image segmentation based on active contour. Since venous and nonvenous areas in captured finger-vein images are hard to distinguish, we design a dehazing algorithm and an edge fitting term to improve the segmentation procedure. Moreover, we employ the kernel fuzzy C-means (KFCM) algorithm to conduct the initialization, which is able to solve the problem that the active contour-based methods are susceptible to initial contours. The experimental results show that compared with latest methods, the proposed method achieves a better performance in segmenting finger-vein images and is able to improve the recognition accuracy of finger-vein identification system.

Fuzzy energy-based dual contours model for automated coronal hole detection in SDO/AIA solar disk images

The presence of coronal holes in solar disk plays an important role in influencing the space weather and generation of the solar wind. As such there lies a requirement in proper study and prediction of coronal holes occurs in the solar disk. This, in turn, arises the necessity of detection of coronal holes present in the solar disk. In this work, a Hough transformed inspired fuzzy-energy simulated dual contours-based segmentation technique has been proposed for the detection and extraction of holes in solar disk. In the proposed method Hough transform has been induced to initialize the contour for the contour-based method of segmentation. In the algorithm, two contours (active and static) have been initiated and made to evolve based on the energy function by incorporating the gray-scale intensity. Here in the work one contour is made to deform its shape while the other contour is kept static for the coronal holes detection purpose. The experiment has been carried out on few benchmark datasets and the corresponding outcomes have been compared with the results of other existing algorithms. The comparison results highlight the performance of the proposed technique in detection of coronal holes in solar disk.

Comparison of Rotor Wake Identification and Characterization Methods for the Analysis of Wake Dynamics and Evolution

Optimal wind power plant design requires understanding of wind turbine wake physics and validation of engineering wake models under wake-controlled operating conditions. In this work, we have developed and investigated several different wake identification and characterization methods for analyzing wake evolution and dynamics. The accuracy and robustness of these methods, based on Gaussian function fitting and adaptive contour identification, have been assessed by application to a large-eddy simulation data set. A new contour-based method based on downstream momentum deficit has been considered. Uncertainties arising from wake-identification errors result in characterizations of the wake expansion, recovery, and meandering motion that differ by 19% of the rotor area, 4% of the freestream, and 15% rotor diameter, respectively.

Three Dimensional Microrobot Tracking Using Learning-based System

As a promising method for robotic catheter therapeutics, a controllable wireless microrobot system with a less invasive intraoperative procedure has been presented for thrombosis surgery. The controllable wireless microrobot utilizes an electromagnetic actuator system for microrobot actuation and biplane X-ray system for microrobot imaging. We propose the new 3D tracking method of microrobot for this system. As a learning-based system, cascade classifier was adapted for real-time microrobot tracking. Combination of cascade classifier and contour-based system made accurate microrobot detection method on 2D projected X-ray images. Kalman filter interpolated lost frames, and triangulation method reconstructed 3D pose (position and orientation) from 4 endpoints of microrobot pairs. Also, the semi-automatic calibration method for bi-plane C-arm devices was proposed by using modified shortest path algorithm. To find the optimal rescaling setting, 3D tracking accuracy was investigated according to the rescaling of original intensity values. The experiment results showed a good performance with tracking errors of 2.37±9.91mm in position and 6.53±13.80° in orientation under 2200 optimal width of rescaling. If tracking evaluation is constrained under frames detected by cascade classifier, 3D tracking errors improved sincerely by 0.28±1.13mm in position and 3.48±2.89° in orientation. The optimal width of the rescaling setting needed bigger value than the mean of intensity values. The proposed tracking technique accomplished a fast frame rate of 34.72 frames/sec under OpenCL implementation of OpenCV. Learning based system is robust to the change of graphics setting since training can adapt rapidly to this change. Also, proposed framework can cooperate with the change of microrobot shape if a contour-based method is optimized. Hence, the method can be used for therapeutic millimeter- or micron-sized manipulator recognition in vascular, as well as implanted objects in the human body.

CBCT image based segmentation method for tooth pulp cavity region extraction.

A method was proposed to segment the tooth pulp cavity region in cone beam CT) images, which aimed to make the extraction process more efficient and generate more reliable results for further research. Cone beam CT images of 50 teeth from 10 patients were randomly collected with the help of Peking University Hospital of Stomatology. All slice images have a ground truth tooth pulp cavity region delineated by two doctors manually. After necessary gamma transform in pre-processing stage, three kinds of information in an image such as greyscale, neighbour average greyscale and gradient were fused to search an optimal segmentation threshold by using plane intercept histogram of reciprocal cross entropy algorithm. With the optimal threshold, binarization was conducted and the tooth pulp cavity regions in slice images can be extracted. Qualitative and quantitative analyses compared to ground truth are involved with the evaluation criterion of average non-coincidence rate ( ). Independent repeated experiments were carried out to test the stability of this segmentation method. Accurate and complete segmentation results are obtained. The proposed method reaches the lowest values in most cases and owns more competitive robustness under various interferences compared with the other popular segmentation methods like reciprocal cross entropy method, active contour-based method, region growing method and level set method. Quantitative analysis verified the effectiveness of this method. The proposed method can extract tooth pulp cavity regions from teeth efficiently. The segmentation results of this method are more accurate compared to other popular methods under different circumstances and can be used for subsequent applications.

Delineation of Carpal Bones From Hand X-Ray Images Through Prior Model, and Integration of Region-Based and Boundary-Based Segmentations

Image segmentation is critical and challenging in computer vision and medical image analysis. Despite decades of research, existing segmentation algorithms are still subject to typical segmentation problems, such as over-segmentation, under-segmentation, and non-closed and spurious edges. In this paper, taking the carpal bones from hand X-ray images as the foreground regions, we propose a segmentation approach to integrate segmentations from region-based and boundary-based methods to tackle these typical segmentation problems. First, adaptive local thresholding and adaptive Canny edge detection are explored to extract foreground regions and the edge map. Second, the integration of the edge map and foreground regions by XORing is proposed, to tackle the over-segmentation by adding a background boundary from the edge map near the carpal bone boundary so as to break the connection between the foreground and the over-segmented background, to handle under-segmentation by adding a foreground boundary from the edge map near the carpal bone boundary so as to enclose the missing foreground due to under-segmentation, and to complement non-closed edge and spurious edge from the edge map through the carpal bone regions from the local adaptive thresholding. Optionally, marker-controlled watershed segmentation or an active contour-based method is employed to refine the integrated segmentation. The segmented foreground regions are identified through exploring a prior model. The proposed approach has been validated on 30 representative X-ray hand images for non-overlapping carpal bones to yield an average Dice coefficient of 0.976 ± 0.006. The proposed method could provide a theory or tool for accurately segmenting images with discernible boundaries and non-uniform grayscale distribution both within the background and foreground.

Segmentation of large images based on super‐pixels and community detection in graphs

Image segmentation has many applications which range from machine learning to medical diagnosis. In this study, the authors propose a framework for the segmentation of images based on super-pixels and algorithms for community identification in graphs. The super-pixel pre-segmentation step reduces the number of nodes in the graph, rendering the method the ability to process large images. Moreover, community detection algorithms provide more accurate segmentation than traditional approaches based on spectral graph partition. The authors also compared their method with two algorithms: (i) the graph-based approach by Felzenszwalb and Huttenlocher and (ii) the contour-based method by Arbelaez. Results have shown that their method provides more precise segmentation and is faster than both of them.

Video Inpainting Using a Contour-Based Method in Presence of More than One Moving Objects

To restore corrupted images and video frames, a technique named inpainting or completion is used. This paper introduces an approach which is used to inpaint damaged objects in video frames. These objects are damaged whether partially or totally. In order to get to a more visually pleasant result, the moving objects and the background are separated from each other. To inpaint the stationary background, a patch-based method is used. Missing moving objects are inpainted using an object-based method with the help of a contour-based method. Presence of more than one moving object makes a problem; how to separate the goal object from other moving objects. This paper proposes a new method based on contour to solve this problem. Finally, the inpainted foreground and background are superimposed; the result is the inpainted video.

Allograft selection for distal femur through cutting contour registration.

Allograft reconstruction is an acceptable procedure for the recovery of normal anatomy after the bone tumor resection. During the past few years, several automated methods have been proposed to select the best anatomically matching allograft from the virtual donor bone bank. The surface-based automated method uses the contralateral healthy bone to obtain the normal surface shape of the diseased bone, which could achieve good matching of the defect and the selected allograft. However, the surface-based method focuses on the matching of the whole bone so that the matching of the contact surface between the allograft and the recipient bone may not be optimal. To deal with the above problem, we propose a cutting contour based method for the allograft selection. Cutting contour from the recipient bone could reflect the structural information of the defect and is seldom influenced by tumor. Thus the cutting contour can be used as the matching template to find the optimal alignment of the recipient bone and the allograft. The proposed method is validated using the data of distal femurs where bone transplantation is commonly performed. Experimental results show that the proposed method generally outperforms the surface-based method within modest extra time. Overall, our contour-based method is an effective complementary technique for allograft selection in the virtual bone bank.

Procedural modeling and visualization of multiple leaves

In this study, we propose an effective method of easy and intuitive modeling of various types of multiple leaves from plants, including flowering plants and trees, and of naturally visualizing them. This method consists of two processes. The first is the procedural modeling of leaf venation patterns. The proposed method enables modeling of the growth of leaf veins based on the information of auxin detected from a binary image of a leaf blade. Therefore, a contour-based method is designed to automatically obtain information on the target auxin, required for the growth, according to blade shapes. In addition, the growth of leaf veins is procedurally modeled by dividing the veins into main, lateral, and tertiary veins. To this end, we propose a two-level growth model. The second method we introduce is a color model based on convolution sums of divisor functions to naturally simulate the color patterns of leaf surfaces. This approach automatically defines various color patterns by creating color tables for consistent changes in the convolution sums. In addition, it synthesizes three layers consisting of noise and vein glow maps. Furthermore, we perform experiments to verify whether the proposed method is effective for generating various realistic leaves.

A novel approach for determining the minimum feed in nanochannels processing via molecular dynamics simulation

A novel approach based on molecular dynamics (MD) simulation has been proposed for the first time with the focus on quantifying the minimum feed (MF) in atomic force microscope (AFM) based nanochannel fabrication. This approach involves a coarse-to-fine criterion to determine MF so that regular nanochannel patterns can be obtained. The method is first introduced step by step and then confirmatory test is performed to demonstrate the capability of this contour-based method. MF judging studies are also performed systematically in which they vary in the aspects of scratching depth, tip angles, and tip shapes. Dislocations generation, surface quality, and scratching forces in the initial and subsequent scratches are investigated in detail. This method can overcome the drawbacks of high cost and low efficiency in experimental studies. Furthermore, our method sheds light on the manufacturing technique of nanochannels, which can help to obtain the surface morphologies with higher quality than traditional approaches.