Cut Algorithm Research Articles

Research on Improved Image Segmentation Algorithm Based on GrabCut

The classic interactive image segmentation algorithm GrabCut achieves segmentation through iterative optimization. However, GrabCut requires multiple iterations, resulting in slower performance. Moreover, relying solely on a rectangular bounding box can sometimes lead to inaccuracies, especially when dealing with complex shapes or intricate object boundaries. To address these issues in GrabCut, an improvement is introduced by incorporating appearance overlap terms to optimize segmentation energy function, thereby achieving optimal segmentation results in a single iteration. This enhancement significantly reduces computational costs while improving the overall segmentation speed without compromising accuracy. Additionally, users can directly provide seed points on the image to more accurately indicate foreground and background regions, rather than relying solely on a bounding box. This interactive approach not only enhances the algorithm’s ability to accurately segment complex objects but also simplifies the user experience. We evaluate the experimental results through qualitative and quantitative analysis. In qualitative analysis, improvements in segmentation accuracy are visibly demonstrated through segmented images and residual segmentation results. In quantitative analysis, the improved algorithm outperforms GrabCut and min_cut algorithms in processing speed. When dealing with scenes where complex objects or foreground objects are very similar to the background, the improved algorithm will display more stable segmentation results.

Designing a resilient supply chain network: A multi-objective data-driven distributionally robust optimization method

Uncertainty of supply chain disruption poses a significant challenge to decision-making in many real-life problems. In this paper, a new multi-objective data-driven distributionally robust optimization (MDDRO) model for the resilient supply chain network (RSCN) design problem under disruption scenario is developed, which includes minimizing the total cost, carbon emissions, and delivery time. In the context of supply chain disruption, it is important self-evidently that products can be supplied normally and the practical demand can be met. In handling the partial probability distribution information of the considered uncertain demand, this paper uses a data-driven Wasserstein-Moment ambiguity set (WMAS), which incorporate the Wasserstein metric and Moment information, and a robust counterpart to transform the developed model into a tractable approximation form. The finite-sample performance guarantee of the optimal solution of MDDRO model with Wasserstein-Moment ambiguous chance constraint is given. An accelerated Branch and cut algorithm (BCA) is constructed to solve the MDDRO model. Finally, through the investigation of a real-life case and sensitivity analysis of key parameters, some managerial insights are put forward.

Quadratic p-Median Problem: A Bender’s Decomposition and a Meta-Heuristic Local-Based Approach

In this paper, the quadratic p-median optimization problem is discussed, where the goal is to connect users to a selected group of facilities (emergency services, telecommunications servers, healthcare facilities) at the lowest possible cost. The problem is aimed at minimizing the cost of connecting these selected facilities. The costs are symmetric, meaning connecting two different points is the same in both directions. This problem extends the traditional p-median problem, a combinatorial problem used in various fields like facility location, network design, transportation, supply chain networks, emergency services, healthcare, and education planning. Surprisingly, the quadratic version has not been thoroughly considered in the literature. The paper highlights the formulation of two mixed-integer quadratic programming models to find optimal solutions to this problem. One model is a classic formulation, and the other is based on set cover theory. Linear versions and Bender’s decomposition formulations for each model are also derived. A Bender’s decomposition is solved using an algorithm that adds constraints during each iteration to improve the solution. Lazy constraints in the Gurobi solver’s branch and cut algorithm are dynamically added whenever a mixed-integer programming solution is found. Additionally, an efficient local search meta-heuristic is proposed that usually finds optimal solutions for tested instances. Challenging instances with up to 60 facilities and 2000 users are successfully solved. Our results show that Bender’s models with lazy constraints are the most effective for Euclidean and random test cases, achieving optimal solutions in less CPU time. The meta-heuristic also finds near-optimal solutions rapidly for these cases.

Deep Learning-Based Workflow for Bone Segmentation and 3D Modeling in Cone-Beam CT Orthopedic Imaging

In this study, a deep learning-based workflow designed for the segmentation and 3D modeling of bones in cone beam computed tomography (CBCT) orthopedic imaging is presented. This workflow uses a convolutional neural network (CNN), specifically a U-Net architecture, to perform precise bone segmentation even in challenging anatomical regions such as limbs, joints, and extremities, where bone boundaries are less distinct and densities are highly variable. The effectiveness of the proposed workflow was evaluated by comparing the generated 3D models against those obtained through other segmentation methods, including SegNet, binary thresholding, and graph cut algorithms. The accuracy of these models was quantitatively assessed using the Jaccard index, the Dice coefficient, and the Hausdorff distance metrics. The results indicate that the U-Net-based segmentation consistently outperforms other techniques, producing more accurate and reliable 3D bone models. The user interface developed for this workflow facilitates intuitive visualization and manipulation of the 3D models, enhancing the usability and effectiveness of the segmentation process in both clinical and research settings. The findings suggest that the proposed deep learning-based workflow holds significant potential for improving the accuracy of bone segmentation and the quality of 3D models derived from CBCT scans, contributing to better diagnostic and pre-surgical planning outcomes in orthopedic practice.

GCphase: an SNP phasing method using a graph partition and error correction algorithm

BackgroundThe utilization of long reads for single nucleotide polymorphism (SNP) phasing has become popular, providing substantial support for research on human diseases and genetic studies in animals and plants. However, due to the complexity of the linkage relationships between SNP loci and sequencing errors in the reads, the recent methods still cannot yield satisfactory results.ResultsIn this study, we present a graph-based algorithm, GCphase, which utilizes the minimum cut algorithm to perform phasing. First, based on alignment between long reads and the reference genome, GCphase filters out ambiguous SNP sites and useless read information. Second, GCphase constructs a graph in which a vertex represents alleles of an SNP locus and each edge represents the presence of read support; moreover, GCphase adopts a graph minimum-cut algorithm to phase the SNPs. Next, GCpahse uses two error correction steps to refine the phasing results obtained from the previous step, effectively reducing the error rate. Finally, GCphase obtains the phase block. GCphase was compared to three other methods, WhatsHap, HapCUT2, and LongPhase, on the Nanopore and PacBio long-read datasets. The code is available from https://github.com/baimawjy/GCphase.ConclusionsExperimental results show that GCphase under different sequencing depths of different data has the least number of switch errors and the highest accuracy compared with other methods.

A branch and cut algorithm to optimize a weighted sum-of-ratios in multiobjective mixed-integer fractional programming

AbstractMultiobjective linear fractional programming is useful to model multiobjective problems where all or some of the objective functions are a ratio or proportion of one linear/affine function to another linear/affine function. In practice, many of such problems include integer variables. If the weighted-sum scalarization is used to compute efficient solutions to the multiobjective problem, then the scalar problem to be solved for each weight vector turns out to be a weighted sum-of-ratios. There are several algorithms reported in the literature to optimize weighted sum-of-ratios, but almost all of them cannot deal with integer variables. In this paper we propose a Branch & Cut algorithm to optimize weighted-sums of the objective functions in multiobjective mixed integer fractional programming (MOMIFP). Several theoretical properties that support the algorithm are presented and proved. Computational experiments with randomly generated general problems are presented and discussed, which show that the algorithm is able to deal with practical MOMIFP problems.

A mathematical programming approach to export pathway planning of distributed hydrogen production in offshore wind farm

Hydrogen production is a vital development trend to improve the economics and penetration rate of offshore wind farms (OWFs), and distributed hydrogen production (DHP) is a preferred solution for deep and far sea OWFs without expensive submarine cables and offshore substations. The export pathway of OWF-DHP consists of collection pipelines, transmission pipelines, and offshore compressor stations. In this paper, mathematical programming is introduced to explore the export pathway planning problem of OWF-DHP. Firstly, the area of OWF is discretized into multiple grids with the center of the grids being the candidate locations of the offshore compressor station. Then, a binary integer quadratic programming problem is established to optimize both the offshore compressor station location and pipeline construction with different topologies. Further, the mathematical model is solved by the branch and cut algorithm integrated with the proposed dimension reduction methods. Finally, the effectiveness of the proposed export pathway planning approach is verified by the actual data of Baltic Eagle OWF in Germany, which would support the construction of the OWF-DHP project.

Octagonal and hexadecagonal cut algorithms for finding the convex hull of finite sets with linear time complexity

This paper is devoted to an octagonal cut algorithm and a hexadecagonal cut algorithm for finding the convex hull of n points in R2, where some octagon and hexadecagon are used for discarding most of the given points interior to these polygons. In this way, the scope of the given problem can be reduced significantly. In particular, the convex hull of n points distributed bleast-bmost-boundedly in some rectangle can be determined with the complexity O(n). Computational experiments demonstrate that our algorithms outperform the Quickhull algorithm by a significant factor of up to 47 times when applied to the tested data sets. The speedup compared to the CGAL library is even more pronounced.

Rethinking the implementation and application of the Benczur-Karger minimum cuts algorithm

Rethinking the implementation and application of the Benczur-Karger minimum cuts algorithm

Minimizing the total travel distance for the locker-based drone delivery: A branch-and-cut-based method

This article investigates the problem of minimizing the total travel distance in locker-based drone delivery, where the roofs of lockers are reused as parking platforms for drones. It is a drone routing and parking hybrid problem with modeling challenges. We find the sufficient and necessary conditions for feasible solutions and transform the original problem into a scale-tractable one. Subsequently, we propose a compact lower-bound formulation for the transformed problem and prove the total unimodality of the coefficient matrix. Furthermore, we develop a two-stage method in which a branch and cut algorithm solves the transformed problem and a heuristic constructs practical schedules for the original problem. Simulated tests demonstrate that the method can solve each simulated instance within one second. Random tests reveal that the method can efficiently solve instances with 1000 sites and 1500 tasks within an acceptable CPU time. A sensitivity analysis indicates that the complexity arising from routing flexibility is greater than that arising from parking flexibility.

Solving the guaranteed-service time inventory model for real-world supply chains by implementing it in commercial optimisers

The guaranteed service time inventory (GSTI) model aims to satisfy customers’ demand in an assured time. As multi-echelon supply chains (SC) grow in size and complexity, there is a need to develop exact algorithms to compute the amount of safety stock to deliver products to customers in the guaranteed service time. This work proposed an algorithm to minimise the safety stock in real–world SCs in minutes. The application reads the data set provided in [31]; then a continuous initial solution is computed in seconds using the software library (IPOpt); finally, that solution is used as the initial solution to run the branch–and–cut (B&C) algorithm implemented in a state-of–the–art commercial solver. In the proposed application, the GSTI model is modified to be implemented in commercial solvers when the demand is normally distributed. The reader can download the application’s source code from [24] to analyse the results of the 38 instances. The application computes an integer solution to each of the 38 SCs; in the worst case, it takes 150 min to find the solution. Seventeen instances are solved optimally, and the worst gap between the actual and best solution is about 24% in three instances. The biggest instance is solved in less than 10 min, but other smaller ones are solved in a longer time because of the echelons’ structure (degree and depth). Thus, the time to compute a solution does not depend on the size of the SC but on its structure. The findings indicate that by using a state-of–the–art commercial solver (based on the B&C method) and running it with powerful computer capabilities, real–world SCs can be solved with techniques that return optimal solutions.

Research on Multimodal Generative Adversarial Networks in the Framework of Deep Learning

This project aims to align facial and vocal characteristics within a closely related common space through the construction of multi-modal generative adversarial networks (GANs). The project proposes a multi-modal approach grounded in visual perception, utilizing the Graph Cut algorithm to align feature components with the image features of each corresponding local context, thereby achieving adaptability in multi-modal information. To enhance the speed and accuracy of the modeling process, a regional attention strategy is integrated. Experimental results demonstrate that the proposed algorithm enhances the accuracy of image recognition tasks.

A deep learning model for the localization and extraction of brain tumors from MR images using YOLOv7 and grab cut algorithm.

Brain tumors are a common disease that affects millions of people worldwide. Considering the severity of brain tumors (BT), it is important to diagnose the disease in its early stages. With advancements in the diagnostic process, Magnetic Resonance Imaging (MRI) has been extensively used in disease detection. However, the accurate identification of BT is a complex task, and conventional techniques are not sufficiently robust to localize and extract tumors in MRI images. Therefore, in this study, we used a deep learning model combined with a segmentation algorithm to localize and extract tumors from MR images. This paper presents a Deep Learning (DL)-based You Look Only Once (YOLOv7) model in combination with the Grab Cut algorithm to extract the foreground of the tumor image to enhance the detection process. YOLOv7 is used to localize the tumor region, and the Grab Cut algorithm is used to extract the tumor from the localized region. The performance of the YOLOv7 model with and without the Grab Cut algorithm is evaluated. The results show that the proposed approach outperforms other techniques, such as hybrid CNN-SVM, YOLOv5, and YOLOv6, in terms of accuracy, precision, recall, specificity, and F1 score. Our results show that the proposed technique achieves a high dice score between tumor-extracted images and ground truth images. The findings show that the performance of the YOLOv7 model is improved by the inclusion of the Grab Cut algorithm compared to the performance of the model without the algorithm.

Setting the regularization coefficient based on image energy in image segmentation using kernel graph cut algorithm

Setting the regularization coefficient based on image energy in image segmentation using kernel graph cut algorithm

Demand-adapted train timetabling with coupling-decoupling operations on a bidirectional intercity railway line

Many factors need to be considered when designing the timetable of intercity railway lines, where the passenger demand is variable and unbalanced along time in both directions of the line. This paper introduces a new multi-objective nonlinear integrated optimization model for designing full-day train timetables incorporating coupling-decoupling operations and rolling stock assignment on a bidirectional railway line. The model explicitly considers train capacity constraints and oversaturation while minimizing the total passenger waiting time and operating costs. To solve the problem, a hybrid algorithm governed by a genetic algorithm is proposed. Before evaluating the fitness of each individual, to complete the definition of each chromosome, a truncated branch and cut algorithm is used to solve a capacity and train unit allocation subproblem. A good-quality initial population is partially generated using the spatiotemporal synchronous coupling algorithm. The proposed approach is applied to a real case using the Shanghai-Hangzhou intercity railway line. The results of different experiments show the effectiveness of the model and algorithm, both in terms of passenger convenience and cost savings.

Deep learning-based segmentation of breast masses using convolutional neural networks

Automatic breast tumor segmentation based on convolutional neural networks (CNNs) is significant for the diagnosis and monitoring of breast cancers. CNNs have become an important method for early diagnosis of breast cancer and, thus, can help decrease the mortality rate. In order to assist medical professionals in breast cancer investigation a computerized system based on two encoder-decoder architectures for breast tumor segmentation has been developed. Two pre-trained DeepLabV3+ and U-Net models are proposed. The encoder generates a high-dimensional feature vector while the decoder analyses the low-resolution feature vector provided by the encoder and generates a semantic segmentation mask. Semantic segmentation based on deep learning techniques can overcome the limitations of traditional algorithms. To assess the efficiency of breast ultrasound image segmentation, we compare the segmentation results provided by CNNs against the Local Graph Cut technique (a semi-automatic segmentation method) in the Image Segmenter application. The output segmentation results have been evaluated by using the Dice similarity coefficient that compares the ground truth images provided by the specialists against the predicted segmentation results provided by the CNNs and Local Graph Cut algorithm. The proposed approach is validated on 780 breast ultrasonographic images of the BUSI public database of which 437 are benign and 210 are malignant. The BUSI database provides classification (benign or malignant) labels for ground truth in binary mask images. The average Dice scores computed between the ground truth images against CNNs were as follows: 0.9360 (malignant) and 0.9325 (benign) for the DeepLabV3+ architecture and of 0.6251 (malignant) and 0.6252 (benign) for the U-Net, respectively. When the segmentation results provided by CNNs were compared with the Local Graph Cut segmented images, the Dice scores were 0.9377 (malignant) and 0.9204 (benign) for DeepLabV3+ architecture and 0.6115 (malignant) and 0.6119 (benign) for U-Net, respectively. The results show that the DeepLabV3+ has significantly better segmentation performance and outperforms the U-Net network.

Impact of 3D printing technology on the field of apparel design in the framework of intellectual property law

Abstract 3D printing technology, with the development of science and technology, the application in the field of clothing can not be counted. In this paper, based on the design technology route of 3D printing clothing, we first establish parametric 3D three-dimensional clothing. After determining the constraints of the clothing curve, we generate the clothing parametric surface by interpolation and then adjust the horizontal mesh to generate the three-dimensional clothing model. The Gragh Cut algorithm is used to segment the garment image and extract the 3D garment contour features. Finally, the exploration of the aesthetic implication and modeling characteristics of 3D printed garments is launched, and examples analyze the aesthetic characteristics and comfort of 3D printed garments under different materials according to the characteristics of local decoration, functionality, parameterization, and so on. The impact of 3D printing technology on clothing design within the framework of intellectual property law is also being explored. The results show that the thermal comfort range of 3D printed garments is 24.1~26.6°C, and 3D printing materials with larger TCR can better regulate the comfort of garment design. This study explores parametric garment design using 3D printing, which is innovative.

Research on the digital protection and three-dimensional modeling technology of ancient buildings

Abstract The starting point of ancient architecture digitization and 3D reconstruction research is data acquisition. Thus, this paper mainly analyzes the processing of 3D laser scanning data and the construction accuracy of 3D reconstruction models of ancient buildings based on point cloud data. This paper discusses the basic theory of point cloud data and the preprocessing of point cloud data, including point cloud splicing, point cloud denoising, point cloud streamlining, point cloud segmentation, and other methods and applicability are discussed in detail. The boundary extraction algorithm based on RANSAC and the graph cut algorithm are utilized to obtain the main frame line of the building, and a proposed method for reconstruction based on multi-view projection is proposed. Classify laser point cloud samples from ancient buildings, calculate each wall color’s R, G, and B values, and obtain preliminary classifications of laser point cloud data categories. The RANSAC algorithm was used to extract the point cloud data plane extraction peak of the ancient tower building, combined with the three-dimensional modeling coordinate difference of the test points, to analyze the accuracy of the three-dimensional modeling technology of ancient buildings in this paper. The number of plane extraction points of the RANSAC algorithm is 9504, and the standard deviation is 0.0505, which is close to 0. The results are more accurate, and the extraction effect has a certain degree of superiority. The plane coordinate deviation of the reconstruction model of the ancient tower is mainly concentrated in the range of 0.10~0.40m, and the individual coordinate difference is more than 0.10m. The errors in the x -direction and y -direction are ±0.18m and ±0.23m, respectively, and it can be seen from the results of the error calculation that the three-dimensional reconstruction plan of the building proposed in this paper can complete the reconstruction of the three-dimensional model of the building with a high degree of accuracy.

SPATIAL PARTITION FOR HETEROGENEOUS CITY NETWORKS COMPOSED OF FACTORS THAT INFLUENCE THE DISTRIBUTION OF THE MACROSCOPIC FUNDAMENTAL DIAGRAM

Using a Macroscopic Fundamental Diagram (MFD) to implement partition control is effective in improving mobility in heterogeneous city networks. As one of the most complex issues in partition control, accurate sub-region partition is critical for control effectiveness. Current partition methods focus on the link density and precondition of existing MFD and disregard the factors that influence MFD distribution. To overcome this drawback, this study uses the characteristic value of the link and the intersection connected to the link as the analysis object and proposes an MFD sub-region partitioning method for large-scale networks. Firstly, the influences of road state parameters on MFD distribution are classified into traffic flow parameters, network physical properties, network operation mechanisms and emergencies. Simulation experiments are conducted to determine the degree to which these classifications affect MFD distribution. Secondly, a partition method combined with the link density and influence parameters of MFD is developed. The method is used for a preliminarily division of a road network through Minimum Spanning Tree (MST) and depth partition by the Normalised Cut (Ncut) algorithm. Finally, a case study is conducted in an actual city centre network, and results show that the developed method is superior to the single method based simply on link density.

TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut.

In this paper, we describe a graph-based algorithm that uses the features obtained by a self-supervised transformer to detect and segment salient objects in images and videos. With this approach, the image patches that compose an image or video are organised into a fully connected graph, in which the edge between each pair of patches is labeled with a similarity score based on the features learned by the transformer. Detection and segmentation of salient objects can then be formulated as a graph-cut problem and solved using the classical Normalized Cut algorithm. Despite the simplicity of this approach, it achieves state-of-the-art results on several common image and video detection and segmentation tasks. For unsupervised object discovery, this approach outperforms the competing approaches by a margin of 6.1%, 5.7%, and 2.6% when tested with the VOC07, VOC12, and COCO20K datasets. For the unsupervised saliency detection task in images, this method improves the score for Intersection over Union (IoU) by 4.4%, 5.6% and 5.2%. When tested with the ECSSD, DUTS, and DUT-OMRON datasets. This method also achieves competitive results for unsupervised video object segmentation tasks with the DAVIS, SegTV2, and FBMS datasets. Our implementation is available at https://www.m-psi.fr/Papers/TokenCut2022/.