Clustering Segmentation Research Articles

Improved Edge Detection using Morphological Operation to Segmentation of Fingernail Images

Accurate segmentation of fingernail images is essential for biomedical applications like dermatological diagnostics and nail disease assessments. This study compares traditional methods (Sobel and Canny edge detectors) with an improved method using adaptive thresholding and morphological closing for fingernail image segmentation. The methodology includes data collection, preprocessing, edge detection, segmentation, and evaluation. A dataset of 500 fingernail images (free of nail polish) was captured using a digital camera. Preprocessing involves grayscale conversion to simplify analysis and Gaussian smoothing to reduce noise while preserving key features. For segmentation, thresholding and K-means clustering isolate the fingernail from the background. Evaluation combines qualitative and quantitative analyses. Qualitative results demonstrate that the improved method consistently outperforms traditional techniques under diverse conditions. Quantitative evaluation, based on accuracy, recall, F1 score, and Intersection over Union (IoU), further supports these findings. The Sobel method achieves 0.80 accuracy, 0.77 recall, 0.87 F1 score, and 0.77 IoU. The Canny method achieves 0.82 accuracy, 0.78 recall, 0.88 F1 score, and 0.78 IoU. In contrast, the improved method achieves 0.97 accuracy, 0.98 recall, 0.99 F1 score, and 0.98 IoU. The results clearly show that the improved method, using adaptive thresholding and morphological closing, provides superior segmentation performance. Additionally, the approach remains computationally efficient, making it suitable for real-time applications in medical diagnostics.

Analysis of Italian craft beer consumers: preferences and purchasing behaviour

PurposeIn the current landscape of the beverage market, craft beer has secured a prominent position, attracting consumers seeking high-quality products with distinctive characteristics. This study aims to identify the key drivers of consumer preferences for craft beer attributes.Design/methodology/approachConjoint analysis and cluster segmentation were employed to analyze the preferences of 351 Italian craft beer consumers.FindingsThe preferences of a representative sample were analyzed to identify the utilities associated with various beer attributes, including colour, alcohol level, body, raw material origin and price. The findings indicate that colour is the most highly valued attribute, followed by price and alcohol level. Consumers prefer beers with a lighter colour, a moderate alcohol level between 5 and 7% and an affordable price. Furthermore, beers that emphasize the Italian origin of raw materials are appreciated, demonstrating a strong link with local identity. The segmentation of the sample into three clusters revealed significant differences in preferences. The first cluster preferred light beers at medium prices, the second for amber beers at low prices and the third opted for dark and full-bodied beers.Originality/valueThe findings of this study provide valuable insights for craft beer producers seeking to refine their marketing strategies and product development. Producers can better meet consumers’ evolving preferences by better understanding the diverse needs of consumers and optimizing their offerings in an increasingly competitive market.

Adaptive Compression and Reconstruction for Multidimensional Medical Image Data: A Hybrid Algorithm for Enhanced Image Quality.

Spatial regions within images typically hold greater priority over adjacent areas, especially in the context of medical images (MI) where minute details can have significant clinical implications. This research addresses the challenge of compressing medical image dimensions without compromising critical information by proposing an adaptive compression algorithm. The algorithm integrates a modified image enhancement module, clustering-based segmentation, and a variety of lossless and lossy compression techniques. Edge enhancement contrast limited adaptive histogram equalization (EE-CLAHE) and 2D adaptive anisotropic diffusion filter are employed to enhance and denoise the images, followed by adaptive expectation maximization clustering (AEMC) for segmentation into regions of interest (ROI) and non-ROI. The clustering process is optimized utilizing fuzzy c-means (FCM) and Otsu thresholding. Subsequently, distinct compression schemes are applied to ROI and non-ROI regions, such as Coiflet + Haar, Coiflet + Daubecheis, modified SPIHT Huffman, EZW, and SPIHT algorithms, to ensure effective storage and transmission while preserving diagnostic details. Experimental results demonstrate that the combination of the modified SPIHT Huffman algorithm for ROI and EZW for non-ROI yields superior reconstruction quality across various measures, enabling comprehensive analysis of multi-dimensional images from MRI, CT, and X-ray modalities.

Robust and Fast Point Cloud Registration for Robot Localization Based on DBSCAN Clustering and Adaptive Segmentation.

This paper proposes a registration approach rooted in point cloud clustering and segmentation, named Clustering and Segmentation Normal Distribution Transform (CSNDT), with the aim of improving the scope and efficiency of point cloud registration. Traditional Normal Distribution Transform (NDT) algorithms face challenges during their initialization phase, leading to the loss of local feature information and erroneous mapping. To address these limitations, this paper proposes a method of adaptive cell partitioning. Firstly, a judgment mechanism is incorporated into the DBSCAN algorithm. This mechanism is based on the standard deviation and correlation coefficient of point cloud clusters. It improves the algorithm's adaptive clustering capabilities. Secondly, the point cloud is partitioned into straight-line point cloud clusters, with each cluster generating adaptive grid cells. These adaptive cells extend the range of point cloud registration. This boosts the algorithm's robustness and provides an initial value for subsequent optimization. Lastly, cell segmentation is performed, where the number of segments is determined by the lengths of the adaptively generated cells, thereby improving registration accuracy. The proposed CSNDT algorithm demonstrates superior robustness, precision, and matching efficiency compared to classical point cloud registration methods such as the Iterative Closest Point (ICP) algorithm and the NDT algorithm.

Noise and cluster size insensitive robust weighted fuzzy clustering for medical image segmentation

Noise and cluster size insensitive robust weighted fuzzy clustering for medical image segmentation

Multi-factor evaluation of clustering methods for e-commerce application

This research aimed to investigate the application of Vlse Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) multi-criteria decision-making to select the optimal clustering for e-commerce customer segmentation. In this context, clustering as an unsupervised machine learning method offered a way to overcome the limitations of traditional grouping, particularly by providing the ability to capture the diverse needs of consumers. A total of five different clustering methods were considered based on the behavioral data of e-commerce customers. Even though the analyzed algorithms were well-known and widely used, the comprehensive and multidirectional comparison was not trivial. Selected approaches were evaluated on the basis of twelve indicators (decision criteria), divided into four characteristics that take into account both the out-of-context aspects of clustering and the requirements arising from the context of using the clustering results. The results showed consistent outcomes from both analyzed Multi-Criteria Decision Methods, with some notable differences. The methods obtained the same ranking of the top three clustering algorithms (K-median - BIRCH - K-means). However, the TOPSIS and VIKOR sensitivity analysis recommended K-means in 87% of the cases and 60% of the variants verified, respectively. The parameterization of the decision factors had a significant impact on the final ranking of clustering options. This research demonstrated the practical application of the decision methods in selecting the best clustering for multivariate user interfaces to improve personalization in e-commerce.

Analyzing Consumer Shopping Interest via Social Media Ads with K-Means and C4.5 Algorithm

It is increasingly important to understand how advertisements affect consumers' propensity to shop as social media becomes the primary medium for advertising. This study uses the C4.5 algorithm for classification and K-Means Clustering for data segmentation to examine the level of consumer shopping interest driven by Facebook and Instagram ads. This strategy utilizes information collected from user interactions with ads on these two social media platforms to determine consumer interest trends more precisely. The research findings show that, compared to conventional methods, this combination of techniques can increase the accuracy of predicting consumer purchase intention by as much as 85%. These results not only validate the usefulness of clustering and classification methods in digital advertising data analysis, but also offer insights that companies can apply to optimize their marketing strategies. By understanding more specific consumer segments, companies can target their ads more precisely, thereby increasing conversions and the effectiveness of advertising campaigns. This research makes a significant contribution to the field of data analysis and digital marketing and opens up opportunities for further research in the integration of more sophisticated analysis methods

An on-machine tool wear area identification method based on image augmentation and advanced segmentation

In industrial manufacturing, tool wear monitoring (TWM) is essential for ensuring high-quality machining, operational efficiency, cost-effectiveness, and safety. However, due to the complexities of on-machine imaging and the constraints of direct measurement techniques, TWM methods face challenges such as unclear boundaries, class imbalance between wear and unworn area, and image diversity. This paper proposes a novel two-step approach for identifying tool wear areas. Firstly, DeepLabV3+ with Focal Loss is utilized to identify the Region of Interest (ROI) of the tool. Secondly, the method employs Intuitionistic Fuzzy C-Means Clustering (IFCM) for detailed segmentation of the wear area. This integration effectively addresses challenges arising from uneven illumination that blur image boundaries and the class imbalance between images with tool wear and those without. To enhance image diversity and quality, we utilize Denoising Diffusion Probabilistic Models (DDPM) for image augmentation, significantly enriching the training dataset. The proposed approach achieves a Mean Pixel Accuracy (MPA) of 95.32% and a Mean Intersection over Union (MIoU) of 93.67%, which marks a substantial improvement over existing TWM models. This progress not only provides a more reliable and efficient tool wear monitoring solution but also sets a new standard for precision in industrial machining processes.

Learning rule in MFR pulse sequence for behavior mode prediction

Radar behavior prediction is an important task in the field of electronic reconnaissance. For the extensive applied multi-function radar (MFR), which can flexibly transition between various work modes and make certain statistical rule of these radar behaviors exist in the signal sequence. Most of existing radar emission prediction methods are inapplicable to the non-cooperative scenario, since the labeled sequence samples are hard to obtain. To solve this challenge, an unsupervised framework is proposed for learning the behavior rule from the pulse sequence and predicting the radar mode in this paper. The framework includes three modules of sequence segmentation for mode switch boundaries detection, segment clustering for behavior mode recognition, and mode prediction for behavior rule extraction. The application of this framework can predict state and numerical values of next mode at the same time. Experimental results demonstrate that the proposed framework has a considerable prediction performance and shows good robustness under the non-ideal conditions.

An approach based on data mining and genetic algorithm to optimizing time series clustering for efficient segmentation of customer behavior

In today's highly competitive market, organizations face significant challenges in accurately understanding and segmenting customer behavior due to the inherently dynamic and evolving nature of customer interactions over time. Traditional customer segmentation methods often neglect these temporal variations, leading to ineffective business strategies and missed opportunities. This research addresses this critical gap by introducing an innovative time series-based approach for customer behavior segmentation. By modeling each customer's behavior as a time series capturing key metrics such as purchase frequency, transaction amounts, and customer lifecycle costs the proposed method dynamically adapts to behavioral changes over time. To enhance segmentation precision, a genetic algorithm is employed to optimize feature weights, ensuring that the most relevant factors are emphasized. These optimized features are then clustered using spectral clustering to identify distinct and meaningful customer segments. The effectiveness of the proposed method is validated using 30 months of transactional data from a payment services company. The results demonstrate that the proposed approach, particularly when combined with spectral clustering and optimally weighted features, significantly surpassing the performance of traditional static segmentation techniques. This research not only provides a more accurate framework for uncovering hidden patterns in customer behavior but also delivers actionable insights for targeted marketing and personalized customer strategies.

Street tree segmentation method combining image semantic segmentation and point cloud clustering

Abstract As a common object in the park scene, the 3D information of street trees is crucial for digital cities, and extracting individual trees from point cloud data accurately and efficiently is a hotspot and a difficult point-in-point cloud processing. Aiming at the interference problem of complex non-tree objects and dynamic objects in the park environment, a tree point cloud segmentation method combining a deep learning network framework with a point cloud clustering algorithm is proposed in this paper. First, this paper applies the YOLOv8 to the semantic segmentation of camera images, and fuses image semantics with point cloud data, to build the semantic point cloud model. Then, preliminary extraction for street trees is performed using the semantic information of this point cloud model, and radius filtering is used to reduce the outliers. Finally, the individual tree segmentation is realized using an enhanced multi-level Euclidean clustering algorithm based on KD-Tree. Experimental results indicate that the proposed method performs well in extracting and segmenting the roadway trees, with a recall of 94.5%, a precision of 80.7%, and an F1-score of 87.0%.

Paclitaxel- or sirolimus-coated balloons used for ArterioVEnous fistulas-2 (PAVE-2): study protocol for a randomised controlled trial to determine the efficacy of paclitaxel- or sirolimus-coated balloons in arteriovenous fistulas used for haemodialysis

BackgroundIn view of the conflicting results from previous studies, the benefit of paclitaxel-coated balloons for arteriovenous fistulas is uncertain and equipoise remains. Although an industry-led trial testing the efficacy of sirolimus-coated balloons in AVFs is in progress, the benefit of sirolimus-coated balloons for arteriovenous fistulas is currently unknown. The purpose of this trial is to compare the efficacy of additional paclitaxel-coated or sirolimus-coated balloons on outcomes after a plain balloon fistuloplasty to preserve the patency of arteriovenous fistulae used for haemodialysis.MethodsThe study design is a multicentre randomised controlled trial. Following a successful plain balloon fistuloplasty, participants will be randomised to further treatment with a paclitaxel-coated balloon, a sirolimus-coated balloon, or an uncoated control balloon. We will recruit 642 patients, each with one or two treatment segments, over a 3-year period. Patients will remain in the trial and be followed up for 1 year. The primary endpoint is time to loss of treatment segment primary patency. Cox-proportional hazards models will be used to estimate hazard ratios for the time to loss of treatment segment primary patency for each treatment group relative to the control group. Analysis of the primary endpoint will be based on treatment segments rather than participants and a shared frailty will be estimated to account for the clustering of treatment segments within patients. Secondary endpoints are time to loss of primary patency at any treatment segment; time to end of access circuit primary patency; time to AVF abandonment; number of radiological or surgical interventions; adverse events; intima-media thickness and degree of stenosis at 3 months on ultrasound; and patient quality of life assessed by EQ-5D-5L and VASQoL.DiscussionThe three-armed design in this proposal will provide an answer on the efficacy of both paclitaxel- and sirolimus-coated balloons in the same trial. This trial is likely to provide a clear answer regarding the efficacy of drug-coated balloons for arteriovenous fistulas.Trial registrationISRCTN ISRCTN40182296. Registered on 4 August 2023.

PIPdb: a comprehensive plasmid sequence resource for tracking the horizontal transfer of pathogenic factors and antimicrobial resistance genes.

Plasmids, as independent genetic elements, carrying resistance or virulence genes and transfer them among different pathogens, posing a significant threat to human health. Under the 'One Health' approach, it is crucial to control the spread of plasmids carrying such genes. To achieve this, a comprehensive characterization of plasmids in pathogens is essential. Here we present the Plasmids in Pathogens Database (PIPdb), a pioneering resource that includes 792964 plasmid segment clusters (PSCs) derived from 1 009571 assembled genomes across 450 pathogenic species from 110 genera. To our knowledge, PIPdb is the first database specifically dedicated to plasmids in pathogenic bacteria, offering detailed multi-dimensional metadata such as collection date, geographical origin, ecosystem, host taxonomy, and habitat. PIPdb also provides extensive functional annotations, including plasmid type, insertion sequences, integron, oriT, relaxase, T4CP, virulence factors genes, heavy metal resistance genesand antibiotic resistance genes. The database features a user-friendly interface that facilitates studies on plasmids across diverse host taxa, habitats, and ecosystems, with a focus on those carrying antimicrobial resistance genes (ARGs). We have integrated online tools for plasmid identification and annotation from assembled genomes. Additionally, PIPdb includes a risk-scoring system for identifying potentially high-risk plasmids. The PIPdb web interface is accessible at https://nmdc.cn/pipdb.

Maize Phenotypic Parameters Based on the Constrained Region Point Cloud Phenotyping Algorithm as a Developed Method

As one of the world’s most crucial food crops, maize plays a pivotal role in ensuring food security and driving economic growth. The diversification of maize variety breeding is significantly enhancing the cumulative benefits in these areas. Precise measurement of phenotypic data is pivotal for the selection and breeding of maize varieties in cultivation and production. However, in outdoor environments, conventional phenotyping methods, including point cloud processing techniques based on region growing algorithms and clustering segmentation, encounter significant challenges due to the low density and frequent loss of point cloud data. These issues substantially compromise measurement accuracy and computational efficiency. Consequently, this paper introduces a Constrained Region Point Cloud Phenotyping (CRPCP) algorithm that proficiently detects the phenotypic traits of multiple maize plants in sparse outdoor point cloud data. The CRPCP algorithm consists primarily of three core components: (1) a constrained region growth algorithm for effective segmentation of maize stem point clouds in complex backgrounds; (2) a radial basis interpolation technique to bridge gaps in point cloud data caused by environmental factors; and (3) a multi-level parallel decomposition strategy leveraging scene blocking and plant instances to enable high-throughput real-time computation. The results demonstrate that the CRPCP algorithm achieves a segmentation accuracy of 96.2%. When assessing maize plant height, the algorithm demonstrated a strong correlation with manual measurements, evidenced by a coefficient of determination R2 of 0.9534, a root mean square error (RMSE) of 0.4835 cm, and a mean absolute error (MAE) of 0.383 cm. In evaluating the diameter at breast height (DBH) of the plants, the algorithm yielded an R2 of 0.9407, an RMSE of 0.0368 cm, and an MAE of 0.031 cm. Compared to the PointNet point cloud segmentation method, the CRPCP algorithm reduced segmentation time by more than 44.7%. The CRPCP algorithm proposed in this paper enables efficient segmentation and precise phenotypic measurement of low-density maize multi-plant point cloud data in outdoor environments. This algorithm offers an automated, high-precision, and highly efficient solution for large-scale field phenotypic analysis, with broad applicability in precision breeding, agronomic management, and yield prediction.

Advances in Medical Image Segmentation: A Comprehensive Review of Traditional, Deep Learning and Hybrid Approaches.

Medical image segmentation plays a critical role in accurate diagnosis and treatment planning, enabling precise analysis across a wide range of clinical tasks. This review begins by offering a comprehensive overview of traditional segmentation techniques, including thresholding, edge-based methods, region-based approaches, clustering, and graph-based segmentation. While these methods are computationally efficient and interpretable, they often face significant challenges when applied to complex, noisy, or variable medical images. The central focus of this review is the transformative impact of deep learning on medical image segmentation. We delve into prominent deep learning architectures such as Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), U-Net, Recurrent Neural Networks (RNNs), Adversarial Networks (GANs), and Autoencoders (AEs). Each architecture is analyzed in terms of its structural foundation and specific application to medical image segmentation, illustrating how these models have enhanced segmentation accuracy across various clinical contexts. Finally, the review examines the integration of deep learning with traditional segmentation methods, addressing the limitations of both approaches. These hybrid strategies offer improved segmentation performance, particularly in challenging scenarios involving weak edges, noise, or inconsistent intensities. By synthesizing recent advancements, this review provides a detailed resource for researchers and practitioners, offering valuable insights into the current landscape and future directions of medical image segmentation.

IC-IE-AKS-O: an automatic recognition method for coastal slope landslide areas

Automatically and accurately identifying the deformation zone of coastal slope landslides is crucial for exploring the mechanism of landslides and predicting landslide disasters. To this end, this study proposes an integrated automatic recognition method combining Image Clipping (IC), Image Information Enhancement (IE), Adaptive K-means Clustering Segmentation (AKS), and Optimization (O): IC-IE-AKS-O, which achieves precise extraction of the deformation area in coastal slope landslide images. Firstly, due to the more complex natural environment of field slopes, to extend the monitoring duration, we introduce a hierarchical operation algorithm based on the HSV color model, which effectively mitigates the impact of sunlight, rain, and foggy weather on image recognition accuracy. Secondly, this study proposes a 2D landslide image segmentation technique that combines K-means clustering with global threshold segmentation for landslide images, enabling the segmentation of small image regions with precision. Finally, we combine image information enhancement technology with image segmentation technology. To verify its effectiveness, we identify a landslide image of a coastal slope in Pingtan. The method displays an average relative error of 5.20% and 5.14% in the X and Y directions, respectively. Its advantages are threefold: (1) The combination of image information enhancement and segmentation techniques can more accurately identify landslide areas that appear blurred in the image; (2) expanding the temporal dimension of coastal slope monitoring; (3) providing excellent boundary conditions and segmentation results. The practical application of this method ensures the stable and accurate operation of the coastal slope monitoring system, providing a safeguard for the sustainable development of marine safety.

A ship trajectory clustering algorithm based on segmentation direction

With the increase of ship AIS data. Through AIS data mining algorithm, it is possible to extract guidelines for the best path of a specific water area by using trajectory segment clustering. The defects of the current trajectory segment clustering algorithm are mainly reflected in: the lack of direction of the path after clustering; For trajectory segment clustering, the whole trajectory is considered rather than a single trajectory segment. In this paper, the trajectory direction and density are used as a measure of similarity between trajectories, and the trajectory segment clustering algorithm is used to analyze the compressed ship trajectory segment data. The first step is to eliminate clusters that contain too few trajectories, and clusters that have too small a distance value between trajectories. For two nearby clusters in opposite directions, the Hausdorff distance is determined. When the distance is less than the threshold, the trajectory is considered to be a two-way route. Finally, the trajectory clusters after clustering are fused to form a view of the overall traffic flow frame of ships in the water area. The framework can describe the main driving direction of the ship in the water and provide decision-making suggestions for the driver's path planning.

Firefighting Robot Extinguishment Decision‐Making Based on Visual Guidance: A Novel Attention and Scale U‐Net Model and Genetic Algorithm

ABSTRACTAt present, rescue firefighting relies mainly on firefighting robots, and robots with perception and decision‐making functions are the key elements for achieving intelligent firefighting. However, traditional firefighting robots often lack the ability for autonomous perception and decision‐making when extinguishing multiple fire sources, leading to low rescue efficiency and increased risk for rescue personnel, especially when making firefighting decisions in extreme fire scenes, which poses a challenge. To effectively handle firefighting tasks and ensure operational efficiency, a robot firefighting decision‐making method based on drone visual guidance is proposed. First, we introduce a novel Attention and Scale U‐Net (ASUNet) model to accurately capture crucial target information, including fire location and size, in a fire scene. The ASUNet model adopts an effective multiscale fusion strategy and attention mechanism to enhance the model's performance. Subsequently, based on the results of the ASUNet model, through pixel segmentation clustering and a genetic optimization algorithm, we obtain the robot's firefighting decision results, thereby guiding the robot to carry out firefighting operations systematically. Finally, through numerical experiments, it is verified that the proposed ASUNet model is superior and effective, as the model can perceive important information in a fire scene and extract it well. The use of improved genetic optimization can further accelerate algorithm convergence. To our knowledge, this study is the first to use drone‐based monocular vision guidance for firefighting decision‐making, providing significant engineering value.

A High-Accuracy Contour Segmentation and Reconstruction of a Dense Cluster of Mushrooms Based on Improved SOLOv2

A High-Accuracy Contour Segmentation and Reconstruction of a Dense Cluster of Mushrooms Based on Improved SOLOv2

Segmentation Method of Zanthoxylum bungeanum Cluster Based on Improved Mask R-CNN

The precise segmentation of Zanthoxylum bungeanum clusters is crucial for developing picking robots. An improved Mask R-CNN model was proposed in this study for the segmentation of Zanthoxylum bungeanum clusters in natural environments. Firstly, the Swin-Transformer network was introduced into the model’s backbone as the feature extraction network to enhance the model’s feature extraction capabilities. Then, the SK attention mechanism was utilized to fuse the detailed information into the mask branch from the low-level feature map of the feature pyramid network (FPN), aiming to supplement the image detail features. Finally, the distance intersection over union (DIOU) loss function was adopted to replace the original bounding box loss function of Mask R-CNN. The model was trained and tested based on a self-constructed Zanthoxylum bungeanum cluster dataset. Experiments showed that the improved Mask R-CNN model achieved 84.0% and 77.2% in detection mAP50box and segmentation mAP50mask, respectively, representing a 5.8% and 4.6% improvement over the baseline Mask R-CNN model. In comparison to conventional instance segmentation models, such as YOLACT, Mask Scoring R-CNN, and SOLOv2, the improved Mask R-CNN model also exhibited higher segmentation precision. This study can provide valuable technology support for the development of Zanthoxylum bungeanum picking robots.