Image Clustering Research Articles

Predictive Assessment of Fetus Features Using Scanned Image Segmentation Techniques and Deep Learning Strategy

Fetus weight at various stages of pregnancy is a critical component in determining the health of the baby. Abnormalities arising early in the pregnancy may be prevented by preventive measures. A variety of techniques suggested to predict foetus weight. Computer vision is a capability that can estimate the weight of a baby based on ultra-sonograms taken at various stages of pregnancy. Using the scanned data, one may train an advanced convolutional neural network that helps in accurately forecasting the fetus's size, weight, and overall health. The research utilizes computer vision techniques with image clustering methods for preprocessing, to predict the foetus's health, training datasets defective foetus datasets and healthy foetus datasets. Developing an integrated computer vision and a deep neural network is the hour which decrease the cost of operations and manual processes This study estimate the fetus's weight with optimal accuracy range at varying gestation age.

Necropolitics and Visuality: Remembering ‘Speculative Fictions’ in Hong Kong after Rancière and Mbembe

In his article, “Necropolitics and Visuality: Remembering ‘Speculative Fictions’ in Hong Kong after Rancière and Mbembe,” Anthony Siu examines images from Defiance.Voices, a two-volume collection that gathers photography and art illustrations about the Hong Kong Protests. He studies how paintings from the second volume register politics and events, arguing that visual art can be viewed as a new form of “speculative fictions,” a material ontology that historicizes modes of sovereign violence in postcolony. The introduction situates the debate of aesthetics in Hong Kong, conjoining Rancière’s thinking on “the people” and Achille Mbembe’s philosophy on “necropolitics.” The first cluster of images looks at the polemics of visibility in tear-gas consumption. The second questions the disposable bodies and the endurance of “cruel optimism” in the younger generation. The third figures Hong Kong as the node of deadly econometrics in the Sino-American network. Despite their individual differences, “speculative fictions” in the three clusters are all entangled with the politics of economics.

Spatial-Spectral Constrained Adaptive Graph for Hyperspectral Image Clustering.

Hyperspectral image (HSI) clustering is a challenging task, whose purpose is to assign each pixel to a corresponding cluster. The high-dimensionality and noise corruption are two main problems that limit the performance of HSI clustering. To address those problems, this paper proposes a projected clustering with a spatial–spectral constrained adaptive graph (PCSSCAG) method for HSI clustering. PCSSCAG first constructs an adaptive adjacency graph to capture the accurate local geometric structure of HSI data adaptively. Then, a spatial–spectral constraint is employed to simultaneously explore the spatial and spectral information for reducing the negative influence on graph construction caused by noise. Finally, projection learning is integrated into the spatial–spectral constrained adaptive graph construction for reducing the redundancy and alleviating the computational cost. In addition, an alternating iteration algorithm is designed to solve the proposed model, and its computational complexity is theoretically analyzed. Experiments on two different scales of HSI datasets are conducted to evaluate the performance of PCSSCAG. The associated experimental results demonstrate the superiority of the proposed method for HSI clustering.

Efficient Supervised Image Clustering Based on Density Division and Graph Neural Networks

In recent research, supervised image clustering based on Graph Neural Networks (GNN) connectivity prediction has demonstrated considerable improvements over traditional clustering algorithms. However, existing supervised image clustering algorithms are usually time-consuming and limit their applications. In order to infer the connectivity between image instances, they usually created a subgraph for each image instance. Due to the creation and process of a large number of subgraphs as the input of GNN, the computation overheads are enormous. To address the high computation overhead problem in the GNN connectivity prediction, we present a time-efficient and effective GNN-based supervised clustering framework based on density division namely DDC-GNN. DDC-GNN divides all image instances into high-density parts and low-density parts, and only performs GNN subgraph connectivity prediction on the low-density parts, resulting in a significant reduction in redundant calculations. We test two typical models in the GNN connectivity prediction module in the DDC-GNN framework, which are the graph convolutional networks (GCN)-based model and the graph auto-encoder (GAE)-based model. Meanwhile, adaptive subgraphs are generated to ensure sufficient contextual information extraction for low-density parts instead of the fixed-size subgraphs. According to the experiments on different datasets, DDC-GNN achieves higher accuracy and is almost five times quicker than those without the density division strategy.

Comparative analysis of the leaf architectural characters of Saurauia bontocensis Merr. and Saurauia polysperma (Blanco) Merr. with the application of Digital Image Analysis Software

Abstract. Daipan BPO, Buot IE Jr., Daipan HMO. 2022. Comparative analysis of the leaf architectural characters of Saurauia bontocensis Merr. and Saurauia polysperma (Blanco) Merr. with the application of Digital Image Analysis Software. Biodiversitas 23: 3869-3875. Major confusion still exists among several authors concerning the taxonomy of the dagwey plant. This species is economically significant to the Ikalahan tribe of Luzon, Philippines. Several papers claimed that the plant is Saurauia bontocensis, while others stated that it is Saurauia subglabra. Many botanical websites claimed that S. subglabra is synonymous with S. polysperma, while another article distinguished S. subglabra from S. polysperma. Thus, to help resolve the taxonomic ambiguities, this paper performed a comparative analysis of the leaf architectural characters of S. bontocensis and S. polysperma with the aid of digital image analysis software and cluster analysis. Results revealed that the blade characters alone, delineate the two species, particularly, in terms of the laminar size, shape, symmetry, leaf L:W ratio, base and apex angle, and base shape. Additionally, the leaf venation characters delineate the two species, specifically, on the 2º to 5º vein categories, 2º vein angle, 3º vein course, 3º vein angle to 1º, areolation, freely ending ultimate veins, marginal ultimate venation, and leaf rank. Generally, S. bontocensis have larger, longer, and wider leaves compared with the S. polysperma. The leaf architecture analysis performed in this paper produced a very promising result in differentiating the two Saurauia species and could be used to address some of the taxonomic confusion of these species. The study indicated that S. bontocensis and S. polysperma are two distinct species. Moreover, the use of digital image analysis software was very helpful in the computations of the various blade characters, particularly the digital herbarium exsiccate in the absence of actual leaf samples.

Improved deep clustering model based on semantic consistency for image clustering

Recently, contrastive learning has gained increasing attention as a research topic for image-clustering tasks. However, most contrastive learning-based clustering models focus only on the similarity of embedded features or divergence of cluster assignments, without considering the semantic distribution of instances, undermining the performance of clustering. Therefore, an improved deep clustering model based on semantic consistency (DCSC) was proposed in this study, motivated by the assumption that the semantic probability distribution of various augmentations of the same instance should be similar and that of different instances should be orthogonal. The DCSC fully exploits instance-level differentiation, cluster-level discrimination, and semantic consistency of instances to design the objective function. Compared with existing contrastive learning-based clustering models, the proposed model is more cluster-sensitive to differentiate semantic concepts owing to the incorporation of cluster structure discovering loss. Extensive experimental results on six benchmark datasets illustrate that the proposed DCSC achieves superior performance compared to the state-of-the-art clustering models, with an improved accuracy of 9.3% for CIFAR-100 and 22.1% for tiny-ImageNet. The visualization results show that the DCSC produces geometrically well-separated cluster embeddings defined by the Euclidean distance, verifying the effectiveness of the proposed DCSC.

Image mining technique using Hadoop map reduce over distributed multi-node computers connections

The amount of today's image collections has exploded to petabytes of data. A fair amount of time cannot be allotted for the analysis of such massive datasets using a personal computer. As a result, distributed computing is required for current image collection mining. This work used multi-nodes-computers for image mining in order to improve reliability, fall tolerance, and time efficiency. Because of this, the data was divided up across the nodes in the Hadoop multi-node cluster, and the results were then compiled to create an image clustering algorithm. One master node and two slave nodes were used to test our technique on a huge dataset. Using multi-node Hadoop, we found that we could get a speed-up in implementing as high as a single-node Hadoop implementation.

Image mining technique using Hadoop map reduce over distributed multi-node computers connections

The amount of today's image collections has exploded to petabytes of data. A fair amount of time cannot be allotted for the analysis of such massive datasets using a personal computer. As a result, distributed computing is required for current image collection mining. This work used multi-nodes-computers for image mining in order to improve reliability, fall tolerance, and time efficiency. Because of this, the data was divided up across the nodes in the Hadoop multi-node cluster, and the results were then compiled to create an image clustering algorithm. One master node and two slave nodes were used to test our technique on a huge dataset. Using multi-node Hadoop, we found that we could get a speed-up in implementing as high as a single-node Hadoop implementation.

Fast robust fuzzy clustering based on bipartite graph for hyper‐spectral image classification

Hyper-spectral image (HSI) clustering has become a hot spot in remote sensing image research. However, due to the large amount and high dimension of HSI data, some traditional image clustering methods are no longer suitable, and even lead to poor clustering performance and long computing time. Therefore, this paper proposes a novel clustering method for HSI to make up for the shortcomings of traditional clustering methods. Firstly, a fuzzy similarity matrix is constructed by using the bipartite graph to obtain low-dimensional hyper-spectral data, which can reduce the complexity and the operation time of the algorithm. Secondly, fuzzy membership mapping is carried out through the constructed bipartite graph, and a non-negative regularization term is added to limit ill-conditioned problems. Thirdly, this paper uses the Geman-McClure function to optimize Euclidean distance. Finally, in this paper, the spectral information of HSI is considered while the neighbourhood information of HSI is added to achieve the unity of space spectrum, which enhances the robustness of the algorithm and improves the clustering performance of the algorithm. Compared with existing HSI clustering algorithms, the proposed algorithm has higher clustering accuracy and efficiency.

Neural mixture models with expectation-maximization for end-to-end deep clustering

Any clustering algorithm must synchronously learn to model the clusters and allocate data to those clusters in the absence of labels. Mixture model-based methods model clusters with pre-defined statistical distributions and allocate data to those clusters based on the cluster likelihoods. They iteratively refine those distribution parameters and member assignments following the Expectation-Maximization (EM) algorithm. However, the cluster representability of such hand-designed distributions that employ a limited amount of parameters is not adequate for most real-world clustering tasks. In this paper, we realize mixture model-based clustering with a neural network where the final layer neurons, with the aid of an additional transformation, approximate cluster distribution outputs. The network parameters pose as the parameters of those distributions. The result is an elegant, much-generalized representation of clusters than a restricted mixture of hand-designed distributions. We train the network end-to-end via batch-wise EM iterations where the forward pass acts as the E-step and the backward pass acts as the M-step. In image clustering, the mixture-based EM objective can be used as the clustering objective along with existing representation learning methods. In particular, we show that when mixture-EM optimization is fused with consistency optimization, it improves the sole consistency optimization performance in clustering. Our trained networks outperform single-stage deep clustering methods that still depend on k-means, with unsupervised classification accuracy of 63.8% in STL10, 58% in CIFAR10, 25.9% in CIFAR100, and 98.9% in MNIST.

Exploring the economics of public health intervention scale-up: a case study of the Supporting Healthy Image, Nutrition and Exercise (SHINE) cluster randomised controlled trial

BackgroundThe costs and benefits of an intervention within the intervention testing phase may differ from those experienced when that intervention is implemented and delivered at scale. Yet limited empirical work has been undertaken to explore how economic constructs related to implementation and scale-up might have an impact on intervention cost. The aim of this study was to explore the potential economic impacts of implementation and scale-up on a healthy weight and body image intervention tested in a Type II translational research trial.MethodsThe Supporting Healthy Image, Nutrition and Exercise (SHINE) study is a cluster randomised controlled trial, aiming to deliver universal education about healthy nutrition, physical activity and wellbeing behaviours to adolescents in Australian secondary schools. Data on the cost of the intervention were collected alongside the trial using standard micro-costing techniques. Semi-structured interviews were conducted with key intervention stakeholders to explore the potential economic impacts of implementation and scale-up. Thematic content analysis was undertaken by two authors.ResultsFifteen intervention group schools participated in the 8-week online intervention targeting students in 2019 (99 Grade 7 classes; 2,240 students). Booster sessions were delivered during one class session in Grades 8 and 9, in 2020 and 2021 respectively. Time costs of intervention delivery and co-ordination comprised the majority (90%) of intervention cost as per the trial, along with costs associated with travel for intervention training and equipment. Themes related to the benefit of the intervention emerged from interviews with six intervention stakeholders, including the potential for economies of scale afforded by online delivery. Contextual themes that may have an impact on intervention implementation and scale included acceptability across all school sectors, availability and reliability of IT infrastructure for intervention delivery and variations in population characteristics. A number of key alterations to the intervention program emerged as important in supporting and sustaining intervention scale-up. In addition, significant implementation costs were identified if the intervention was to be successfully implemented at scale.ConclusionsThe findings from this study provide important information relevant to decisions on progression to a Type III implementation trial, including budget allocation, and will inform modelled economic evaluation.

Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing Images

Image clustering is a very useful technique that is widely applied to various areas, including remote sensing. Recently, visual representations by self-supervised learning have greatly improved the performance of image clustering. To further improve the well-trained clustering models, this paper proposes a novel method by first ranking samples within each cluster based on the confidence in their belonging to the current cluster and then using the ranking to formulate a weighted cross-entropy loss to train the model. For ranking the samples, we developed a method for computing the likelihood of samples belonging to the current clusters based on whether they are situated in densely populated neighborhoods, while for training the model, we give a strategy for weighting the ranked samples. We present extensive experimental results that demonstrate that the new technique can be used to improve the state-of-the-art image clustering models, achieving accuracy performance gains ranging from 2.1% to 15.9%. Performing our method on a variety of datasets from remote sensing, we show that our method can be effectively applied to remote sensing images.

Active deep image clustering

Deep clustering has attracted increasingly more attention in recent years. However, due to the absence of labels, deep clustering sometimes still provides unreliable clustering results. Although semi-supervised deep clustering can alleviate this problem to some extent by involving few human annotations, we observe that the performance of semi-supervised clustering highly depends on the selection of data for human labeling, but unfortunately, the supervised information selection is still a tough problem as traditional semi-supervised methods pay no attention to it. To tackle this problem, in this paper, we propose a novel deep active clustering method, which can actively select the key data for human labeling and apply the human annotations to improve the deep clustering. Different from conventional semi-supervised deep clustering methods which use fixed pre-given supervised information, we design a simple yet effective strategy to select the informative and uncertain data for querying annotation, which is beneficial to the clustering task. Furthermore, we integrate deep representation learning, clustering, and data selection into a unified framework, so that each task can be boosted by each other. Finally, we conduct extensive experiments on benchmark data sets by comparing it with some state-of-the-art deep clustering methods and semi-supervised clustering methods. The experimental results show that our active clustering methods can outperform both the unsupervised and semi-supervised clustering methods, demonstrating the effectiveness of the proposed method. The codes of this paper are released in https://doctor-nobody.github.io/codes/ADC_codes.zip.

Application of mathematical methods and machine learning algorithms for classification of X-ray images

The relevance of the topic, in particular, if to take one of the information flows, whether it is the action of a human factor or a specific object, then it is true that special processing of the machine learning language and automatic information output significantly optimize human life. With the help of neural networks and their chest radiography is one of the most accessible radiological studies for screening and diagnosis of many lung diseases a special machine learning language is to study the flow of information about it and the same object in real time using neural networks. The article describes the terminology of the problem of X-ray recognition using machine learning methods and algorithms, examines the relevance of the problem, and analyzes the current state of the problem in the field of X-ray recognition. The aspects of the problem being solved, identified during the analysis, in the form of solved problems, approaches, methods, information technologies used, tools and software solutions to the problem are noted The paper is devoted to the description of a modified method of fuzzy clustering of halftone images, which at each iteration performs a dynamic transformation of the source data based on a singular decomposition with automatic selection of the most significant columns of the matrix of left singular vectors. The results of experimental studies were obtained by processing X-ray images. As a result of testing a neural network model, in the output layer of which a sigmoidal activation function was used to activate neurons, and an algorithm was used as an optimization method, the best values of accuracy and completeness were obtained: accuracy – 94.2 During testing, the neural network showed an accuracy of pneumonia recognition equal to 94,27 %

A Study on Edge Board for Blur Image Judgment and Cluster Image Behavior Analysis: AI-Based Image Processing System Research

The purpose of this study is to solve the problem that the control center cannot cope with the situation properly due to the difficulty of analyzing the behavior in the case of cluster images or the occurrence of unclear images due to weather conditions and fine dust. Edge board development is necessary for cases in which the image sharpness check and overlap image check are inaccurate. In addition, evaluation techniques such as PSNR (; Peak Signal-to-Noise Ratio) and SSIM (; Structural Similarity Index) are used for the corresponding images to evaluate the degree of image improvement of the model with a validation dataset for each fixed image. After evaluating the model's inference speed in terms of FPS (; Frame Per Second), verification is performed for each stored model for each training, and the improvement rate of the image is calculated to evaluate which model is the most optimal for each weather condition. Development of modular edge board for CCTV (; Closed Circuit Television) linked event processing and ICPoIP (; Image Check Processing over IP) system for hybrid-based image classification, video improvement solution and superimposed image shape analysis by linking with the video control system Develop solutions for image processing systems to advance the performance of the image processing system.

Precision Marketing Strategy for Ecotourism Based on Data Mining and User Images

With the continuous development of ecotourism industry, it has become a common concern in ecotourism industry to utilize the available data to realize the change of ecotourism industry and promote the product development and business expansion of ecotourism industry. To this end, we propose a personalized ecotourism route recommendation (PTIR) algorithm based on the popularity of points of interest (POI) and users’ interest preferences. First, we analyze the real historical ecotourism footprints of users, propose a time-based user interest preference, and design a method to calculate the best ecotourism route given the travel time limit, departure point, and end point. Experiments were conducted on a real dataset of the Flickr social networking site, and the results showed that this personalized ecotourism route recommendation algorithm has greatly improved accuracy and recall compared with the traditional algorithm that only considers POI popularity, and the results were visualized through specific experimental cases based on user image clustering.

Adaptive Correlation Integration for Deep Image Clustering

Deep clustering methods often estimate data correlations to guide unsupervised learning. However, since different kinds of correlations capture different data characteristics, a strong data correlation may not be appropriate for every case. In this paper, we propose a novel Teacher-Student framework to adaptively estimate correlation and interactively learn a deep clustering model for various data distributions. Specifically, a teacher module mines and integrates various kinds of correlations from different perspectives. To adapt to various cases, we propose a novel Adaptive Integration Gate (ADI-Gate) to selectively and dynamically integrate different data correlations in a teaching-feedback manner. Furthermore, a student module performs unsupervised clustering inference with the estimated correlation and provides a preference for teacher module. We also design a Pairwise-Weighted loss (PW-loss) to enhance high-confident correlation guidance of data pairs during the learning process of student module. In image clustering experiments on four public datasets, our model achieves consistent improvements over state-of-the-art models.

An overview of Cuckoo Optimization Algorithm based Image Processing

The Cuckoo Search (CS) algorithm is an effective swarm intelligence optimization algorithm whose important developments were presented by Yang and Deb in 2009. The CS algorithm has been used in many applications to solve optimization problems. This paper describes an overview of the applications of CS in the scope of image processing to solve optimization problems for the image during the years 2015-2021. The main categories reviewed that used CS in the field of image processing are: image segmentation, image optimization, image noise removal, image classification, feature extraction in images, image clustering and edge detection. The aim of this paper is to provide an overview and summarize the literature review of applying CS algorithm in these categories in order to extract which categories that applied this algorithm more than others. From this review we conclude that CS was mostly applied in the image segmentation category to optimize the threshold search.

Climatic zonation of Egypt based on high-resolution dataset using image clustering technique

Egypt, a predominantly arid and hyper-arid country, is one of the environmentally most fragile regions of the world. The country became a hot spot for climatic extremes and aridity change in the global warming context. The unavailability of a detailed and reliable climate zonation map is a major hindrance to climatic studies in Egypt. This study attempted to generate a high-resolution climate zone map of Egypt based on a novel image analysis technique. For this purpose, a colored image representing Egypt's composite climatology was developed using three high-resolution (1-km) climate variables: rainfall, maximum temperature and minimum temperature during 1979–2013. A spherical evolution algorithm was used to classify the image into different climate zones. Subsequently, the climate zones representing similar climate distribution were merged to generate the climate map of Egypt. The study revealed that Egypt’s distinguishable climate zones could be recognized when the land area was classified into nine zones using the image analysis technique. The statistical analysis of climate variables of each zone revealed similar climatology only in two pairs of zones. The merging of similar climate zones yielded seven climate zones having distinct climate characteristics. The validation of climate zonation using various statistical tests revealed the robustness of the proposed method in classifying climate. The climate zone map generated in the study can be used as a reference for climate change analysis in Egypt.

Deep subspace image clustering network with self-expression and self-supervision

Deep subspace image clustering network with self-expression and self-supervision