K-means Segmentation Algorithm Research Articles

A Novel 3D Multi-Layer Convolutional Neural Networks for Lung Cancer Segmentation in CT Images

Background/Objectives: A novel three-dimensional efficient Multi-Layer Convolutional Neural Network (3D-MLCNN) is proposed for detecting lung tumors accurately using Computerized Tomography (CT) lung tumor images. The proposed K-means segmentation algorithm for labeling the tumor region automatically. This proposed K-means segmentation algorithm automatically labels the tumor regions to process with the 3D MLCNN model to predict tiny tumors and extract tumor regions accurately. Methods: The proposed 3DMLCNN network goal is to extract the tumor region in CT lung images to classify the lung tumor volume by pixel-wise segmentation model. Findings: The proposed 3D MLCNN segmentation model for detecting the segmenting tumors produces outperforming results for predicting even tiny tumors in the lung images. Experimental results demonstrated with lung cancer CT images in TCIA datasets show that the proposed model 3D-MLCNN achieved a dice coefficient (9.6%), Intersection over Union (IoU) (80%), F1-Score (9.33%), Sensitivity (17.11%), and Accuracy (98%) respectively. However, the proposed model 3D MLCNN was evaluated and compared with the existing state-of-the-art segmentation methods, which shows a 10% improvement in the segmentation process. Novelty: A novel 3D MLCNN model enhances the tumor region and predicts the tumor accurately by labeling the tumor using K-means labeling techniques. Keywords: 3D Convolutional Neural Networks, Lung Cancer CT Images, K - Means Labeling, Feature Visualization, Deep Learning

Image Segmentation and Classification using Neural Network

Image segmentation and classification tasks in computer vision have proven to be highly effective using neural networks, specifically Convolutional Neural Networks (CNNs). These tasks have numerous practical applications, such as in medical imaging, autonomous driving, and surveillance. CNNs are capable of learning complex features directly from images and achieving outstanding performance across several datasets. In this work, we have utilized three different datasets to investigate the efficacy of various preprocessing and classification techniques in accurssedately segmenting and classifying different structures within the MRI and natural images. We have utilized both sample gradient and Canny Edge Detection methods for pre-processing, and K-means clustering have been applied to segment the images. Image augmentation improves the size and diversity of datasets for training the models for image classification. This work highlights transfer learning’s effectiveness in image classification using CNNs and VGG 16 that provides insights into the selection of pre-trained models and hyper parameters for optimal performance. We have proposed a comprehensive approach for image segmentation and classification, incorporating preprocessing techniques, the K-means algorithm for segmentation, and employing deep learning models such as CNN and VGG 16 for classification.

Development Of A Web-Based Supply Chain Management System At The Minahasa Cooperatives And Umkm Service Using The K-Means Algorithm

The development of Micro, Small and Medium Enterprises (MSMEs) plays a very important role in the regional economy. Therefore, a Supply Chain Management (SCM) system is a very important aspect of business operations that involves coordinating the activities involved in the production and delivery of goods and services to customers. SCM can be applied to small and medium enterprises (MSMEs) in the Minahasa Cooperatives and UMKM Department to improve their performance and competitiveness. SCM aims to efficiently manage the flow of goods, information and capital from suppliers to end consumers. This research aims to design and develop a web-based Supply Chain Management system for the Department of Cooperatives and MSMEs by applying the k-means algorithm for customer segmentation. In this research, the K-Means algorithm is used to group similar data points. This algorithm works by defining clusters so that the total intra-cluster variation (known as total within-cluster variation) is minimized. The results of this research can help increase the efficiency and effectiveness of supply chain management. In developing this system, customer, supplier and product data were successfully grouped into several groups based on similar characteristics using the k-means algorithm. Apart from that, the system that has been developed can also help facilitate the SCM process by utilizing information technology.

An efficient machine learning approach for classification of diabetic retinopathy stages

Diabetic retinopathy (DR) the prime cause of blindness, develops when glucose levels rise, causing retinal damage. DR can be prevented if the illness is detected early. As a result, early grading, categorization, and diagnosis of DR can help diabetic patients avoid visual loss. Several system methods assist in the classification of DR using high-performance criteria. This work proposes an efficient system-based DR classification. The purpose of efficient machine learning dabetic retinopatyy grading classification (EML-DRGC) design is to recognize DR impulsively with highest accuracy. The proposed technique employs preprocessing methods such as employing the Gaussian filtering approach for removing noise present in retinal fundus images. The segmentation process is followed using K-means segmentation algorithm which is used for segmenting the region of interest (ROI) from background. Moreover, Feature extraction process is done by using gray level co-occurrence matrix (GLCM) in which features are extracted bycapturing the image's visual content and features from acceerated segment test (FAST) design is used as extractor of features. Finally, multi support vector machine is utilized as classifier for detecting severity levels of DR. Performance metrics such as accuracy of 98.38% and specificity of 98.34% are obtained which are superior to existing designs.

Automated Fruit Quality Detection Using Image Processing

In this paper, an automated fruit quality inspection and sorting system for apples has been proposed. The objective of this system is to replace the manual inspection system. This helps to speed up the process, improve the accuracy and efficiency of the system. In this work, the multiple images of apple are captured by using camera place above the conveyor belt. We have captured multiple images to make the proposed system more accurate which covers the maximum surface area of fruit. Then various image processing algorithms are used to extract the features of fruit such as texture, color, and size. Automated sorting and grading are done based on these features. The defected apple is diverted from conveyor using motor. The proposed embedded system works at higher speed and gives high accuracy in grading with low-cost solution. It will have a good prospect of application in fruit quality detection and grading areas. In the proposed algorithm, we have used k-means algorithm for segmentation and local Binary Pattern technique is used extract feature vectors of the test and training images. Then, the training and testing features are given to neural network algorithm to classify the test image into normal and abnormal class. We have considered the normal and abnormal (rotten apple images) for training purposes. Experimental results show that the proposed system accurately classifies the apple and gives better accuracy.

Automated Fruit Quality Detection Using Image Processing

In this paper, an automated fruit quality inspection and sorting system for apples has been proposed. The objective of this system is to replace the manual inspection system. This helps to speed up the process, improve the accuracy and efficiency of the system. In this work, the multiple images of apple are captured by using camera place above the conveyor belt. We have captured multiple images to make the proposed system more accurate which covers the maximum surface area of fruit. Then various image processing algorithms are used to extract the features of fruit such as texture, color, and size. Automated sorting and grading are done based on these features. The defected apple is diverted from conveyor using motor. The proposed embedded system works at higher speed and gives high accuracy in grading with low-cost solution. It will have a good prospect of application in fruit quality detection and grading areas. In the proposed algorithm, we have used k-means algorithm for segmentation and local Binary Pattern technique is used extract feature vectors of the test and training images. Then, the training and testing features are given to neural network algorithm to classify the test image into normal and abnormal class. We have considered the normal and abnormal (rotten apple images) for training purposes. Experimental results show that the proposed system accurately classifies the apple and gives better accuracy.

Segmentation of image based on k-means and modified subtractive clustering

Image segmentation has widespread applications in medical science, for example, classification of different tissues, identification of tumors, estimation of tumor size, surgery planning, and atlas matching. Clustering is a widely implemented unsupervised technique used for image segmentation mainly because of its simplicity and fast computation. However, the quality and efficiency of clustering-based segmentation is highly depended on the initial value of the cluster centroid. In this paper, a new hybrid segmentation approach based on k-means clustering and modified subtractive clustering is proposed. K-means clustering is a very efficient and powerful algorithm but it requires initialization of cluster centroid. And, the consistency of the clustering outcomes of k-means algorithm depends on the initial selection of the cluster center. To overcome this drawback, a modified subtractive clustering algorithm based on distance relations between cluster centers and data points is proposed which finds a more accurate cluster centers compared to the conventional subtractive clustering. These cluster centroids obtained from the modified subtractive clustering are used in k-means algorithm for segmentation of the image. The proposed method is compared with other existing conventional segmentation methods by using several synthetic and real images and experimental finding validates the superiority of the proposed method.

An improved K-means algorithm for underwater image background segmentation

Conventional algorithms fail to obtain satisfactory background segmentation results for underwater images. In this study, an improved K-means algorithm was developed for underwater image background segmentation to address the issue of improper K value determination and minimize the impact of initial centroid position of grayscale image during the gray level quantization of the conventional K-means algorithm. A total of 100 underwater images taken by an underwater robot were sampled to test the aforementioned algorithm in respect of background segmentation validity and time cost. The K value and initial centroid position of grayscale image were optimized. The results were compared to the other three existing algorithms, including the conventional K-means algorithm, the improved Otsu algorithm, and the Canny operator edge extraction method. The experimental results showed that the improved K-means underwater background segmentation algorithm could effectively segment the background of underwater images with a low color cast, low contrast, and blurred edges. Although its cost in time was higher than that of the other three algorithms, it none the less proved more efficient than the time-consuming manual segmentation method. The algorithm proposed in this paper could potentially be used in underwater environments for underwater background segmentation.

Superpixel Image Segmentation Based on Improved K-means

Superpixel algorithm is the pretreatment of the image processing steps, in the processing of computer vision, precision of the superpixel algorithm is very important. In order to improve the accuracy of superpixel segmentation, an improved k-means algorithm for superpixel segmentation is proposed. This algorithm uses the improved k-means algorithm to cluster the images. By changing the calculation method of distance, it improves the measurement of similarity, improves the accuracy of segmentation, and improves the quality of segmentation results. Experimental data show that this algorithm performs better than the traditional algorithm and improves the segmentation quality and visual effect.

Hidden object detection for classification of threat

The automated video surveillance has become important due to the focus from government and users for improving the smart nature of the buildings. A system developed for handling this can be used for prison, airport, banks, etc. Though there are solutions for this they fail in situations of mishaps and objects that are hidden that could become a threat to the environment. In this paper a framework has been built using modified K-means segmentation algorithm to detect hidden objects. The framework operates in two phases: phase 1 – modified K-means segmentation algorithm for segmenting the hidden objects; phase 2 – deep convolutional neural network for classifying the hidden object the algorithm selects searched for the approximately optimal value of K and segments the object. The result of the algorithm is given to deep convolutional neural network for classifying the type of object. The algorithm is tested with manually built dataset using Fluke Tis40 Thermal Imager. The experiments were carried out in batches of 50*50 images and the performance of the approach is presented using top-1 accuracy and mean average precision and they are 0.94 and 0.64, respectively. From the experimental analysis, we infer that the proposed algorithm works with precision 0.88 false discovery rates 0.12.

Hidden object detection for classification of threat

The automated video surveillance has become important due to the focus from government and users for improving the smart nature of the buildings. A system developed for handling this can be used for prison, airport, banks, etc. Though there are solutions for this they fail in situations of mishaps and objects that are hidden that could become a threat to the environment. In this paper a framework has been built using modified K-means segmentation algorithm to detect hidden objects. The framework operates in two phases: phase 1 – modified K-means segmentation algorithm for segmenting the hidden objects; phase 2 – deep convolutional neural network for classifying the hidden object the algorithm selects searched for the approximately optimal value of K and segments the object. The result of the algorithm is given to deep convolutional neural network for classifying the type of object. The algorithm is tested with manually built dataset using Fluke Tis40 Thermal Imager. The experiments were carried out in batches of 50*50 images and the performance of the approach is presented using top-1 accuracy and mean average precision and they are 0.94 and 0.64, respectively. From the experimental analysis, we infer that the proposed algorithm works with precision 0.88 false discovery rates 0.12.

Intellectual Acute Lymphoblastic Leukemia (ALL) Detection Model for Diagnosis of Blood Cancer from microscopic images using Hybrid Convolutional Neural Network

Blood cell malignantly growth has been accounted for to be one of the most transcendent types of disease maladies. ALL (Acute Lymphoblastic Leukaemias) is the malignant types of blood cancer and their detection and classification in earlier stage is biggest issue. Automatic detection and classification of ALL from microscopic images is a challenging and intellectual assignment in medical science. Existing techniques for ALL detection and classification are an understandable alternative for real-time dermoscopic data analysis. Existing microscopic image processing approaches are unable to analyze the ALL data with non-stationary nature. In this perspective, the focus of this research is to design hybrid Convolutional Neural Network (CNN) architecture by utilizing Firefly Optimization Algorithm (FOA/FFA) to detect the ALL from microscopic images of human blood cell into malignant or normal blood cell. Methods: For training and testing of proposed ALL Detection and Classification (ALL-DC) Model, Standard ALL-IDB (Acute-Lymphoblastic-Leukaemias Image Database for Image Processing) is used with hybrid CNN architecture based on the FOA. Here, Histogram of Oriented Gradients (HOG) descriptor with FOA is used as feature extraction and selection mechanism from the Region of Blood Cell (ROBC).Feature extraction approach plays an important responsibility to classify lots of blood diseases. On the way to achieve this goal, we proposed ALL-DC model that combines recent developments in deep learning with fuzzy based CNN structure and for ROBC segmentation, hybridization of K-means segmentation algorithm with FOA that are capable to segment the accurate blood cell region from microscopic images. Using k-means segmentation technique, the foreground and background component is separated into two regions and after that to improve the segmentation results; FOA is used with the novel concept of image enhancement approach. Results: The proposed ALL-DC system is evaluated using the largest publicly accessible standard ALL-IDB dataset, containing 600 training and 400 testing microscopic images. When the evaluation parameters of proposed work is compared with a number of other state-of-art schemes, the proposed scheme achieves the most excellent performance of 98.5% in terms of accuracy which also known as area under the curve (AUC) in differentiating ALL from benign cell using only the extracted and optimized HOG feature. Conclusion: When the proposed model is tested on different microscopic images, evaluation parameters is calculated and compared with a few other state-of-art methods and we obtained the proposed method achieves the best performance in terms of classification accuracy. ALL-DC model is implemented and constructed using the concept of Image Processing and Neural Network Toolbox within MATLAB Software.

Multimodal Device for Real-Time Monitoring of Skin Oxygen Saturation and Microcirculation Function

The present study introduces a recently developed compact hybrid device for real-time monitoring of skin oxygen saturation and temperature distribution. The prototype involves a snapshot hyperspectral camera, multi-wavelength illuminator, thermal camera, and built-in computer with custom-developed software. To validate this device in-vivo we performed upper arm vascular occlusion on eight healthy volunteers. Palm skin oxygen saturation maps were analyzed in real-time using k-means segmentation algorithm and two-layer optical diffuse model. The prototype system demonstrated a satisfying performance of skin hyperspectral measurements in the spectral range of 507–625 nm. The results confirmed the reliability of the proposed system for in-vivo assessment of skin hemoglobin saturation with oxygen and microcirculation.

Evaluation of modified adaptive k-means segmentation algorithm

Segmentation is the act of partitioning an image into different regions by creating boundaries between regions. k-means image segmentation is the simplest prevalent approach. However, the segmentation quality is contingent on the initial parameters (the cluster centers and their number). In this paper, a convolution-based modified adaptive k-means (MAKM) approach is proposed and evaluated using images collected from different sources (MATLAB, Berkeley image database, VOC2012, BGH, MIAS, and MRI). The evaluation shows that the proposed algorithm is superior to k-means++, fuzzy c-means, histogram-based k-means, and subtractive k-means algorithms in terms of image segmentation quality (Q-value), computational cost, and RMSE. The proposed algorithm was also compared to state-of-the-art learning-based methods in terms of IoU and MIoU; it achieved a higher MIoU value.

A low complexity hardware architecture of K-means algorithm for real-time satellite image segmentation

The Real time monitoring of forest area, coastal regions, sea, river basins, nation borders etc. helps in quick determination of devastations caused by natural or man-made catastrophes, which can lead to emergency situations. Real-time Segmentation of satellite images is essential to detect fire, floods, volcanoes, earthquakes etc. of a specific geographical zone. Effective determination of such calamities and taking proactive measures can save a lot of lives and natural resources. In this paper, an efficient FSM based architecture is proposed for performing segmentation of satellite Images procured from NASA’s Operational Land Imager (OLI) on Landsat 8 and Landsat 5. The K-means clustering algorithm even after five decades of it’s existence is quite effective and mostly used for big data applications, owing to its lower complexity. However, it’s effective implementation has started only in the last couple of years. Here a FSM-based reconfigurable architecture is proposed for K-means algorithm taking into consideration the real-time segmentation of satellite Images. Compared to other architectures in the literature, the proposed one has reduced hardware usage, lower area, power consumption with a satisfactory clock frequency, most importantly it is reconfigurable and can be used with the on-board circuitry within satellites. The testing is carried out on eight latest satellite images of natural and human devastations, taken from NASA’s OLI. The number of possible clusters within the geographical image is studied with the help of histogram analysis based on Otsu’s thresholding method. The performance analysis is carried out by computing the Peak Signal to Noise (PSNR) and Mean Structural Similarity Index (M-SSIM) of the resultant clusters. It is observed that by increasing the number of clusters, the detailed classes were effectively segmented and the quality of clustering is ensured by the improvement in PSNR and M-SSIM values. Comparison of the obtained clusters with their true land features also yielded satisfactory results.

A New Augmented K-Means Algorithm for Seed Segmentation in Microscopic Images of the Colon Cancer

A New Augmented K-Means Algorithm for Seed Segmentation in Microscopic Images of the Colon Cancer

DEFECT IDENTIFICATION IN THE FRUIT APPLE USING K-MEANS COLOR IMAGE SEGMENTATION ALGORITHM

To propose a variation in the already existing algorithm to find whether an apple is defected or not, is the primary objective of this paper. The defected part on an apple’s image is identified using K-means segmentation algorithm. Color images of Apples with certain defects are taken as input dataset for applying the newly proposed algorithm. Color components of an apple’s image are used for segmentation. K-means clustering technique – an iterative process is used to partition an apple’s image into k clusters. Pixels are clustered based on color intensity values and images are generated to identify the defected part. After detecting the defected part, image enhancement is done using median filter in order to enhance the defected part and which in turn will increase the efficiency of classification process in the proposed algorithm. The experimental study clarifies the effectiveness of both the already existing method and newly proposed method.

Unsupervised Learning Framework for Customer Requisition and Behavioral Pattern Classification

Maintaining healthy organization-customers relationship has positive influence on customers’ behavioral tendencies as regards preference to products and services, buying behavior, loyalty, satisfaction, and so on. To achieve this, an in-depth analysis of customers’ characteristics and purchasing behavioral trend is required. This paper proposes a hybrid unsupervised learning framework consisting of k-means algorithm and self-organizing maps (SOMs) for customer segmentation and behavior analysis. K-means algorithm was used to partition the entire input space of customers’ transaction dataset into 3 and 4 disjoint segments based on customers’ frequency (F) and monetary value (MV). SOM provided visualization of the underlying clusters and discovered customers’ relationships in the dataset. Interaction of F and MV clusters resulted in 12 sub-clusters. An in-depth analysis of each sub-cluster was also performed and appropriate customer relationship management (CRM) strategies established for each sub-cluster. Discovered knowledge will guide effective allocation of resources to each customer cluster and other organizational decision support functions much required by CRM systems.

A novel overlapped nuclei splitting algorithm for histopathological images

Background and objectiveNuclei segmentation is a common process for quantitative analysis of histopathological images. However, this process generally results in overlapping of nuclei due to the nature of images, the sample preparation and staining, and image acquisition processes as well as insufficiency of 2D histopathological images to represent 3D characteristics of tissues. We present a novel algorithm to split overlapped nuclei. MethodsThe histopathological images are initially segmented by K-Means segmentation algorithm. Then, nuclei cluster are converted to binary image. The overlapping is detected by applying threshold area value to nuclei in the binary image. The splitting algorithm is applied to the overlapped nuclei. In first stage of splitting, circles are drawn on overlapped nuclei. The radius of the circles is calculated by using circle area formula, and each pixel's coordinates of overlapped nuclei are selected as center coordinates for each circle. The pixels in the circle that contains maximum number of intersected pixels in both the circle and the overlapped nuclei are removed from the overlapped nuclei, and the filled circle labeled as a nucleus. ResultsThe algorithm has been tested on histopathological images of healthy and damaged kidney tissues and compared with the results provided by an expert and three related studies. The results demonstrated that the proposed splitting algorithm can segment the overlapping nuclei with accuracy of 84%. ConclusionsThe study presents a novel algorithm splitting the overlapped nuclei in histopathological images and provides more accurate cell counting in histopathological analysis. Furthermore, the proposed splitting algorithm has the potential to be used in different fields to split any overlapped circular patterns.

Curvelet Based Seed Point Segmentation for Abnormality Detection in Fetus us Images

Objectives: A new method for automatic segmentation is designed for improving accuracy and abnormality detection in fetus Ultra Sound images at an early stage. Methods: Curvelet-based Seed Point Selection (S-CSPS) method is developed for improving abnormality detection rate using 𝑘-means segmentation algorithm. Correct identification of regions for each pixel that belongs to the objects in US images is obtained through seed point evaluation reducing the speckle and therefore resulting in the improvement of abnormality being detected. Findings: The proposed S-CSPS is implemented in MATLAB platform using ultrasound images of anomalies of fetal spine dataset. The performance analysis is conducted on factors such as noise, segmentation accuracy abnormality detection rate and segmentation time with respect to a different number of fetus images. Improvement: The simulation analysis results shows that S-CSPS method offers better performance with an improvement of segmentation accuracy and improving the abnormality detection rate compared to state-of-the art methods.