Image Segmentation Based on Support Vector Machine

Image segmentation is a necessary step in image analysis. Support vector machine （SVM） approach is proposed to segment images and its segmentation performance is evaluated. Experimental results show that： the effects of kernel function and model parameters on the segmentation performance are significant; SVM approach is less sensitive to noise in image segmentation; The segmentation performance of SVM approach is better than that of back-propagation multi-layer perceptron （BP-MLP） approach and fuzzy c-means （FCM） approach.

Approximate entropy and support vector machines for electroencephalogram signal classification

The automatic detection and identification of electroencephalogram waves play an important role in the prediction, diagnosis and treatment of epileptic seizures. In this study, a nonlinear dynamics index–approximate entropy and a support vector machine that has strong generalization ability were applied to classify electroencephalogram signals at epileptic interictal and ictal periods. Our aim was to verify whether approximate entropy waves can be effectively applied to the automatic real-time detection of epilepsy in the electroencephalogram, and to explore its generalization ability as a classifier trained using a nonlinear dynamics index. Four patients presenting with partial epileptic seizures were included in this study. They were all diagnosed with neocortex localized epilepsy and epileptic foci were clearly observed by electroencephalogram. The electroencephalogram data form the four involved patients were segmented and the characteristic values of each segment, that is, the approximate entropy, were extracted. The support vector machine classifier was constructed with the approximate entropy extracted from one epileptic case, and then electroencephalogram waves of the other three cases were classified, reaching a 93.33% accuracy rate. Our findings suggest that the use of approximate entropy allows the automatic real-time detection of electroencephalogram data in epileptic cases. The combination of approximate entropy and support vector machines shows good generalization ability for the classification of electroencephalogram signals for epilepsy.

Human Behavior Classification Using Geometrical Features of Skeleton and Support Vector Machines

Classification of human actions under video surveillance is gaining a lot of attention from computer vision researchers.In this paper,we have presented methodology to recognize human behavior in thin crowd which may be very helpful in surveillance.Research have mostly focused the problem of human detection in thin crowd,overall behavior of the crowd and actions of individuals in video sequences.Vision based Human behavior modeling is a complex task as it involves human detection,tracking,classifying normal and abnormal behavior.The proposed methodology takes input video and applies Gaussian based segmentation technique followed by post processing through presenting hole filling algorithm i.e.,fill hole inside objects algorithm.Human detection is performed by presenting human detection algorithm and then geometrical features from human skeleton are extracted using feature extraction algorithm.The classification task is achieved using binary and multi class support vector machines.The proposed technique is validated through accuracy,precision,recall and F-measure metrics.

Multiple mental tasks classification based on nonlinear parameter of mean period using support vector machines

Mental task classification is one of the most important problems in Brain-computer interface.This paper studies the classification of five-class mental tasks.The nonlinear parameter of mean period obtained from frequency domain information was used as features for classification implemented by using the method of SVM(support vector machines).The averaged classification accuracy of 85.6% over 7 subjects was achieved for 2-second EEG segments.And the results for EEG segments of 0.5s and 5.0s compared favorably to those of Garrett's.The results indicate that the parameter of mean period represents mental tasks well for classification.Furthermore,the method of mean period is less computationally demanding,which indicates its potential use for online BCI systems.

Enhanced Wolf Pack Algorithm (EWPA) and Dense-kUNet Segmentation for Arterial Calcifications in Mammograms

Breast Arterial Calcification(BAC)is a mammographic decision dissimilar to cancer and commonly observed in elderly women.Thus identifying BAC could provide an expense,and be inaccurate.Recently Deep Learning(DL)methods have been introduced for automatic BAC detection and quantification with increased accuracy.Previously,classification with deep learning had reached higher efficiency,but designing the structure of DL proved to be an extremely challenging task due to overfitting models.It also is not able to capture the patterns and irregularities presented in the images.To solve the overfitting problem,an optimal feature set has been formed by Enhanced Wolf Pack Algorithm(EWPA),and their irregularities are identified by Dense-kUNet segmentation.In this paper,Dense-kUNet for segmentation and optimal feature has been introduced for classification(severe,mild,light)that integrates DenseUNet and kU-Net.Longer bound links exist among adjacent modules,allowing relatively rough data to be sent to the following component and assisting the system in finding higher qualities.The major contribution of the work is to design the best features selected by Enhanced Wolf Pack Algorithm(EWPA),and Modified Support Vector Machine(MSVM)based learning for classification.k-Dense-UNet is introduced which combines the procedure of Dense-UNet and kU-Net for image segmentation.Longer bound associations occur among nearby sections,allowing relatively granular data to be sent to the next subsystem and benefiting the system in recognizing smaller characteristics.The proposed techniques and the performance are tested using several types of analysis techniques 826 filled digitized mammography.The proposed method achieved the highest precision,recall,F-measure,and accuracy of 84.4333%,84.5333%,84.4833%,and 86.8667%when compared to other methods on the Digital Database for Screening Mammography(DDSM).

A Novel Inherited Modeling Structure of Automatic Brain Tumor Segmentation from MRI

Brain tumor is one of the most dreadful worldwide types of cancer and affects people leading to death.Magnetic resonance imaging methods capture skull images that contain healthy and affected tissue.Radiologists checked the affected tissue in the slice-by-slice manner,which was timeconsuming and hectic task.Therefore,auto segmentation of the affected part is needed to facilitate radiologists.Therefore,we have considered a hybrid model that inherits the convolutional neural network(CNN)properties to the support vector machine(SVM)for the auto-segmented brain tumor region.The CNN model is initially used to detect brain tumors,while SVM is integrated to segment the tumor region correctly.The proposed method was evaluated on a publicly available BraTS2020 dataset.The statistical parameters used in this work for the mathematical measures are precision,accuracy,specificity,sensitivity,and dice coefficient.Overall,our method achieved an accuracy value of 0.98,which is most prominent than existing techniques.Moreover,the proposed approach is more suitable for medical experts to diagnose the early stages of the brain tumor.

A Feature Selection Strategy to Optimize Retinal Vasculature Segmentation

Diabetic retinopathy (DR) is a complication of diabetesmellitus thatappears in the retina. Clinitians use retina images to detect DR pathologicalsigns related to the occlusion of tiny blood vessels. Such occlusion brings adegenerative cycle between the breaking off and the new generation of thinnerand weaker blood vessels. This research aims to develop a suitable retinalvasculature segmentation method for improving retinal screening proceduresby means of computer-aided diagnosis systems. The blood vessel segmentationmethodology relies on an effective feature selection based on SequentialForward Selection, using the error rate of a decision tree classifier in theevaluation function. Subsequently, the classification process is performed bythree alternative approaches: artificial neural networks, decision trees andsupport vector machines. The proposed methodology is validated on threepublicly accessible datasets and a private one provided by Hospital Sant Joanof Reus. In all cases we obtain an average accuracy above 96% with a sensitivityof 72% in the blood vessel segmentation process. Compared with the state-ofthe-art, our approach achieves the same performance as other methods thatneed more computational power.Our method significantly reduces the numberof features used in the segmentation process from 20 to 5 dimensions. Theimplementation of the three classifiers confirmed that the five selected featureshave a good effectiveness, independently of the classification algorithm.

Geometric active contour based approach for segmentation of high-resolution spaceborne SAR images

Segmentation is the key step in auto-interpretation of high-resolution spaceborne synthetic aperture radar（SAR） images. A novel method is proposed based on integrating the geometric active contour（GAC） and the support vector machine（SVM）models. First, the images are segmented by using SVM and textural statistics. A likelihood measurement for every pixel is derived by using the initial segmentation. The Chan-Vese model then is modified by adding two items： the likelihood and the distance between the initial segmentation and the evolving contour. Experimental results using real SAR images demonstrate the good performance of the proposed method compared to several classic GAC models.

Defocus Blur Segmentation Using Genetic Programming and Adaptive Threshold

Detection and classification of the blurred and the non-blurred regions in images is a challenging task due to the limited available information about blur type,scenarios and level of blurriness.In this paper,we propose an effective method for blur detection and segmentation based on transfer learning concept.The proposed method consists of two separate steps.In the first step,genetic programming(GP)model is developed that quantify the amount of blur for each pixel in the image.The GP model method uses the multiresolution features of the image and it provides an improved blur map.In the second phase,the blur map is segmented into blurred and non-blurred regions by using an adaptive threshold.A model based on support vector machine(SVM)is developed to compute adaptive threshold for the input blur map.The performance of the proposed method is evaluated using two different datasets and compared with various state-of-the-art methods.The comparative analysis reveals that the proposed method performs better against the state-of-the-art techniques.

Defocus Blur Segmentation Using Local Binary Patterns with Adaptive Threshold

Enormousmethods have been proposed for the detection and segmentation of blur and non-blur regions of the images.Due to the limited available information about blur type,scenario and the level of blurriness,detection and segmentation is a challenging task.Hence,the performance of the blur measure operator is an essential factor and needs improvement to attain perfection.In this paper,we propose an effective blur measure based on local binary pattern(LBP)with adaptive threshold for blur detection.The sharpness metric developed based on LBP used a fixed threshold irrespective of the type and level of blur,that may not be suitable for images with variations in imaging conditions,blur amount and type.Contrarily,the proposed measure uses an adaptive threshold for each input image based on the image and blur properties to generate improved sharpness metric.The adaptive threshold is computed based on the model learned through support vector machine(SVM).The performance of the proposed method is evaluated using two different datasets and is compared with five state-of-the-art methods.Comparative analysis reveals that the proposed method performs significantly better qualitatively and quantitatively against all of the compared methods.

SVM for density estimation and application to medical image segmentation

A method of medical image segmentation based on support vector machine (SVM) for density estimation is presented. We used this estimator to construct a prior model of the image intensity and curvature profile of the structure from training images. When segmenting a novel image similar to the training images, the technique of narrow level set method is used. The higher dimensional surface evolution metric is defined by the prior model instead of by energy minimization function. This method offers several advantages. First, SVM for density estimation is consistent and its solution is sparse. Second, compared to the traditional level set methods, this method incorporates shape information on the object to be segmented into the segmentation process. Segmentation results are demonstrated on synthetic images, MR images and ultrasonic images.

Improvement of Liver Segmentation by Combining High Order Statistical Texture Features with Anatomical Structural Features

Automatic segmentation of liver in medical images is challenging on the aspects of accuracy, automation and robustness. A crucial stage of the liver segmentation is the selection of the image features for the segmentation. This paper presents an accurate liver segmentation algorithm. The approach starts with a texture analysis which results in an optimal set of texture features including high order statistical texture features and anatomical structural features. Then, it creates liver distribution image by classifying the original image pixelwisely using support vector machines. Lastly, it uses a group of morphological operations to locate the liver organ accurately in the image. The novelty of the approach is resided in the fact that the features are so selected that both local and global texture distributions are considered, which is important in liver organ segmentation where neighbouring tissues and organs have similar greyscale distributions. Experiment results of liver segmentation on CT images using the proposed method are presented with performance validation and discussion.

Osteosarcoma Segmentation in MRI Based on Zernike Moment and SVM

Osteosarcoma is primary malignant neoplasms derived from cells of mesenchymal origin, and often has distinct phenotypes at different stages. The location of tumor and reaction zone can be identified by an expert in magnetic resonance imaging (MRI), with MRI being one of the choices for evaluating the extent of osteosarcoma. However, it is still a challenge to automatically extract tumor from its surrounding tissues because of their low intensity differences in MRI. We investigated an approach based on Zernike moment and support vector machine (SVM) for osteosarcoma segmentation in T1-weighted image (TIWI). Firstly, the different order moments around each pixel are calculated in small windows. Secondly, the grayscale and the module values of different order moments are used as a texture feature vector which is then used as the training set for SVM. Finally, an SVM classifier is trained based on this set of features to identify the osteosarcoma, and the segmented tumor tissue is rendered in 3D by the ray casting algorithm based on graphics processing unit (GPU). The performance of the method is validated on T1WI, showing that the segmentation method has a high similarity index with the expert's manual segmentation.

An enhanced segmentation technique and improved support vector machine classifier for facial image recognition

Purpose-One of the challenging issues in computer vision and pattern recognition is face image recognition.Several studies based on face recognition were introduced in the past decades,but it has few classification issues in terms of poor performances.Hence,the authors proposed a novel model for face recognition.Design/methodology/approach-The proposed method consists of four major sections such as data acquisition,segmentation,feature extraction and recognition.Initially,the images are transferred into grayscale images,and they pose issues that are eliminated by resizing the input images.The contrast limited adaptive histogram equalization(CLAHE)utilizes the image preprocessing step,thereby eliminating unwanted noise and improving the image contrast level.Second,the active contour and level set-based segmentation(ALS)with neural network(NN)or ALS with NN algorithm is used for facial image segmentation.Next,the four major kinds of feature descriptors are dominant color structure descriptors,scale-invariant feature transform descriptors,improved center-symmetric local binary patterns(ICSLBP)and histograms of gradients(HOG)are based on clour and texture features.Finally,the support vector machine(SVM)with modified random forest(MRF)model for facial image recognition.Findings-Experimentally,the proposed method performance is evaluated using different kinds of evaluation criterions such as accuracy,similarity index,dice similarity coefficient,precision,recall and F-score results.However,the proposed method offers superior recognition performances than other state-of-art methods.Further face recognition was analyzed with the metrics such as accuracy,precision,recall and F-score and attained 99.2,96,98 and 96%,respectively.Originality/value-The good facial recognition method is proposed in this research work to overcome threat to privacy,violation of rights and provide better security of data.

Precise Multi-Class Classification of Brain Tumor via Optimization Based Relevance Vector Machine

The objective of this research is to examine the use of feature selection and classification methods for distinguishing different types of brain tumors.The brain tumor is characterized by an anomalous proliferation of brain cells that can either be benign or malignant.Most tumors are misdiagnosed due to the variabil-ity and complexity of lesions,which reduces the survival rate in patients.Diagno-sis of brain tumors via computer vision algorithms is a challenging task.Segmentation and classification of brain tumors are currently one of the most essential surgical and pharmaceutical procedures.Traditional brain tumor identi-fication techniques require manual segmentation or handcrafted feature extraction that is error-prone and time-consuming.Hence the proposed research work is mainly focused on medical image processing,which takes Magnetic Resonance Imaging(MRI)images as input and performs preprocessing,segmentation,fea-ture extraction,feature selection,similarity measurement,and classification steps for identifying brain tumors.Initially,the medianfilter is practically applied to the input image to reduce the noise.The graph-cut segmentation technique is used to segment the tumor region.The texture feature is extracted from the output of the segmented image.The extracted feature is selected by using the Ant Colony Opti-mization(ACO)algorithm to improve the performance of the classifier.This prob-abilistic approach is used to solve computing issues.The Euclidean distance is used to calculate the degree of similarity for each extracted feature.The selected feature value is given to the Relevance Vector Machine(RVM)which is a multi-class classification technique.Finally,the tumor is classified as abnormal or nor-mal.The experimental result reveals that the proposed RVM technique gives a better accuracy range of 98.87%when compared to the traditional Support Vector Machine(SVM)technique.

Contrast Normalization Strategies in Brain Tumor Imaging:From Preprocessing to Classification

Cancer-related to the nervous system and brain tumors is a leading cause of mortality in various countries.Magnetic resonance imaging(MRI)and computed tomography(CT)are utilized to capture brain images.MRI plays a crucial role in the diagnosis of brain tumors and the examination of other brain disorders.Typically,manual assessment of MRI images by radiologists or experts is performed to identify brain tumors and abnormalities in the early stages for timely intervention.However,early diagnosis of brain tumors is intricate,necessitating the use of computerized methods.This research introduces an innovative approach for the automated segmentation of brain tumors and a framework for classifying different regions of brain tumors.The proposed methods consist of a pipeline with several stages:preprocessing of brain images with noise removal based on Wiener Filtering,enhancing the brain using Principal Component Analysis(PCA)to obtain well-enhanced images,and then segmenting the region of interest using the Fuzzy C-Means(FCM)clustering technique in the third step.The final step involves classification using the Support Vector Machine(SVM)classifier.The classifier is applied to various types of brain tumors,such as meningioma and pituitary tumors,utilizing the Contrast-Enhanced Magnetic Resonance Imaging(CE-MRI)database.The proposed method demonstrates significantly improved contrast and validates the effectiveness of the classification framework,achieving an average sensitivity of 0.974,specificity of 0.976,accuracy of 0.979,and a Dice Score(DSC)of 0.957.Additionally,this method exhibits a shorter processing time of 0.44 s compared to existing approaches.The performance of this method emphasizes its significance when compared to state-of-the-art methods in terms of sensitivity,specificity,accuracy,and DSC.To enhance the method further in the future,it is feasible to standardize the approach by incorporating a set of classifiers to increase the robustness of the brain classification method.

L_(1)-Smooth SVM with Distributed Adaptive Proximal Stochastic Gradient Descent with Momentum for Fast Brain Tumor Detection

Brain tumors come in various types,each with distinct characteristics and treatment approaches,making manual detection a time-consuming and potentially ambiguous process.Brain tumor detection is a valuable tool for gaining a deeper understanding of tumors and improving treatment outcomes.Machine learning models have become key players in automating brain tumor detection.Gradient descent methods are the mainstream algorithms for solving machine learning models.In this paper,we propose a novel distributed proximal stochastic gradient descent approach to solve the L_(1)-Smooth Support Vector Machine(SVM)classifier for brain tumor detection.Firstly,the smooth hinge loss is introduced to be used as the loss function of SVM.It avoids the issue of nondifferentiability at the zero point encountered by the traditional hinge loss function during gradient descent optimization.Secondly,the L_(1) regularization method is employed to sparsify features and enhance the robustness of the model.Finally,adaptive proximal stochastic gradient descent(PGD)with momentum,and distributed adaptive PGDwithmomentum(DPGD)are proposed and applied to the L_(1)-Smooth SVM.Distributed computing is crucial in large-scale data analysis,with its value manifested in extending algorithms to distributed clusters,thus enabling more efficient processing ofmassive amounts of data.The DPGD algorithm leverages Spark,enabling full utilization of the computer’s multi-core resources.Due to its sparsity induced by L_(1) regularization on parameters,it exhibits significantly accelerated convergence speed.From the perspective of loss reduction,DPGD converges faster than PGD.The experimental results show that adaptive PGD withmomentumand its variants have achieved cutting-edge accuracy and efficiency in brain tumor detection.Frompre-trained models,both the PGD andDPGD outperform other models,boasting an accuracy of 95.21%.

An Effective Diagnosis System for Brain Tumor Detection and Classification

A brain tumor is an excessive development of abnormal and uncontrolled cells in the brain.This growth is considered deadly since it may cause death.The brain controls numerous functions,such as memory,vision,and emotions.Due to the location,size,and shape of these tumors,their detection is a challenging and complex task.Several efforts have been conducted toward improved detection and yielded promising results and outcomes.However,the accuracy should be higher than what has been reached.This paper presents a method to detect brain tumors with high accuracy.The method works using an image segmentation technique and a classifier in MATLAB.The utilized classifier is a SupportVector Machine(SVM).DiscreteWavelet Transform(DWT)and Principal Component Analysis(PCA)are also involved.A dataset from the Kaggle website is used to test the developed approach.The obtained results reached nearly 99.2%of accuracy.The paper provides a confusion matrix of applying the proposed approach to testing images and a comparative evaluation between the developed method and some works in the literature.This evaluation shows that the presented system outperforms other approaches regarding the accuracy,precision,and recall.This research discovered that the developed method is extremely useful in detecting brain tumors,given the high accuracy,precision,and recall results.The proposed system directs us to believe that bringing this kind of technology to physicians diagnosing brain tumors is crucial.

Combined spatial frequency spectroscopy analysis with visible resonance Raman for optical biopsy of human brain metastases of lung cancers

The purpose of this study is to examine optical spatial frequency spectroscopy analysis(SFSA)combined with visible resonance Raman(VRR)spectroscopic method,for thefirst time,to discriminate human brain metastases of lung cancers adenocarcinoma(ADC)and squamous cell carcinoma(SCC)from normal tissues.A total of 31 label-free micrographic images of three type of brain tissues were obtained using a confocal micro-Raman spectroscopic system.VRR spectra of the corresponding samples were synchronously collected using excitation wavelength of 532 nm from the same sites of the tissues.Using SFSA method,the difference in the randomness of spatial frequency structures in the micrograph images was analyzed using Gaussian functionfitting.The standard deviations,calculated from the spatial frequencies of the micrograph images were then analyzed using support vector machine(SVM)classifier.The key VRR biomolecularfingerprints of carotenoids,tryptophan,amide II,lipids and proteins(methylene/methyl groups)were also analyzed using SVM classifier.All three types of brain tissues were identified with high accuracy in the two approaches with high correlation.The results show that SFSA–VRR can potentially be a dual-modal method to provide new criteria for identifying the three types of human brain tissues,which are on-site,real-time and label-free and may improve the accuracy of brain biopsy.

Prediction of Blood-to-Brain Barrier Partitioning of Drugs and Organic Compounds Using a QSPR Approach

The purpose of this study was to develop a quantitative structure–property relationship(QSPR) model based on the enhanced replacement method(ERM) and support vector machine(SVM) to predict the blood-to-brain barrier partitioning behavior(log BB) of various drugs and organic compounds. Different molecular descriptors were calculated using a dragon package to represent the molecular structures of the compounds studied. The enhanced replacement method(ERM) was used to select the variables and construct the SVM model. The correlation coefficient, R^2, between experimental results and predicted log BB was 0.878 and 0.986, respectively. The results obtained demonstrated that, for all compounds, the log BB values estimated by SVM agreed with the experimental data, demonstrating that SVM is an effective method for model development, and can be used as a powerful chemometric tool in QSPR studies.