SVM-PUK Kernel Based MRI-brain Tumor Identification Using Texture and Gabor Wavelets

Chinnam, Siva Koteswara Rao; Sistla, Venkatrama Phani Kumar; Kolli, Venkata Krishna Kishore

doi:10.18280/ts.360209

Cited by 17 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The patient's normality or abnormality is after that determined using DNN technology. Venkatramaphanikumar Sistla, Venkata Krishna Kishore Koll and Siva Koteswara Rao Chinnam [15] discuss this topic in their work. Apply SVM PUK first to eliminate noise and smooth brain images.…”

Section: Literature Surveymentioning

confidence: 99%

Brain Tumor Diagnosis using Machine Learning: A Review

Abdulateef¹

2023

IJERAT

View full text Add to dashboard Cite

Recently, early brain tumor diagnosis has grown in importance as a study area recently. The patient's rateof survival rises with early tumor detection for primarytreatment. Because ofthe high processing overhead caused by the enormous volume regardingimage input to processing system, processing magnetic resonance image (MRI) for the early detection of tumors presents a problem. This led to a significant delay and a decline in system effectiveness. As a result, recently, there has been an increased requirement for an improved detection system for precise representation and segmentationfor accurate and fasterprocessing. Latestliterature has suggested the creation of novel methods depending onenhanced processing and learningfor the detection of brain tumors. This essay provides a succinct overview of the MRI-related advancements. The machine learning (ML)algorithms' capacity for fine processing and learninghas shown an enhancementin the efficiency and accuracy of processing for the detection of the brain tumor in existing automation systems. Restrictions, advantages,and outlook for future regardingthe present approaches for computer-aided diagnostics (CAD)in the detection of the brain tumor are discussed, along with current advances in automation related tobrain tumor detections. In the presented study, researcherexplore the history of numerous methods that have been put forth to image brain tumors across a variety of domains.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Brain Tumor Diagnosis using Machine Learning: A Review

Abdulateef¹

2023

IJERAT

View full text Add to dashboard Cite

show abstract

“…Furthermore, texture analysis applications have been widely applied in the medical research for the detection of various diseases including: tumor heterogeneity [9], [17], [18]; brain tumor [19], [20]; head and neck cancer [21], [22]; emphysema [23], [24]; prostate segmentation [25]- [27], colon cancer [28], [29]; small vessel disease and blood brain barrier [30], breast cancer [31]- [34]; skin cancer [35]- [37] retinal vessel segmentation [38], [39] and lung cancer [40], [41].…”

Section: A Related Workmentioning

confidence: 99%

Image Texture Analysis for Medical Image Mining: A Comparative Study Direct to Osteoarthritis Classification using Knee X-ray Image

Chan¹,

Dittakan²,

García-Constantino³

2020

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Knee Osteoarthritis (OA) is one of the most prominent diseases in an ageing society and has affected over 10 million people in Thailand. When people suffer from OA, it is very difficult to recover. Therefore, early detection and prevention are important. The typical way to detect OA is by using X-ray imaging. This research study is focused on early detection of OA by applying image processing and classification techniques to knee X-ray imagery. The fundamental concept is to find a region of interest, use feature extraction techniques and build a classifier that can classify between OA or non-OA imageries. There are four regions of interest obtained from each image: (i) Medial Femur (MF), (ii) Lateral Femur (LF), (iii) Medial Tibia (MT), and (iv) Lateral Tibia (LT). The ten texture analysis techniques are then adopted to generate the embedded properties of the bone surface. Once the feature vector has been generated the variety of techniques of machine learning mechanisms are applied to generate the desired classifiers, which can be used to distinguish between OA and non-OA images. From the conducted experiments, a total of 131 images (68 OA cases and 63 non-OA cases) was used, the results obtained show that LF region with Local Binary Pattern descriptor produced the most appropriate classifier with an AUC value of 0.912.

show abstract

“…Pattern classification identifies the classes of the target image against the judgement criteria formulated based on the eigenvectors, which are obtained in feature extraction. In the field of image classification, the most popular pattern classifiers include Bayesian classifier, decision tree (DT) classifier, nearest neighbor classifier, neural network (NN) classifier, and support vector machine (SVM) classifier [13][14][15]. Among them, the SVM takes root in statistical learning, and boasts excellent generalization ability.…”

Section: Literature Reviewmentioning

confidence: 99%

An Image Recognition Algorithm of Bolt Loss in Underground Pipelines Based on Local Binary Pattern Operator

Yan¹,

Song²

2020

View full text Add to dashboard Cite

This paper mainly designs an image recognition algorithm of bolt loss in underground pipelines. Firstly, the local binary pattern (LBP) operator was improved to optimize the information content of eigenvectors and enhance the discriminability. Next, the patterns were selected through weighting and ranking, thereby optimizing the original features in each channel of the image. Meanwhile, the main patterns of each channel were classified and identified with the support vector machine (SVM) classifier. The radial basis function (RBF) was taken as the kernel function for the SVM, and the teaching-learning-based optimization (TLBO) algorithm was improved to optimize the SVM parameters. Finally, the improved SVM classifier assigns suitable weights to the predicted class tags of different channels, facilitating the recognition of bolt loss. The research results shed new light on the application of swarm intelligence in image recognition.

show abstract

SVM-PUK Kernel Based MRI-brain Tumor Identification Using Texture and Gabor Wavelets

Cited by 17 publications

References 31 publications

Brain Tumor Diagnosis using Machine Learning: A Review

Brain Tumor Diagnosis using Machine Learning: A Review

Image Texture Analysis for Medical Image Mining: A Comparative Study Direct to Osteoarthritis Classification using Knee X-ray Image

An Image Recognition Algorithm of Bolt Loss in Underground Pipelines Based on Local Binary Pattern Operator

Contact Info

Product

Resources

About