Feature extraction and classification of ultrasound liver images using haralick texture-primitive features: Application of SVM classifier

Ramamoorthy, Suganya; Rajaram, S.

doi:10.1109/icrtit.2013.6844269

Cited by 15 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The contrast, 46,51 also called the variance or inertia, measures the presence of unexpected transitions of gray levels in the image. It can be calculated as follows…”

Section: Feature Extraction Based On Gray Level Co-occurrence Matrixmentioning

confidence: 99%

See 1 more Smart Citation

An enhanced method for the identification of ferritic morphologies in welded fusion zones based on gray-level co-occurrence matrix: A computational intelligence approach

Souza

Silva

Caldeira

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

This work focuses on the identification of five of the most common ferritic morphologies present in welded fusion zones of low carbon steel through images acquired by photomicrographies. With this regards, we discuss the importance of the gray-level co-occurrence matrix to extract the features to be used as the input of the computational intelligence techniques. We use artificial neural networks and support vector machines to identify the proportions of each morphology and present the error identification rate for each technique. The results show that the use of gray-level co-occurrence extraction allows a less intense computational model with statistical validity and the support vector machine as a computational intelligence technique allows smaller variability when compared to the artificial neural networks.

show abstract

“…The contrast, 46,51 also called the variance or inertia, measures the presence of unexpected transitions of gray levels in the image. It can be calculated as follows…”

Section: Feature Extraction Based On Gray Level Co-occurrence Matrixmentioning

confidence: 99%

“…Correlation 46,51 measures the joint probability occurrence of the specified pixel pairs and it returns a measure of how a pixel is correlated with its neighbor along the whole image…”

Section: Feature Extraction Based On Gray Level Co-occurrence Matrixmentioning

confidence: 99%

An enhanced method for the identification of ferritic morphologies in welded fusion zones based on gray-level co-occurrence matrix: A computational intelligence approach

Souza

Silva

Caldeira

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

show abstract

“…If entropy measured is low then darker portion is darker and lighter portion will become lighter. (15) Dissimilarity:…”

Section: ∑∑mentioning

confidence: 99%

“…Feature selection is performed randomly with the help of ABC algorithm and the selected features are given to SVM classifier with performs classification using RBF kernel (Gaussian) [14]. Gaussian kernel is represented as: Likewise, features selected are given to k-NN classifier and on the basis of those features for k=3, k-NN classifier predicts the class of the input sample [15].…”

mentioning

confidence: 99%

Feature selection using Artificial Bee Colony algorithm for medical image classification

Agrawal

Chandra

2015

2015 Eighth International Conference on Contemporary Computing (IC3)

View full text Add to dashboard Cite

Feature Selection in medical image processing is a process of selection of relevant features, which are useful in model construction, as it will lead to reduced training times and classification model designed will be easier to interrupt. In this paper a meta-heuristic algorithm Artificial Bee Colony (ABC) has been used for feature selection in Computed Tomography (CT Scan) images of cervical cancer with the objective of detecting whether the data given as input is cancerous or not. Starting with segmentation as a first step, performed by implementing Active Contour Segmentation (ACM) algorithm over the images. In this paper a semi-automated the system has been developed so as to obtain the region of interest (ROI). Further, textural features proposed by Haralick are extracted region of interest. Classification is performed using hybridization of Artificial Bee Colony (ABC) and k-Nearest Neighbors (k-NN) algorithm, ABC and Support Vector Machine (SVM). It is observed that combination of ABC with SVM (Gaussian kernel) performs better than combination of ABC with SVM (Linear Kernel) and ABC with K-NN classifier.

show abstract

“…Texture features and their subsets such as Gray Level Co-occurrence Matrix (GLCM) features, owing to their sensitivity to the textured nature of the ultrasound images, have been extensively analyzed for their class separability capabilities. 19,20 Further hybrid combinations of GLCM features and Gray Level Run Length Matrix (GLRLM) features, Law's Texture Energy Measures, Gabor Features, uniform local binary patterns, Hurst's Coefficients, and so forth have been experimented to improve the discrimination capability of the classifier. 9,[21][22][23][24][25][26][27][28][29] Fusion of complementing information extracted from Gray Level Difference Matrix (GLDM) variants prove to be efficient in the enhancement of visualization capability and characterization of cirrhosis, chronic liver, normal liver and HCC progressed to cirrhosis and report an accuracy of 94.5%.…”

Section: Introductionmentioning

confidence: 99%

Particle swarm optimization‐based liver disorder ultrasound image classification using multi‐level and multi‐domain features

Krishnamurthy

Sudhakar²,

Kadhar³

2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Liver ultrasound is a cost-effective, non-invasive, and sufficient technique to diagnose most of the liver disorders. The recent advancements in research in image processing have led to the development of image-based liver disorder classification systems. In spite of being popular in the diagnostic imaging of liver, ultrasound images, owing to their poor quality, render the conventional and state of the art segmentation and feature extraction techniques incapable, to accurately classify a large mixed group of liver disorders; due to the similarities and differences in appearances among the different and same disorders, respectively. Classification of liver disorders using ultrasound images poses various challenges at each phase, from segmentation to classification. There is a need for better segmentation, powerful features, and optimal classification parameter combinations to obtain decent classification accuracy, when a large sub-set of liver disorders is considered. In this work, the region of interest is extracted using iso-contour technique. Feature extraction is performed using multi-level fractal features and multi-domain wavelet-texture features for better discrimination capability. Then, an optimization problem is formulated, for minimizing the five fold cross validation error to classify 10 types of disorders, both focal and diffused, by selecting the best features, suitable classifier, and its parameters using the particle swarm optimization technique for obtaining better classification. An overall accuracy of 91% is obtained using the proposed features in addition to 50% reduction in multi-level fractal feature set which justifies the efficacy of the proposed technique.

show abstract

Feature extraction and classification of ultrasound liver images using haralick texture-primitive features: Application of SVM classifier

Cited by 15 publications

References 10 publications

An enhanced method for the identification of ferritic morphologies in welded fusion zones based on gray-level co-occurrence matrix: A computational intelligence approach

An enhanced method for the identification of ferritic morphologies in welded fusion zones based on gray-level co-occurrence matrix: A computational intelligence approach

Feature selection using Artificial Bee Colony algorithm for medical image classification

Particle swarm optimization‐based liver disorder ultrasound image classification using multi‐level and multi‐domain features

Contact Info

Product

Resources

About