Comparison of SVM and ANN classifier for mammogram classification using ICA features

Phadke, Anuradha C.; Rege, Priti P.

doi:10.2495/icie130581

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accuracy has priority for testing the performance of mammogram classification system. The accuracy of proposed system is greater than the system by Phadke and Rege [8].…”

Section: Resultsmentioning

confidence: 63%

“…Though the accuracy obtained in the proposed method is slightly less than the accuracy reported by Shanthi & Murali Bhaskaran [9], proposed method is capable of detecting five types of abnormalities namely microcalcifications (CALC), circumscribed masses (MASS), spiculated masses (SPIC) architectural distortions (ARCH) and ill-defined or miscellaneous masses (MISC). In the work by Phadke & Rege [8], sensitivity is higher than the sensitivity of the proposed system. As the former technique classifies only malignant samples whereas proposed system classifies both malignant and benign abnormalities from normal samples.…”

Section: Resultsmentioning

confidence: 74%

“…It is reported that classification accuracy is improved because of the proposed feature selection method. The framework by Phadke & Rege [8] is based on combining principal component analysis (PCA) and independent component analysis (ICA) for deriving features of normal and malignant tissues in mammograms. Classification of malignant tissues is done by SVM and ANN Classifier and their performance is compared.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fusion of local and global features for classification of abnormality in mammograms

Phadke¹,

Rege²

2016

Sādhanā

View full text Add to dashboard Cite

Mammography is the most widely used tool for the early detection of breast cancer. Computerbased algorithms can be developed to improve diagnostic information in mammograms and assist the radiologist to improve diagnostic accuracy. In this paper, we propose a novel computer aided technique to classify abnormalities in mammograms using fusion of local and global features. The objective of this work is to test the effectiveness of combined use of local and global features in detecting abnormalities in mammograms. Local features used in the system are Chebyshev moments and Haralick's gray level co-occurrence matrix based texture features. Global features used are Laws texture energy measures, Gabor based texture energy measures and fractal dimension. All types of abnormalities namely clusters of microcalcifications, circumscribed masses, spiculated masses, architectural distortions and ill-defined masses are considered. A support vector machine classifier is designed to classify the samples into abnormal and normal classes. It is observed that combined use of local and global features has improved classification accuracy from 88.75% to 93.17%.

show abstract

“…Accuracy has priority for testing the performance of mammogram classification system. The accuracy of proposed system is greater than the system by Phadke and Rege [8].…”

Section: Resultsmentioning

confidence: 63%

Section: Resultsmentioning

confidence: 74%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation