Mammogram Classification in Transform Domain

Samant, Neha S.; Sonar, Poonam

doi:10.1109/spin.2018.8474186

Cited by 4 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the breast tumor tissue analysis, it is noteworthy [Spanhol et al 2016], which focuses on tumor tissue (benign and malignant) image classification through the feature vector creation based on the extraction of characteristics by Local Phase Quantization (LPQ) of the 2-D DFT texture. The discrete cosine transform (DCT) and 2-D DFT are used in the mammogram classification for the tumor detection (benign, malignant and, normal), as shown Samant and Sonar [2018], in which DCT or DFT are applied to the mammographic images and then the gray-kevel co-occurrence matrix (GLCM) features are extracted for classification using the SVM or k-nearest neighbors (KNN), where the 2-D DFT and SVM combination achieves an accuracy of 93.89%.…”

Section: Related Workmentioning

confidence: 99%

“…The two-dimensional (2-D) Discrete Fourier Transform (DFT) has supported breast cancer inspection through imaging, where images features are extracted and classified by methods commonly used in machine learning [Spanhol et al 2016;Samant and Sonar 2018]. Data augmentation is used to increase the number of training images through transformations, enabling the improvement of classification performance and the reduction of overfitting.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CNN-DFT Based Approach Applied to Image Inspection of Railcar Component: A Comparison with Machine Learning Methods

Rocha

Silva

Gomes

et al. 2021

jidm

View full text Add to dashboard Cite

The railcar component inspection is one of the most critical tasks in railway maintenance. The use of image processing, coupled with machine learning has emerged as a solution for replacing current standard methodologies. The spectral analysis gives the frequency representation of a signal and has been largely used in signal processing tasks. In this sense, this work proposes the evaluation of the use of the discrete Fourier transform (DFT) in addition to the spatial representation image of railcar component for an automatic detector of defective parts performed by convolutional neural network (CNN) classification. The most appropriate combination of images of the spatial and frequency domains is compared to the histogram of oriented gradients (HOG) feature descriptor linked to the multilayer perceptron (MLP) and support vector machine (SVM) classification, where data augmentation is investigated to improve the classification performed by all approaches. A search is made for the parameters that best fit the MLP and SVM models for comparison with the proposed approach. The results are given in measure of accuracy in addition to accuracy boxplot, and it showed encouraging results in the combination of spatial image and DFT magnitude combined with data augmentation as CNN inputs, reaching an accuracy of 96.04% and demonstrating statistically to have a significant difference between the comparative methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%