Computer Based Advanced Approach for MRI Image Classification Using Neural Network With The Texture Features Extracted

Neelakanteswara, P.; Bharadwaja, Doradla; Viswanath, P.; Basha, Cmak Zeelan; Savarapu, Pradeep Raj

doi:10.1109/icosec49089.2020.9215332

Cited by 7 publications

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

A novel parallel unsupervised texture segmentation approach

2023

SN Appl. Sci.

View full text Add to dashboard Cite

This study presents a new idea for unsupervised texture segmentation from the angle of bionics. According to this idea, a novel approach called “side-by-side superposition unsupervised texture segmentation (SSUTS)” is designed. When doing texture segmentation in this paper, the traditional time–frequency analysis-based methods are improved by introducing the analytic phase theory and the Bi-dimensional Empirical mode decomposition (BEMD) theory. Experiments prove that the SSUTS approach is effective in texture segmentation of different styles. Article Highlights From the angle of bionics, an effective approach called “side-by-side superposition unsupervised texture segmentation (SSUTS)” is proposed in this paper. To get reasonable choice of texture segmentation tool for the approach of SSUTS, some classic texture segmentation methods are analyzed and compared in this paper. This paper shows and explains the improvements in texture segmentation, when the Bi-dimensional Empirical Mode Decomposition (BEMD) theory and the two-dimensional analytic phase theory are applied in some classic texture segmentation methods.

show abstract