Soft computing-based edge-enhanced dominant peak and discrete Tchebichef extraction for image segmentation and classific
- PDF / 1,638,776 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 5 Downloads / 189 Views
(0123456789().,-volV)(0123456789(). ,- volV)
METHODOLOGIES AND APPLICATION
Soft computing-based edge-enhanced dominant peak and discrete Tchebichef extraction for image segmentation and classification using DCML-IC K. Ramalakshmi1 • V. SrinivasaRaghavan2
Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Texture analysis is a very predominant scope in the area of computer vision and associated fields. In this work, edgeenhanced dominant valley and discrete Tchebichef (EDV-DT) method is presented to eradicate noise and segment image into number of partitions with higher accuracy and lesser time. In EDV-DT method, an edge-enhancing anisotropic diffusion filtering technique is used to perform the preprocessing for MRI, CT and texture features. The adaptive anisotropic diffusion creates scale space and reduces the image noise without removing the texture image content (i.e., edges, lines) that is found to be essential for texture image segmentation. Followed by preprocessing, histogram dominant peak valley segmentation technique is applied to segment the localization of region of interest. Valleys in histogram for the preprocessed images help in segmenting the texture image into equal-sized texture regions. Finally, with the segmented images, discrete Tchebichef moment feature extraction is applied to extract relevant features from the segmented texture image for reducing the dimensionality. This in turn helps in improving the feature extraction rate. Further a deep convolution multinomial logarithmic-based image classification (DCML-IC) model is presented for predicting results via positive and negative fact classification. The proposed system provides the better prediction of accuracy and the prediction of time to compare the other existing methods. Keywords Soft computing Magnetic resonance imaging Computed tomography Adaptive anisotropic diffusion Histogram dominant peak valley Discrete Tchebichef moment
1 Introduction Certain characteristics involved in image processing are gray value, color, reflection features and the textures. Color texture image segmentation was presented in Akbulut et al. (2018) using information pertaining to color and texture in an independent manner. However, edge preservation was not said to be achieved. In Shah et al. (2019), selective segmentation of texture images was applied to smooth the texture in image without losing information pertaining to Communicated by V. Loia. & K. Ramalakshmi [email protected] 1
Department of ECE, P.S.R. Engineering College, Sivakasi, India
2
S.Veerasamy Chettiar College of Engineering and Technology, Puliangudi, India
edges. However, the higher prediction was not said to be achieved. A modified generator called MG-GAN was presented in Chaudhari et al. (2020) for improved cancer classification on gene data. However, prediction accuracy and execution time were found to be compromised. In Cong et al. (2016), an MR image segmentation model based on local and global information was proposed with the purpose of
Data Loading...
