DISCRETE TCHEBICHEF EXTRACTION FOR IMAGE CLASSIFICATION USING MEDICAL IMAGES WITH VARIOUS DATASETS AND APPLICATIONS

Image processing converts the image into digital form with the objective of extracting essential for future use. During the last few decades, texture is considered to be one of the subjects of study in the recent image processing community. Texture analysis is a very predominant scope in the area of computer vision and associated fields. Image segmentation partitions the image into diverse numbers of nonintersecting region. Several methods have been researched, however, the segmentation time and prediction performance was not improved. In this work, Edge-enhanced 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 Dif usion Filtering technique is used to perform the pre-processing for MRI, CT and texture features. The adaptive anisotropic dif usion 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 pre-processing, Histogram Dominant Peak Valley Segmentation technique is applied to segment the localization of region of interest. Valleys in histogram for the pre-processed images help in segmenting the texture image into equal-sized texture regions. This in turn assists in reducing the segmentation time, besides increasing the segmentation accuracy. Finally, with the segmented images, Discrete Tchebichef Moment Feature Extraction is performed to extract relevant features from the segmented texture image for reducing the dimensionality. This in turn helps in improving the feature extraction rate