Open AccessMedical Image Retrieval using Dual Tree Complex Wavelet Transform and Principal Component Analysis with Haralick Texture Features
Author(s) -
C. Keerthika,
R. Jinuraj K.
Publication year - 2020
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.e6511.018520
Subject(s) - artificial intelligence , pattern recognition (psychology) , complex wavelet transform , principal component analysis , computer science , mahalanobis distance , computer vision , image retrieval , wavelet transform , image texture , feature (linguistics) , precision and recall , pixel , wavelet , image processing , discrete wavelet transform , image (mathematics) , linguistics , philosophy
Noise and distortion occurs in all types of medical images (Computed Tomography (CT), Magnetic Resonance Imaging (MRI.)..) and are unavoidable during the stages of image acquisition. We use medical image retrieval to extract the images from database by texture, shaptrix or color features. We use Dual Tree Complex Wavelet Transform (DTCWT) and Principal Component Analysis (PCA). DTCWT extracts the information of images. PCA compress the images. It also minimizes the feature vectors dimensions of all images. Haralick texture features are extracted from images with the co-occurrence matrix. This matrix describes the relationship of pixels. The similar images are found by calculating the similarity measure of the query image and all images in database by Mahalanobis distance. This method retrieves the similar images from database with respect to the input image provided by the user. The performance of the proposed algorithm can be found by precision and recall measures for evaluation. This system can be used in hospitals, clinics etc., for detecting diseases earlier.