Improved Content Based Medical Image Retrieval using PCA with SURF Features
S.Govindaraju1, B.Mukunthan2
1S.Govindaraju, Assistant Professor (Part-Time Ph.D., Research Scholar), Department of Computer Science, School of Computing, Sri Ramakrishna College of Arts & Science (formerly SNR Sons College), Bharathiar University, Coimbatore-641006, Tamil Nadu, India.
2Dr B.Mukunthan, Assistant Professor, Department of Computer Science, School of Computing, Sri Ramakrishna College of Arts & Science (formerly SNR Sons College), Bharathiar University, Coimbatore-641006, Tamil Nadu, India.
Manuscript received on 19 October 2019 | Revised Manuscript received on 25 October 2019 | Manuscript Published on 29 June 2020 | PP: 112-114 | Volume-8 Issue-10S2 August 2019 | Retrieval Number: J102008810S19/2019©BEIESP | DOI: 10.35940/ijitee.J1020.08810S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In the computer era, the Content Based Image Retrieval system (CBIR) has most widely used in medical field and crime invention. During the last decade, CBIR emerged as powerful tool to efficiently retrieved images visually similar to query image. The basic process behind this concept is representation of image as feature vector and to measure the similarities between the images with distance between their corresponding feature vectors according to some metrics. The finding of correct features to represent images with, as well as the similarity metric that groups visually similar image together, are important milestone in construction of any CBIR system .The work in this paper focused on retrieve the correct query image from a huge number of medical image databases with the help of Principal Component Analysis (PCA) through SURF feature vector detection. The combination of this method produces an accurate and quick response than other conventional methods like SIFT and SURF feature vector based medical image retrieval.
Keywords: CBMIR, SURF, PCA, MRI Images, Fast-Hessian matrix.
Scope of the Article: Knowledge Representation and Retrievals