Magnetic resonance image retrieval based on contour to centroid triangulation with shape feature similarity

Authors:
Byung K. Jung;Seong H. Son;Jeong K. Pack
Affiliations:
South Dakota State University Brookings, SD;Telecommunications Research Institute (ETRI), DaeJeon, South Korea;Chungnam National University, South Korea
Venue:
Proceedings of the 2013 Research in Adaptive and Convergent Systems
Year:
2013

Citing 7
Cited 0

A shape recognition scheme based on relative distances of feature points from the centroid

Pattern Recognition
Content-Based Image Retrieval at the End of the Early Years

IEEE Transactions on Pattern Analysis and Machine Intelligence
Region-based shape representation and similarity measure suitable for content-based image retrieval

Multimedia Systems
Classification for Breast MRI Using Support Vector Machine

CITWORKSHOPS '08 Proceedings of the 2008 IEEE 8th International Conference on Computer and Information Technology Workshops
Robust shape similarity retrieval based on contour segmentation polygonal multiresolution and elastic matching

Pattern Recognition
Plant species identification using leaf image retrieval

Proceedings of the ACM International Conference on Image and Video Retrieval
A sectorized object matching approach for breast magnetic resonance image similarity study

Proceedings of the 2012 ACM Research in Applied Computation Symposium

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present an image retrieval method based on contour to centroid triangulation with shape feature similarity. We assume test images and database images used in this paper are all single objects that are segmented by known algorithms such as SVM and K-means algorithms. From these classified binary images, we propose novel Shape based image retrieval method integrating sectored characteristic points to the Contour to Centroid Triangulation (CTCT) method using Unique Representation Grid (URG) as shape feature that can perform as the filtering process. The experimental result shows proposed method has improved conventional CTCT in retrieving medical object image compared to conventional CTCT method with 79 percent match rate while CTCT showed 33 percent match.