This paper is published in Volume-3, Issue-1, 2017
Area
Multimedia Computing
Author
Anuradha Karlekar
Org/Univ
Siddhivinayak College of Higher Education & Research, RTU, India
Keywords
Graph-based Image Representation, Dynamic Region Merging, Frequent Approximate Sub-graphs, Graph Clusturing, Segmentation, Watershed, VEAM (Vertex and Edge Approximate graphMiner).
Citations
IEEE
Anuradha Karlekar. Graph-Based Image Search Using Clustering Approach, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.
APA
Anuradha Karlekar (2017). Graph-Based Image Search Using Clustering Approach. International Journal of Advance Research, Ideas and Innovations in Technology, 3(1) www.IJARIIT.com.
MLA
Anuradha Karlekar. "Graph-Based Image Search Using Clustering Approach." International Journal of Advance Research, Ideas and Innovations in Technology 3.1 (2017). www.IJARIIT.com.
Anuradha Karlekar. Graph-Based Image Search Using Clustering Approach, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.
APA
Anuradha Karlekar (2017). Graph-Based Image Search Using Clustering Approach. International Journal of Advance Research, Ideas and Innovations in Technology, 3(1) www.IJARIIT.com.
MLA
Anuradha Karlekar. "Graph-Based Image Search Using Clustering Approach." International Journal of Advance Research, Ideas and Innovations in Technology 3.1 (2017). www.IJARIIT.com.
Abstract
From the many approaches for image classification, the graph-based approach is gaining popularity due to its ability in reflecting global image properties. In this report, VEAM (Vertex and Edge Approximate graphMiner) algorithm is used for mining frequently connected sub-graphs over undirected and labeled graph collections. Slight variations of the data, keeping the topology of the graphs, are allowed. In this report, we have proposed graph-based image representation by using Dynamic Region Merging (DRM) technique. DRM is used with watershed segmentation. It can tolerate some variations for grouping meaningful regions.
