22-01-2011, 06:22 PM
In-Picture Search Algorithm
ANAND BABU.N.B.
2K7705
Overview
Abstract
Introduction
K-tree index structure
R-tree index structure
Advantages and Comparison of K-tree
The Generalized Indexing/Retrieval Model
Visualisation of Retrieval Model
Virtual Node Concept
In-Picture Search Algorithm
Illustration
Conclusion
In-Picture Search Algorithm presentation.pdf (Size: 702.06 KB / Downloads: 57)
ABSTRACT
Researchers are currently more interested in searching for fragments that are similar to a query, than a total data item that is similar to a query; the search interest is for “contains”, not “is”.
This paper presents an O(log n)algorithm, called the “generalized virtual node (GVN)”algorithm.
The GVN algorithm is a search algorithm for data fragments that have similar contents to that of a query.
INTRODUCTION
Image (multimedia) data query can be classified into two different approaches:
•a-whole-picture (a-wholeobject) search
•in-picture (in-object) search
It uses a universal model that is able to represent the characteristic features of any multimedia datatype.
K-TREE INDEX STRUCTURE
A k-tree is a directed graph.
Each node has 2k incoming edges and one outgoing edge with a balanced structure.
ADVANTAGES OF K-TREE
The structure of the k-tree is feature independent.
Since a k-tree is a hierarchical data structure, multiresolution processing can be exploited into this structure.
The complexity of data structure affects only the degree k of the tree.
The k-tree-based feature index for a feature can be used for many types of queries.
ANAND BABU.N.B.
2K7705
Overview
Abstract
Introduction
K-tree index structure
R-tree index structure
Advantages and Comparison of K-tree
The Generalized Indexing/Retrieval Model
Visualisation of Retrieval Model
Virtual Node Concept
In-Picture Search Algorithm
Illustration
Conclusion
In-Picture Search Algorithm presentation.pdf (Size: 702.06 KB / Downloads: 57)
ABSTRACT
Researchers are currently more interested in searching for fragments that are similar to a query, than a total data item that is similar to a query; the search interest is for “contains”, not “is”.
This paper presents an O(log n)algorithm, called the “generalized virtual node (GVN)”algorithm.
The GVN algorithm is a search algorithm for data fragments that have similar contents to that of a query.
INTRODUCTION
Image (multimedia) data query can be classified into two different approaches:
•a-whole-picture (a-wholeobject) search
•in-picture (in-object) search
It uses a universal model that is able to represent the characteristic features of any multimedia datatype.
K-TREE INDEX STRUCTURE
A k-tree is a directed graph.
Each node has 2k incoming edges and one outgoing edge with a balanced structure.
ADVANTAGES OF K-TREE
The structure of the k-tree is feature independent.
Since a k-tree is a hierarchical data structure, multiresolution processing can be exploited into this structure.
The complexity of data structure affects only the degree k of the tree.
The k-tree-based feature index for a feature can be used for many types of queries.