AUTOMATIC IMAGE ANNOTATION USING WEAKLY SUPERVISED GRAPH PROPAGATION
Journal Title: International Journal of Advanced Research in Computer Engineering & Technology(IJARCET) - Year 2013, Vol 2, Issue 2
Abstract
Weakly supervised graph propagation is a method to automatically assign the annotated labels to semantically derived a semantic region. Inputs given are, the training images directory, the labels which are pre-assigned, and the Input Image .In this section, the graph Construction is done with the help of two types of relationships. Consistency Relationship mining, Incongruity Relationship mining. Propagate image labels from patches. The factors needed to be considered are, Patch Label Self-Constraints. Patch–Patch Contextual Relationships, ImagePatch Inclusion Supervision, the supervisions are the supervised and un supervised technique.Weakly supervised graph propagation is a method to automatically assign the annotated labels to semantically derived a semantic region. Inputs given are, the training images directory, the labels which are pre-assigned, and the Input Image .In this section, the graph Construction is done with the help of two types of relationships. Consistency Relationship mining, Incongruity Relationship mining. Propagate image labels from patches. The factors needed to be considered are, Patch Label Self-Constraints. Patch–Patch Contextual Relationships, ImagePatch Inclusion Supervision, the supervisions are the supervised and un supervised technique.Weakly supervised graph propagation is a method to automatically assign the annotated labels to semantically derived a semantic region. Inputs given are, the training images directory, the labels which are pre-assigned, and the Input Image .In this section, the graph Construction is done with the help of two types of relationships. Consistency Relationship mining, Incongruity Relationship mining. Propagate image labels from patches. The factors needed to be considered are, Patch Label Self-Constraints. Patch–Patch Contextual Relationships, ImagePatch Inclusion Supervision, the supervisions are the supervised and un supervised technique.Weakly supervised graph propagation is a method to automatically assign the annotated labels to semantically derived a semantic region. Inputs given are, the training images directory, the labels which are pre-assigned, and the Input Image .In this section, the graph Construction is done with the help of two types of relationships. Consistency Relationship mining, Incongruity Relationship mining. Propagate image labels from patches. The factors needed to be considered are, Patch Label Self-Constraints. Patch–Patch Contextual Relationships, ImagePatch Inclusion Supervision, the supervisions are the supervised and un supervised technique.
Authors and Affiliations
Kalaivani. R , Thamaraiselvi. K
Keywords
Related Articles
- EP ID EP125820
- DOI -
- Views 104
- Downloads 0
Review and Study of Different Methods for Author Identification
As assessment of an individual has become an important aspect in the field of distance learning, it is difficult for these institutions to verify whether the individual participated is the person enrolled. Author i...
Comparative Study of Two-way Finite Automata and Turing machine
Two-way finite Automata are termed as read only Turing machine. Two way finite automata is one of variant of Turing machine, which is blessed with an infinite tape, and could be used by tape head to read or write i...
Design and Verification Eight Port Router for Network on Chip
Multiprocessor system on chip is emerging as a new trend for System on chip design but the wire and power design constraints are forcing adoption of new design methodologies. Researchers pursued a scalable soluti...
Feature Based Image Sequence Retargeting in the Uncompressed Video Domain
The system propose a video retargeting algorithm to resize images based on the extracted saliency information from the compressed domain. The system utilizes DCT coefficients in JP2 bit stream to perform saliency d...
PSO optimized reduced order PID Controller design
A novel algorithm is proposed to obtain a reduced model for stable linear time invariant continuous system. A PSO PID controller is designed for the reduced order model to meet the desired performance specifications by u...