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 96
- Downloads 0
Study on Techniques to Improve Diversity in Recommender Systems
Recommender systems play a significant role in E-Marketing. Many companies got increase in their sale due to establishing their products in the sites like Amazon.com, Netflix.com, and Movielens.com etc. These sites h...
DATA SHARING IN THE CLOUD USING DISTRIBUTED ACCOUNTABILITY
Cloud computing enables highly scalable services to be easily consumed over the Internet on an as-needed basis. A major feature of the cloud services is that users’ data are usually processed remotely in unknown...
Web usage mining: Review on preprocessing of web log file
Web log data is one of the major source which contain all the information regarding the users visited links browsing pattern, time spent on a particular page. A web server log file contain information about user nam...
Device Driver Fault Simulation Using KEDR
t- The failure resilience of a system is very important for availability and reliability. The systems like servers or systems where reliability and availability is highly demanding data loss is unacceptable during...
Segmentation of the White Matter from the Brain fMRI Images
Segmentation of the white matter from the brain fMRI images for the study of brain activities and for the diagnosis for various brain related diseases caused by the changes and damages to regions of the brain conti...