AUTOMATIC IMAGE ANNOTATION USING WEAKLY SUPERVISED GRAPH PROPAGATION 

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

SHOE: A Platform for Semantic Web Language Usage and Analysis  

The World Wide Web before Web 2.0 is an immense search for expertise has superior in modern years. Although in the sequence resource with near unlimited potential for the reason that there are tranquil many types o...

A Latest Method for Improving Resolution in Three Dimension Imaging Light Detection and Ranging 

Light detection and ranging (LiDAR) has recently emerged as a powerful tool for direct the three dimension (3D) measurement. 3D imaging LiDAR has found widespread applications in aerospace reconnaissance, deep-space...

Energy efficient and Demand based Topology Maintenance for various network traffic conditions  

Due to the nodes’ limited resource in the adhoc networks, the scalability is the crucial for network operation. Energy efficient topology in Ad-hoc networks can be achieved mainly in two different ways. In the firs...

An Efficient Sharing of Personal Health Records Using DABE in Secure Cloud Environment

Cloud computing has emerged as one of the most influential paradigms in the IT industry for last few years. Normally data owners and service providers are not in the same trusted domain in cloud computing. Personal healt...

Problems of character segmentation in Handwritten Text Documents written in Devnagari Script

Character segmentation is a process of dividing a word from a text document. Document from which the words are to be used may be handwritten or printed text. In this paper, prime focus is on the problems which may occ...

Download PDF file
  • EP ID EP125820
  • DOI -
  • Views 77
  • Downloads 0

How To Cite

Kalaivani. R, Thamaraiselvi. K (2013). AUTOMATIC IMAGE ANNOTATION USING WEAKLY SUPERVISED GRAPH PROPAGATION . International Journal of Advanced Research in Computer Engineering & Technology(IJARCET), 2(2), 855-860. https://europub.co.uk/articles/-A-125820