Retreive Similarly Facial Images Using Unsupervised Label Refinement. |
Author(s): |
| Boopalan K , Bharath University, Selaiyur, Chennai.; A Helen Sharmila, C. Abdul Hakeem College Of Engineering And Technology.; Dr.A Rajesh, CSE,C.Abdul Hakeem College Of Engineering And Technology. |
Keywords: |
| Auto face annotations, SBFA, Face Annotation |
Abstract |
|
Auto face annotations is an important technique that aims to annotate facial images automatically. Search based face annotations (SBFA) is data – driven and model – free. This SBFA can be done by mining the facial images that are weakly labeled these can be taken from World Wide Web (www). One challenge faced by such SBFA paradym is how to effectively exploit .the short list of candidate facial image and their weak labels. This problem can be solved by using unsupervised label refinement (URL) scheme by exploring machine learning technique to enhance the label purely from the weakly labeled data without human manual efforts. We also propose a clustering – based approximation algorithm which can improve the scalability. |
Other Details |
|
Paper ID: IJSRDV2I12313 Published in: Volume : 2, Issue : 12 Publication Date: 01/03/2015 Page(s): 845-848 |
Article Preview |
|
|
|
|
