Implementation of Face Annotation with refined label content

 

Mr. Anuj Rai1*, Prof. Piyush Singh2

1M. Tech Student, RKDFIST, Bhopal
2Assistant Professor, RKDFIST, Bhopal

*Corresponding Author Email: anujrai31@gmail.com

 

ABSTRACT:

A face annotation has many  applications the main part of  based face  annotation is to management of most same  facial images and their weak data labels. These problem, different methods are adopted. The efficiency  of annotating systems are improved  by using these methods.  This paper proposes a review on various  techniques used for detection and analysis of each technique. Combine techniques are used in retrieving facial images based on  query. So it is effective to label the images with their exact names. The detected face recognition techniques can annotate the faces with exact data labels which will help to improve the detection more efficiently.

 

For a set of semantically similar images Annotations from them. Then content-based search is performed on this set to retrieve visually similar images, annotations are mined from the data descriptions. The method is to find the face data association in images with data label. The task of face name association should obey the   constraint  face can  be  a data appearing in its associated  a name can be given  to at most one face and  a face can be assigned to one name. Many methods have proposed to used this while suffering from some common

 

KEYWORDS: Face Annotation, Content Based.

 


 

INTRODUCTION:

The face annotation is an important technique that  to annotate facial feature images automatically.   The  face annotation can be useful  to many Applications. The face annotation approaches are often treated as an extended face recognition issue, where different classification models are trained model based face annotation time consuming for collect a large amount of human labelled  facial images.

Few studies have attempted to get a search based annotation for facial image annotation by mining to tackle the automated face annotation by exploiting content-based image retrieval method. The  objective of is to assign correct data labels  given query facial image. It is usually time consuming and cost to collect a large amount of human data labeled training facial images. It is usually difficult to the models when new data or new persons are added, in which an  retraining process is usually required.

 

The annotation or  recognition performance often  poorly when the number of persons or classes is very large.

Modulus

·        Database creation with image in binary bit format array

·        Scanning BMP Format  Reading per pixel value in RGB value

·        Facial feature indexing  with data label

·        Similar face retrieval with value

·        Detected Final output

·        Refined data

 

METHODOLOGY:

1.    The system fed with a  image.

2.    Extracting facial Features

3.    The important data is extracted from the sample. Using software where many algorithms are available  The outcome    which is a reduced set of data that represents the important  features of the enrolled user's face.

4.    Comparison new Templates

5.    This depends on the application at hand. That  identification purposes, It  will be a comparison between the stored on a database.

6.    Declaring a Match with data

7.    The face recognition system will  return a match The intervention of a human operator will be required in order to select the best fit from the candidate data.

 

 

Data Labeling

Data labeling procedure. The procedure are compared with data labeling on  spectral clustering. After initial labeling with  partial clustering, The proposed  labeling algorithm and spectral clustering  to label the rest of the faces. We  recluster label  faces, then data label the cluster, which  similarity variation is the lowest. proposed data labeling algorithm get  higher efficiency at the beginning of data labeling,

 

Software

C#. NET is also compliant with Common Language that  supports structured exception handling. The set of rules and constructs that are supported by the Common Language Runtime. It  is the runtime environment provided by the .NET Framework; it manages the execution of the code and also makes the development process easier by providing services process.   

 

Flow Diagram

 

 

CONCLUSION:

The face annotation on labeled images. So  research works and new methods are being proposed. The research in this field  importance as it is very useful in  searching and social Media. The future work will work on multi person data task and thereby  efficiency and accuracy of result. If the techniques are implemented properly, then the data  label problem will be solved.

 

REFERENCES:

1.       X. J. Wang, L. Zhang, F. Jing, and W.-Y. Ma, “AnnoSearch: Image Auto-Annotation by Search,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition (CVPR), pp. 1483- 1490, 2006.

2.       D. Wang, S.C.H. Hoi, Y. He, and J. Zhu, “Retrieval-Based Face Annotation by Weak Label Regularized Local Coordinate Coding,” Proc. 19th ACM Int’l Conf. Multimedia (Multimedia), pp. 353-362, 2011.

3.       A.W.M. Smeulders, M. Worring, S. Santini, A. Gupta, and R. Jain, “Content-Based Image Retrieval at the End of the Early Years,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 12, pp. 1349-1380, Dec. 2000.

4.       Dayong Wang, Steven C.H. Hoi, Ying He, and Jianke Zhu,” Mining Weakly Labeled Web Facial Images for Search-Based Face Annotation” IEEE Transactions on Knowledge and Data Engineering, vol. 26, no. 1, January 2014

5.       W. Dong, Z. Wang, W. Josephson, M. Charikar, and K. Li, “Modeling LSH for Performance Tuning,” Proc. 17th ACM Conf. Information and Knowledge Management (CIKM), pp. 669-678, 2008.

6.       C. Siagian and L. Itti, “Rapid Biologically-Inspired Scene Classification Using Features Shared with Visual Attention,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.29, no. 2,pp. 300-312, Feb. 2007.

7.       Y. Tian, W. Liu, R. Xiao, F. Wen, and X. Tang, “A Face Annotation Framework with Partial Clustering and Interactive Labeling,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2007.

 

 

Received on 27.03.2016            Accepted on 28.05.2016           

© EnggResearch.net All Right Reserved

Int. J. Tech. 2016; 6(1): 14-16

DOI: 10.5958/2231-3915.2016.00004.3