Matlab Code for Face Recognition using Combined SIFT


Face Recognition using Combined SIFT

100 in stock

SKU: Face Recognition using Combined SIFT Category:



People are sometimes known by their faces. Developments the accomplished few decades accept enabled animal to mechanically do the identification method. Most of instructed algorithms are concerning properly distinguishing face photos and assignment them to an individual within the info. This study focuses on face recognition supported improved SIFT algorithmic program. Results indicate the prevalence of the planned algorithmic program over the SIFT. To evaluate the planned algorithmic program, it’s applied on ORL info and so compared to different face detection algorithms as well as  Gabor and SIFT


Facial recognition system could be a medicine mechanism of distinguishing numerous expressions. automatic face recognition system is often employed in security applications however conjointly used heavily in different applications. automatic face recognition system involves variety of techniques. These techniques are primarily related to feature extraction. face could be a house of distinct expression that varies with time regularly. therefore economical classifier is needed that generate variety of best options as amount to represent entire face expression residing on face. best feature choice is tough with single classifier therefore properties of multiple classifiers are collaborated along to attain best classifier. during this the non-domination based mostly improvement technique has been introduced that acknowledge the renowned and unknown faces with a semi-supervised classifier that are supported the various eventualities.


Image matching could be a basic method in image process and plays a vital role in photogrammetric and remote sensing processes  PCA. The technique employed in making Eigen faces and mistreatment them for recognition is additionally used outside of automatic face recognition. this adjustment is additionally acclimated for autography analysis, lip reading, articulation recognition, assurance language/hand gestures estimation and medical imaging analysis. about the tactic is abundantly acute to scale, therefore, a low-level preprocessing continues to be all-important for calibration normalization


In planned technique we tend to ar mistreatment SIFT algorithmic program for face recognition. SIFT is An economical matching algorithmic program that has with success been accustomed match the remote sensing pictures mechanically. However, feature extraction operator continues to be a serious weakness of the algorithmic program. Despite the high procedure quality, it may be partly controlled in feature extraction from remote sensing pictures. To alleviate the procedure quality whereas rising the potency, this study limit the feature extraction operators in SIFT yet as key-points extraction operators to an exact variety to develop seek out the compatible matching




  • High accuracy
  • No complexity


  • Biometric applications
  • Security analysis


  • MATLAB 7.14 or above versions


People square measure sometimes known by their faces. Developments within the past few decades has enabled human to mechanically do the identification method. Early face recognition algorithmic program used straightforward geometric models. Now, face recognition method employs the advanced applied mathematics science and matching strategies. enhancements and innovations in face recognition technology throughout ten to fifteen past years have propelled it to this standing. Face recognition is applicable for each investigation and identification. This study provided a replacement face recognition technique supported SIFTS options. rising SIFT algorithmic program, this study targeted on face recognition. Results indicated the prevalence of the planned algorithmic program over the SIFT.. The results obtained from numerous tests showed that the planned algorithmic program, with 98.75% accuracy and run time of four.3 seconds, is a lot of economical and correct than different algorithms nonetheless the run time was but others. 


[1] David G. Lowe(2004), Distinctive image features from scale-invariant key points, International journal of computer vision 60.

[2] W. Zhao, R. Chellappa, P. J. Phillips, and A. Rosenfeld(2003). Face recognition: A literature survey. ACM Computing Surveys, 399-458 ,December.

[3] N. Belhumeur Peter, Joao P. Hespanha, David J. Kriegman(1996).Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions On Pattern Analysis And Machine Intelligence,711-720, July.

[4] Daniel L. Swets, John Weng (1996), Using discriminant eigen features for image retrieval, IEEE Transactions On Pattern Analysis And Machine Intelligence, 18(8):831-836, August.

[5] Matthew A. Turk, Alex P. Pentland (1991).Face recognition using eigenfaces. In Proceedings CVPR 91., IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6] Fisher A (1936), The use of multiple measures in taxonomic problems. Ann. Eugenics, 7:197-188.

[7] Wei Xia, Shouyi Yin and Peng Ouyang (2013)A High Precision Feature Based on LBP and Gabor Theory forFace Recognition”Sensors 2013, 13, 4499-4513; doi:10.3390/s130404499,ISSN 1424-8220.



There are no reviews yet.

Be the first to review “Matlab Code for Face Recognition using Combined SIFT”

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.