{"id":179,"date":"2021-02-17T01:08:57","date_gmt":"2021-02-17T01:08:57","guid":{"rendered":"http:\/\/enriquegortiz.com\/wordpress\/enriquegortiz-staging\/?post_type=fw-portfolio&p=179"},"modified":"2022-12-18T19:02:31","modified_gmt":"2022-12-18T19:02:31","slug":"face-recognition-for-web-scale-datasets","status":"publish","type":"fw-portfolio","link":"https:\/\/enriquegortiz.com\/wordpress\/enriquegortiz\/project\/face-recognition-for-web-scale-datasets\/","title":{"rendered":"Face Recognition for Web-Scale Datasets"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\r\n\r\n
\r\n
\r\n\t\t

E. G. Ortiz<\/a><\/strong> and B. C. Becker<\/a>. \u00a0\"Face Recognition for Web-Scale Datasets\"<\/a>.<\/em>\u00a0ELSEVIER Computer Vision and Image Understanding, 2013.<\/p>

Related Publication:
B. C. Becker<\/a>\u00a0and E. G. Ortiz<\/a><\/strong>. \u201cEvaluating Open-Universe Face Identification on the Web<\/a>\u201d. IEEE CVPR Workshop on Analysis and Modeling of Faces and Gestures, 2013. [Project Page<\/a>]<\/p>

B. C. Becker, E. G. Ortiz.\u00a0\"Evaluation of Face Recognition Techniques for Application to Facebook\"<\/a>.<\/em>\u00a0IEEE International Conference on Automatic Face and Gesture Recognition.<\/p>

\"Open-Universe<\/p>

Motivation<\/h1>

With the increasing pervasiveness of digital cameras, the Internet, and social networking, there is a growing need to catalog and analyze large collections of photos. Because photo interest is largely determined by who appears in the picture, labeling photos with identities is particularly important. In fact, popular social networks such as Facebook allow users to place tags on photos to label people, encouraging collaboratively organized photo albums amongst friends. Imagine millions of social network users needing to tag their photos: such web-scale labeling problems present a real challenge and fascinating opportunity for automation by face recognition.<\/p>

Linearly Approximated Sparse Representation-based Classification (LASRC)<\/h1>

Method details coming soon.<\/p>

Results<\/h1>

\"\"<\/p>

SRC based methods outperform all other methods in terms of precision and recall. It is important to notice that our method performs comparably to standard SRC, but with a 100x speedup as seen in the timing diagram below.<\/p>

\"\"<\/p>

Timeline of all steps in the entire face recognition system. All times reported with a single core of a 2.27 GHz machine.<\/p>

MATLAB Face Recognition Toolbox<\/h1>

To foster future research and improvements, we are releasing a full\u00a0MATLAB Face Recognition Evaluator (25 MB)<\/a><\/strong>\u00a0that includes our LASRC algorithm as well as all others we have compared against this study: NN, SVM, SVM-KNN, SRC, Mtjsrc, LLC, KNN-SRC, LRC, L2, and CRC_RLS.<\/p>