Loading...
Please wait, while we are loading the content...
Similar Documents
Uma Abordagem Escalável para Manutenção de Galeria de Faces
| Content Provider | Semantic Scholar |
|---|---|
| Author | Carlos, Gerson De Paulo Pedrini, Hélio |
| Copyright Year | 2012 |
| Abstract | Face recognition has received increased attention due to its application in biometrics and surveillance systems, emerging two main objectives, verification and identification of faces. The first one aims at accepting or rejecting an identity assigned to a correct face, whereas the second aims at, given an unknown face, finding the best identity to it from a gallery of known faces. For the identification task, discriminative approaches such as the one-against-all method have achieved higher accuracy than descriptive approaches such as eigenfaces. However, such methods have scalability problems when the gallery with known individuals increases, since it is necessary to rebuild all discriminative models. This work describes and evaluates a novel method for making the process of gallery maintenance more efficient. This method is based on the construction of one-againstsome models with random selection of subset of subjects and on the use of a priority queue to match test samples. Experimental results obtained by applying the proposed method on a publicly available face data set are presented and compared with other approaches in the literature. Keywords-Face Identification; Partial Least Squares; Face Gallery. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://homepages.dcc.ufmg.br/~william/papers/paper_2012_WUW.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
