FaceLab: a tool for performance evaluation of face recognition strategies

Gespeichert in:
Bibliographische Detailangaben
Titel: FaceLab: a tool for performance evaluation of face recognition strategies
Autoren: TISATO, FRANCESCO, SCHETTINI, RAIMONDO, CUSANO, CLAUDIO, COLOMBO, ALESSANDRO, Caflisch, L.
Quelle: SPIE Proceedings. 6061:60610V
Verlagsinformationen: SPIE, 2006.
Publikationsjahr: 2006
Schlagwörter: performance evaluation, face recognition strategies, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology
Beschreibung: This paper presents FaceLab, an innovative, open environment created to evaluate the performance of face recognition strategies. It simplifies, through an easy-to-use graphical interface, the basic steps involved in testing procedures such as data organization and preprocessing, definition and management of training and test sets, definition and execution of recognition strategies and automatic computation of performance measures. The user can extend the environment to include new algorithms, allowing the definition of innovative recognition strategies. The performance of these strategies can be automatically evaluated and compared by the tool, which computes several performance measures for both identity verification and identification scenarios.
Publikationsart: Article
Conference object
ISSN: 0277-786X
DOI: 10.1117/12.648347
Zugangs-URL: https://www.spiedigitallibrary.org/conference-proceedings-of-spie/6061/1/FaceLab--a-tool-for-performance-evaluation-of-face-recognition/10.1117/12.648347.full
https://spiedigitallibrary.org/proceeding.aspx?articleid=728341
https://boa.unimib.it/handle/10281/13988?mode=simple.14
https://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=728341
https://hdl.handle.net/10281/13988
https://doi.org/10.1117/12.648347
Dokumentencode: edsair.doi.dedup.....757d389a072352a8c48f96b5f4267c6f
Datenbank: OpenAIRE
Beschreibung
Abstract:This paper presents FaceLab, an innovative, open environment created to evaluate the performance of face recognition strategies. It simplifies, through an easy-to-use graphical interface, the basic steps involved in testing procedures such as data organization and preprocessing, definition and management of training and test sets, definition and execution of recognition strategies and automatic computation of performance measures. The user can extend the environment to include new algorithms, allowing the definition of innovative recognition strategies. The performance of these strategies can be automatically evaluated and compared by the tool, which computes several performance measures for both identity verification and identification scenarios.
ISSN:0277786X
DOI:10.1117/12.648347