Learning for Meta-Recognition

Autor(es)

Scheirer, Walter J. ^[1] ; Rocha, Anderson de Rezende ^[2] ; Parris, Jonathan ^[1] ; Boult, Terrance E. ^[1]

Afiliação do(s) autor(es)

^[1] Univ Colorado, Dept Comp Sci, Colorado Springs, CO 80907 - USA

^[2] Univ Estadual Campinas, Inst Comp, BR-13083852 Sao Paulo - Brazil

• Tipo de documento: Artigo Científico
• Fonte: IEEE Transactions on Information Forensics and Security; v. 7, n. 4, p. 1214-1224, AUG 2012.
• Citações Web of Science: 6

Resumo

In this paper, we consider meta-recognition, an approach for postrecognition score analysis, whereby a prediction of matching accuracy is made from an examination of the tail of the scores produced by a recognition algorithm. This is a general approach that can be applied to any recognition algorithm producing distance or similarity scores. In practice, meta-recognition can be implemented in two different ways: a statistical fitting algorithm based on the extreme value theory, and a machine learning algorithm utilizing features computed from the raw scores. While the statistical algorithm establishes a strong theoretical basis for meta-recognition, the machine learning algorithm is more accurate in its predictions in all of our assessments. In this paper, we present a study of the machine learning algorithm and its associated features for the purpose of building a highly accurate meta-recognition system for security and surveillance applications. Through the use of feature-and decision-level fusion, we achieve levels of accuracy well beyond those of the statistical algorithm, as well as the popular ``cohort{''} model for postrecognition score analysis. In addition, we also explore the theoretical question of why machine learning-based algorithms tend to outperform statistical meta-recognition and provide a partial explanation. We show that our proposed methods are effective for a variety of different recognition applications across security and forensics-oriented computer vision, including biometrics, object recognition, and content-based image retrieval. (AU)

• Processo FAPESP: 10/05647-4 - Computação forense e criminalística de documentos: coleta, organização, classificação e análise de evidências
• Beneficiário: Anderson de Rezende Rocha
• Linha de fomento: Auxílio à Pesquisa - Apoio a Jovens Pesquisadores