Busca avançada
Ano de início
Entree
(Referência obtida automaticamente do Web of Science, por meio da informação sobre o financiamento pela FAPESP e o número do processo correspondente, incluída na publicação pelos autores.)

Open set source camera attribution and device linking

Texto completo
Autor(es):
Costa, Filipe de O. [1] ; Silva, Ewerton [1] ; Eckmann, Michael [2] ; Scheirer, Walter J. [3, 4] ; Rocha, Anderson [1]
Número total de Autores: 5
Afiliação do(s) autor(es):
[1] Univ Campinas Unicamp, Inst Comp, BR-1308385 Campinas, SP - Brazil
[2] Skidmore Coll, Dept Math & Comp Sci, Saratoga Springs, NY 12866 - USA
[3] Harvard Univ, Sch Engn & Appl Sci, Cambridge, MA 02138 - USA
[4] Harvard Univ, Ctr Brain Sci, Dept Mol & Cellular Biol, Cambridge, MA 02138 - USA
Número total de Afiliações: 4
Tipo de documento: Artigo Científico
Fonte: PATTERN RECOGNITION LETTERS; v. 39, n. SI, p. 92-101, APR 1 2014.
Citações Web of Science: 25
Resumo

Camera attribution approaches in digital image forensics have most often been evaluated in a closed set context, whereby all devices are known during training and testing time. However, in a real investigation, we must assume that innocuous images from unknown devices will be recovered, which we would like to remove from the pool of evidence. In pattern recognition, this corresponds to what is known as the open set recognition problem. This article introduces new algorithms for open set modes of image source attribution (identifying whether or not an image was captured by a specific digital camera) and device linking (identifying whether or not a pair of images was acquired from the same digital camera without the need for physical access to the device). Both algorithms rely on a new multi-region feature generation strategy, which serves as a projection space for the class of interest and emphasizes its properties, and on decision boundary carving, a novel method that models the decision space of a trained SVM classifier by taking advantage of a few known cameras to adjust the decision boundaries to decrease false matches from unknown classes. Experiments including thousands of unconstrained images collected from the web show a significant advantage for our approaches over the most competitive prior work. (C) 2013 Elsevier B.V. All rights reserved. (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