Utilize este identificador para referenciar este registo: https://hdl.handle.net/10216/98583
Autor(es): Francisco P. M. Oliveira
João Manuel R. S. Tavares
Todd C. Pataky
Título: Rapid pedobarographic image registration based on contour curvature and optimization
Data de publicação: 2009
Resumo: Image registration, the process of optimally aligning homologous structures in multiple images, has recently been demonstrated to support automated pixel-level analysis of pedobarographic images and, subsequently, to extract unique and biomechanically relevant information from plantar pressure data. Recent registration methods have focused on robustness, with slow but globally powerful algorithms. In this paper, we present an alternative registration approach that affords both speed and accuracy, with the goal of making pedobarographic image registration more practical for near-real-time laboratory and clinical applications. The current algorithm first extracts centroid-based curvature trajectories from pressure image contours, and then optimally matches these curvature profiles using optimization based on dynamic programming. Special cases of disconnected images (that occur in high-arched subjects, for example) are dealt with by introducing an artificial spatially linear bridge between adjacent image clusters. Two registration algorithms were developed: a 'geometric' algorithm, which exclusively matched geometry, and a 'hybrid' algorithm, which performed subsequent pseudo-optimization. After testing the two algorithms on 30 control image pairs considered in a previous study, we found that, when compared with previously published results, the hybrid algorithm improved overlap ratio (p = 0.010), but both current algorithms had slightly higher mean-squared error, assumedly because they did not consider pixel intensity. Nonetheless, both algorithms greatly improved the computational efficiency (25 +/- 8 and 53 +/- 9ms per image pair for geometric and hybrid registrations, respectively). These results imply that registration-based pixel-level pressure image analyses can, eventually, be implemented for practical clinical purposes.
Assunto: Engenharia mecânica, Engenharia mecânica
Mechanical engineering, Mechanical engineering
Áreas do conhecimento: Ciências da engenharia e tecnologias::Engenharia mecânica
Engineering and technology::Mechanical engineering
URI: https://repositorio-aberto.up.pt/handle/10216/98583
Tipo de Documento: Artigo em Revista Científica Internacional
Condições de Acesso: restrictedAccess
Aparece nas coleções:FEUP - Artigo em Revista Científica Internacional

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
  Restricted Access
273.16 kBAdobe PDF    Request a copy from the Author(s)

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.