J
John Soldera
Researcher at Universidade Federal do Rio Grande do Sul
Publications - 10
Citations - 131
John Soldera is an academic researcher from Universidade Federal do Rio Grande do Sul. The author has contributed to research in topics: Facial recognition system & Face (geometry). The author has an hindex of 5, co-authored 10 publications receiving 120 citations. Previous affiliations of John Soldera include Universidade do Vale do Rio dos Sinos.
Papers
More filters
Journal ArticleDOI
Understanding people motion in video sequences using Voronoi diagrams
TL;DR: This work describes a model for understanding people motion in video sequences using Voronoi diagrams, focusing on group detection and classification, and determines the temporal evolution of some sociological and psychological parameters that are used to compute individual characteristics.
Journal ArticleDOI
Customized Orthogonal Locality Preserving Projections With Soft-Margin Maximization for Face Recognition
TL;DR: A novel face recognition method based on projections of high-dimensional face image representations into lower dimensionality and highly discriminative spaces is proposed by a modified orthogonal locality preserving projection (OLPP) method that uses a customized locality definition scheme to preserve the face class structure in the lowerdimensionality face feature space.
Proceedings ArticleDOI
Detection of Unusual Motion Using Computer Vision
TL;DR: Experimental results showed that different criteria for detecting unusual motion in surveillance cameras can be used as an automatic pre-screening of suspect motion in Surveillance applications.
Proceedings ArticleDOI
Face recognition based on geodesic distance approximations between multivariate normal distributions
TL;DR: A novel generative approach for face recognition is proposed, in which sparse facial features are extracted from high resolution color face images using predefined landmark topologies which mark discriminative locations on face images, unlike the appearance-based approach, which low resolution grayscale face images are used, reducing the computational complexity.
Journal ArticleDOI
Face recognition based on texture information and geodesic distance approximations between multivariate normal distributions
TL;DR: The proposed face recognition method was compared to methods representative of the state-of-the-art, using color or grayscale face images, and presented higher recognition rates and also is efficient in general texture discrimination (e.g., texture recognition of material images), as the experiments suggest.