Repository logo
 

Search Results

Now showing 1 - 5 of 5
  • An integrated framework for combining gist vision with object segregation categorisation and recognition
    Publication . Rodrigues, J. M. F.; Almeida, D.; Martins, Jaime; Lam, Roberto
    There are roughly two processing systems: (1) very fast gist vision of entire scenes, completely bottom-up and data driven, and (2) Focus-of-Attention (FoA) with sequential screening of specific image regions and objects. The latter system has to be sequential because unnormalised input objects must be matched against normalised templates of canonical object views stored in memory, which involves dynamic routing of features in the visual pathways.
  • Building the what and where systems: multi-scale lines, edges and keypoints
    Publication . Rodrigues, J. M. F.; Almeida, D.; Nunes, S.; Lam, Roberto; du Buf, J. M. H.
    Computer vision for realtime applications requires tremendous computational power because all images must be processed from the first to the last pixel. Ac tive vision by probing specific objects on the basis of already acquired context may lead to a significant reduction of processing. This idea is based on a few concepts from our visual cortex (Rensink, Visual Cogn. 7, 17-42, 2000): (1) our physical surround can be seen as memory, i.e. there is no need to construct detailed and complete maps, (2) the bandwidth of the what and where systems is limited, i.e. only one object can be probed at any time, and (3) bottom-up, low-level feature extraction is complemented by top-down hypothesis testing, i.e. there is a rapid convergence of activities in dendritic/axonal connections.
  • Artistic rendering of the visual cortex
    Publication . Lam, Roberto; Rodrigues, J. M. F.; du Buf, J. M. H.
    In this paper we explain the processing in the first layers of the visual cortex by simple, complex and endstopped cells, plus grouping cells for line, edge, keypoint and saliency detection. Three visualisations are presented: (a) an integrated scheme that shows activities of simple, complex and end-stopped cells, (b) artistic combinations of selected activity maps that give an impression of global image structure and/or local detail, and (c) NPR on the basis of a 2D brightness model. The cortical image representations offer many possibilities for non-photorealistic rendering.
  • Looking through the eyes of the painter: from visual perception to non-photorealistic rendering
    Publication . Lam, Roberto; Rodrigues, J. M. F.; du Buf, J. M. H.
    In this paper we present a brief overview of the processing in the primary visual cortex, the multi-scale line/edge and keypoint representations, and a model of brightness perception. This model, which is being extended from 1D to 2D, is based on a symbolic line and edge interpretation: lines are represented by scaled Gaussians and edges by scaled, Gaussian-windowed error functions. We show that this model, in combination with standard techniques from graphics, provides a very fertile basis for non-photorealistic image rendering.
  • Invariant Categorisation of Polygonal Objects using Multi-resolution Signatures
    Publication . Lam, Roberto; du Buf, J. M. H.
    With the increasing use of 3D objects and models, mining of 3D databases is becoming an important issue. However, 3D object recognition is very time consuming because of variations due to position, rotation, size and mesh resolution. A fast categorisation can be used to discard non-similar objects, such that only few objects need to be compared in full detail. We present a simple method for characterising 3D objects with the goal of performing a fast similarity search in a set of polygonal mesh models. The method constructs, for each object, two sets of multi-scale signatures: (a) the progression of deformation due to iterative mesh smoothing and, similarly, (b) the influence of mesh dilation and erosion using a sphere with increasing radius. The signatures are invariant to 3D translation, rotation and scaling, also to mesh resolution because of proper normalisation. The method was validated on a set of 31 complex objects, each object being represented with three mesh resolutions. The results were measured in terms of Euclidian distance for ranking all objects, with an overall average ranking rate of 1.29.