A pyramid of n-dimensional generalized maps is a hierarchical data structure. It can be used, for instance, in order to represent an irregular pyramid of n-dimensional images. A pyramid of generalized maps can be built by successively removing and/or contracting cells of any dimension. In this paper, we define generalized orbits, which extend the classical notion of receptive fields. Generalize...

This paper describes a document image analysis system using multiple agents working on a pyramid structure to separate text from graphics in the image. Text strings appear as different groupings of connected components at different resolution of the images. As such, the pyramid structure, which is a multi-resolution image representation, provides a natural means of identifying and grouping of c...

Toy designers may benefit from a universal classification system to communicate and brainstorm new toy concepts. Being able to classify types of play may also help a designer in determining whether a potential toy product has play value. We have defined four categories of play (Construction, Fantasy, Sensory, Challenge) loosely based on Piaget’s four stages of cognitive development. These four ...

The Bounded Irregular Pyramid (BIP) is a hierarchical structure for image representation whose aim is to combine concepts from regular and irregular pyramids. The data structure is a combination of the simplest regular and irregular structures: the 2× 2/4 regular one and the simple graph representation. However, simple graphs only take into account adjacency relationships, being unable to corre...

Visual tracking is very important for many applications in computer vision, such as traac control, intelligent surveillance, industry automation, human computer interaction, etc. In this paper, we propose a hierarchical framework for estimating displacement vectors at feature points with the coarse-tone block matching method. Feature points are chosen to be the image locations having large curv...

Issue of the iterated filters in the directional filter bank is examined. The result is called pyramidal directional filter bank PDFB. Recently.NDFB with a new multiscale pyramid, we propose the surfacelet transform, which. A Frequency partitioning of the directional filter bank with 3 levels.In this paper, multiscale directional filter bank MDFB is investigated for texture characterization. Te...

 Similarity Pyramid: Browsing a Document Database with ildus Ahmadullin, Jan Allebach HP Laboratories HPL-2012-21 Document database management; document visual similarity; similarity pyramid; Isomap Managing large document databases has become an important task. Sorting documents with respect to their visual similarity and layout features, and visualization of the whole document database is a ...

Some of the most successful exposure fusion algorithms are based on image decomposition in Gaussian/Laplacian pyramids. However, the visual quality of the fused result is highly dependent on the number of decomposition levels, i.e. the pyramid height. In this paper, the analysis of that dependence is performed, and an automated algorithm for optimization of the pyramid height is proposed. The a...

Texture mapping is a common technique used to increase the visual quality of 3D scenes. As texture mapping requires large memory to deal with large textures generally r e quired in the current visual systems, we propose an algorithm for compressing a pyramid texture used for mipmapping. Vector quantization is used to compress all levels of the pyramid texture to one representative value databoo...

An effective method for the early detection of breast cancer is the mammographic screening. One of the most important signs of early breast cancer is the presence of microcalcifications. For the detection of microcalcification in a mammography image, we propose to conceive a multiagent system based on a dual irregular pyramid. An initial segmentation is obtained by an incremental approach; the ...