In this paper, we discuss a novel method, based on singularity representation, for integrating a rotational invariant visual object extraction and understanding technique,. This new compression method applies Arnold...
详细信息
ISBN:
(纸本)081943678X
In this paper, we discuss a novel method, based on singularity representation, for integrating a rotational invariant visual object extraction and understanding technique,. This new compression method applies Arnold's Differential Mapping Singularities Theory in the context of three-dimensional (3D) object projection onto the 2D image plane. It takes advantage of the fact that object edges can be interpreted in terms of singularities, which can be described by simple polynomials. We discuss the relationship between traditional approaches, including wavelet transform and Differential Mapping Singularities Theory or Catastrophe Theory (CT) in the context of image understanding and rotational invariant objectextraction and compression. CT maps 3D surfaces with exact results to construct an image-compression algorithm based on an expanded set of operations. This set includes shift, scaling rotation, and homogeneous nonlinear transformations. This approach permits the mathematical description of a full set of singularities that describes edges and other specific points of objects. The edges and specific points (degenerate critical points) are the products of mapping smooth 3D surfaces, which can be described by a simple set of polynomials that are suitable for image compression and Automatic Target Recognition.
An effective analysis of visualobjects appearing in still images and video flames is required in order to offer fine grain access to multimedia and audiovisual contents. In previous papers, we showed how our method f...
详细信息
ISBN:
(纸本)0819434396
An effective analysis of visualobjects appearing in still images and video flames is required in order to offer fine grain access to multimedia and audiovisual contents. In previous papers, we showed how our method for segmenting still images into visualobjects could improve content-based image retrieval and video analysis methods. visualobjects are used in particular for extracting semantic knowledge about the contents. However, low-level segmentation methods for still images are not likely to extract a complex object as a whole but instead as a set of several sub-objects. For example, a person would be segmented into three visualobjects: a face, hair, and a body. In this paper, we introduce the concept of Composite visualobject. Such an object is hierarchically composed of sub-objects called Component objects. Production rules implementing some common sense knowledge are used to extract and label composite visualobjects based on the output of our still image segmentation method, and to label the component objects with their semantic values. Composite visualobjects of the database (e.g.: "persons") can then be searched for, possibly with some constraints on some of their components (e.g.: "only with a blue suit!").
暂无评论