In this paper, we present a mathematical theory for Marr's primal sketch. We first conduct a theoretical study of the descriptive Markov random field model and the generative wavelet/sparse coding model from the perspective of entropy and complexity. The competition between the two types of models defines the concept of "sketchability", which divides image into texture and geometry. We then propose a primal sketch model that integrates the two models and, in addition, a Gestalt field model for spatial organization. We also propose a sketching pursuit process that coordinates the competition between two pursuit algorithms: the matching pursuit (Mallat and Zhang, 1993) and the filter pursuit (Zhu, et al., 1997), that seek to explain the image by bases and filters respectively. The model can be used to learn a dictionary of image primitives, or textons in Julesz's language, for natural images. The primal sketch model is not only parsimonious for image representation, but produces meaningful sketches over a large number of generic images.
Towards a mathematical theory of primal sketch and sketchability
Proceedings Ninth IEEE International Conference on Computer Vision ; 1228-1235 vol.2
2003-01-01
1059299 byte
Conference paper
Electronic Resource
English
Towards a Mathematical Theory of Primal Sketch and Sketchability
British Library Conference Proceedings | 2003
|Image hallucination with primal sketch priors
IEEE | 2003
|Primal sketch: Integrating structure and texture
British Library Online Contents | 2007
|Image Hallucination with Primal Sketch Priors
British Library Conference Proceedings | 2003
|Video Primal Sketch: A Unified Middle-Level Representation for Video
British Library Online Contents | 2015
|