The Role of Sparse Data Representation in Semantic Image Understanding

Within the general framework of the analysis of the geographic space and its ontological components by remote sensing, the author explores the ability of the morphogenetic modeling in the recognition of one major ontological and semantic concept of geography: the “locus-object.” The “locus-object” couple concept results from the interrelation formalization between the geographic locus, the geographic object, and the geo-localization notions. Geographic loci and objects are linked and both geo-localized. The links and relations between locus and object are mathematically formalized by geospatiology, the study of the logical role of space in the study of entities on the surface of the Earth. Morphogenetic modeling recognizes the loci of the geographic space by spatial discontinuities detection. The spatial discontinuities allow the identification of the types of spatial differentiations (boundaries, limits) between two geographic entities. The concept of “locus-object” is one of the key conceptual ontological elements of the geographic space.

Download Full-text

The role of image understanding in contour detection

2012 IEEE Conference on Computer Vision and Pattern Recognition ◽

10.1109/cvpr.2012.6247729 ◽

2012 ◽

Cited By ~ 16

Author(s):

C. L. Zitnick ◽

D. Parikh

Keyword(s):

Image Understanding ◽

Contour Detection

Download Full-text

Situated Image Understanding in a Multiagent Framework

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s021800149800035x ◽

1998 ◽

Vol 12 (05) ◽

pp. 595-624 ◽

Cited By ~ 1

Author(s):

N. Bianchi ◽

P. Bottoni ◽

P. Mussio ◽

C. Spinu ◽

C. Garbay

Keyword(s):

Liver Biopsy ◽

Image Understanding ◽

The State ◽

Reactive Control ◽

Preliminary Results ◽

Low Level ◽

Local Properties ◽

High Level ◽

Biopsy Image

The paper addresses the problem of controlling situated image understanding processes. Two complementary control styles are considered and applied cooperatively, a deliberative one and a reactive one. The role of deliberative control is to account for the unpredictability of situations, by dynamically determining which strategies to pursue, based on the results obtained so far and more generally on the state of the understanding process. The role of reactive control is to account for the variability of local properties of the image by tuning operations to subimages, each one being homogeneous with respect to a given operation. A variable organization of agents is studied to face this variability. The two control modes are integrated into a unified formalism describing segmentation and interpretation activities. A feedback from high level interpretation tasks to low level segmentation tasks thus becomes possible and is exploited to recover wrong segmentations. Preliminary results in the field of liver biopsy image understanding are shown to demonstrate the potential of the approach.

Download Full-text