HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Three-dimensional object recognition from single two-dimensional images
Artificial Intelligence
Localizing Overlapping Parts by Searching the Interpretation Tree
IEEE Transactions on Pattern Analysis and Machine Intelligence
Invariant Descriptors for 3D Object Recognition and Pose
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Comparing Images Using the Hausdorff Distance
IEEE Transactions on Pattern Analysis and Machine Intelligence
Proceedings of the Second Joint European - US Workshop on Applications of Invariance in Computer Vision
An Approach to Object Recognition: Aligning Pictorial Descriptions
An Approach to Object Recognition: Aligning Pictorial Descriptions
Three-Dimensional Recognition of Solid Objects from a Two- Dimensional Image
Three-Dimensional Recognition of Solid Objects from a Two- Dimensional Image
ACM Transactions on Graphics (TOG)
Deformation Energy for Size Functions
EMMCVPR '99 Proceedings of the Second International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
The Use of Size Functions for Comparison of Shapes Through Differential Invariants
Journal of Mathematical Imaging and Vision
Size functions for comparing 3D models
Pattern Recognition
Describing shapes by geometrical-topological properties of real functions
ACM Computing Surveys (CSUR)
Multidimensional Size Functions for Shape Comparison
Journal of Mathematical Imaging and Vision
Recognition of Occluded Shapes Using Size Functions
ICIAP '09 Proceedings of the 15th International Conference on Image Analysis and Processing
Coreduction homology algorithm for inclusions and persistent homology
Computers & Mathematics with Applications
Image-Based Surface Matching Algorithm Oriented to Structural Biology
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
A global method for reducing multidimensional size graphs
GbRPR'11 Proceedings of the 8th international conference on Graph-based representations in pattern recognition
A new algorithm for computing the 2-dimensional matching distance between size functions
Pattern Recognition Letters
| Hi-index | 0.00 |
Size functions are integer valued functions of tworeal variables which have been recently proposed for therepresentation and recognition of shape. A main limitation of thetheory of size functions appeared to be the fragility of the producedrepresentation with respect to edge fragmentation. In this paper itis shown that size functions can actually be defined without makingassumptions on the topological structure of the viewedshape. Consequently, size functions can be profitably used even in thepresence of fragmented edge maps. In order to demonstrate thepotential of size functions for computer vision, a system for shaperecognition is described and tested on two different domains. Thevery good performances of the system indicate that size functions areextremely effective for the analysis of shapes for which geometricmodels might be difficult to obtain.