Three-dimensional object recognition from single two-dimensional images
Artificial Intelligence
Can one hear the shape of a drum? revisited
SIAM Review
Finite difference schemes and partial differential equations
Finite difference schemes and partial differential equations
Eigenmodes of Isospectral Drums
SIAM Review
The Laplacian eigenvalues of a polygon
Computers & Mathematics with Applications
Fractal-Based Description of Natural Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Business Intelligence and Data Mining
Optimization of spectral functions of Dirichlet-Laplacian eigenvalues
Journal of Computational Physics
Hi-index | 0.01 |
The eigenvalues of the Dirichlet Laplacian are used to generate three different sets of features for shape recognition and classification in binary images. The generated features are rotation-, translation-, and size-invariant. The features are also shown to be tolerant of noise and boundary deformation. These features are used to classify hand-drawn, synthetic, and natural shapes with correct classification rates ranging from 88.9% to 99.2%. The classification was done using few features (only two features in some cases) and simple feedforward neural networks or minimum Euclidian distance.