Pattern Recognition with Fuzzy Objective Function Algorithms
Pattern Recognition with Fuzzy Objective Function Algorithms
Neural Computation
As-rigid-as-possible image registration for hand-drawn cartoon animations
Proceedings of the 7th International Symposium on Non-Photorealistic Animation and Rendering
Clustering Stability: An Overview
Foundations and Trends® in Machine Learning
Point Set Registration: Coherent Point Drift
IEEE Transactions on Pattern Analysis and Machine Intelligence
Representing moving images with layers
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
Whereas one part of art history is a history of inventions, the other part is a history of transfer, of variations and copies. Art history wants to understand the differences between these, in order to learn about artistic choices and stylistic variations. In this paper we develop a method that can detect variations between artworks and their reproductions, in particular deformations in shape. Specifically, we present a novel algorithm which automatically finds regions which share the same transformation between original and its reproduction. We do this by minimizing an energy function which measures the distortion between local transformations of the shape. Thereby, the grouping and registration problem are addressed jointly and model complexity is obtained using a stability analysis. Moreover, our method allows art historians to evaluate the exactness of a copy by identifying which contours where considered relevant to copy. The proposed shape-based approach thus helps to investigate art through the art of reproduction.