Multi-feature matching of fresco fragments

Corey Toler-Franklin, Benedict Brown, Tim Weyrich, Thomas Funkhouser, Szymon Rusinkiewicz
2010 ACM Transactions on Graphics  
Figure 1 : Feature descriptors based on surface normal characteristics can capture a variety of physical characteristics such as brush strokes, string impressions, and erosion, that are used by archaeologists when assembling fresco fragments. Combining these with more traditional color-based features and 3D features using classification trees yields significantly improved matching performance. Abstract We present a multiple-feature approach for determining matches between small fragments of
more » ... ll fragments of archaeological artifacts such as Bronze-Age and Roman frescoes. In contrast with traditional 2D and 3D shape matching approaches, we introduce a set of feature descriptors that are based on not only color and shape, but also normal maps. These are easy to acquire and combine high data quality with discriminability and robustness to some types of deterioration. Our feature descriptors range from general-purpose to domain-specific, and are quick to compute and match. We have tested our system on three datasets of fresco fragments, demonstrating that multi-cue matching using different subsets of features leads to different tradeoffs between efficiency and effectiveness. In particular, we show that normal-based features are more effective than color-based ones at similar computational complexity, and that 3D features are more discriminative than ones based on 2D or normals, but at higher computational cost. We also demonstrate how machine learning techniques can be used to effectively combine our new features with traditional ones. Our results show good retrieval performance, significantly improving upon the match prediction rate of state-of-the-art 3D matching algorithms, and are expected to extend to general matching problems in applications such as texture synthesis and forensics. * Princeton University. {ctoler, smr, funk} † Katholieke Universiteit Leuven. ‡ University College London.
doi:10.1145/1882261.1866207 fatcat:poqbj7vyojfnxnt7ezbuiu5ffm