In southeastern North America, Indigenous potters and woodworkers carved complex, primarily abstract, designs into wooden pottery paddles, which were subsequently used to thin the walls of hand-built, clay vessels. Original paddle designs carry rich historical and cultural information, but pottery paddles from ancient times have not survived. Archaeologists have studied design fragments stamped on sherds to reconstruct complete or nearly complete designs, which is extremely laborious and time-consuming. In Snowvision, we aim to develop computer vision methods to assist archaeologists to accomplish this goal more efficiently and effectively. For this purpose, we identify and study three computer vision tasks: (1) extracting curve structures stamped on pottery sherds; (2) matching sherds to known designs; (3) clustering sherds with unknown designs. Due to the noisy, highly fragmented, composite-curve patterns, each task poses unique challenges to existing methods. To solve them, we propose (1) a weakly-supervised CNN-based curve structure segmentation method that takes only curve skeleton labels to predict full curve masks; (2) a patch-based curve pattern matching method to address the problem of partial matching in terms of noisy binary images; (3) a curve pattern clustering method consisting of pairwise curve matching, graph partitioning and sherd stitching. We evaluate the proposed methods on a set of collected sherds and extensive experimental results show the effectiveness of the proposed algorithms.
相似文献