Minimum correspondence sets for improving large-scale augmented paper
Xin Yan Yang, Chunyuan Liao, Qiong Liu, Kwang-Ting Tim Cheng · 2011
Augmented Paper (AP) is an important area of Augmented Reality (AR). Many AP systems rely on visual features for paper document identification. Although promising, these systems can hardly support large sets of documents (i.e. one million documents) because of high memory and time cost in handling high-dimensional features. On the other hand, general large-scale image identification techniques are not well customized to AP, costing unnecessarily more resources to achieve the identification accuracy required by AP.