Interacting with paper on the DigitalDesk
Communications of the ACM - Special issue on computer augmented environments: back to the real world
Video Google: A Text Retrieval Approach to Object Matching in Videos
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Scalable Recognition with a Vocabulary Tree
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Target acquisition with camera phones when used as magic lenses
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Mobile Retriever: access to digital documents from their physical source
International Journal on Document Analysis and Recognition
HOTPAPER: multimedia interaction with paper using mobile phones
MM '08 Proceedings of the 16th ACM international conference on Multimedia
Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Embedded media markers: marks on paper that signify associated media
Proceedings of the 15th international conference on Intelligent user interfaces
Pacer: fine-grained interactive paper via camera-touch hybrid gestures on a cell phone
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Proceedings of the international conference on Multimedia
Spatial coding for large scale partial-duplicate web image search
Proceedings of the international conference on Multimedia
Large-scale EMM identification based on geometry-constrained visual word correspondence voting
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Hi-index | 0.00 |
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. To address this mismatching between AP and image identification techniques, we propose a novel large-scale image identification technique well geared to AP. At its core is a geometric verification scheme based on Minimum visual-word Correspondence Set (MICSs). MICS is a set of visual word (i.e. quantized visual feature) correspondences, each of which contains a minimum number of correspondences that are sufficient for deriving a transformation hypothesis between a captured document image and an indexed image. Our method selects appropriate MICSs to vote in a Hough space of transformation parameters, and uses a robust dense region detection algorithm to locate the possible transformation models in the space. The models are then utilized to verify all the visual word correspondences to precisely identify the matching indexed image. By taking advantage of unique geometric constraints in AP, our method can significantly reduce the time and memory cost while achieving high accuracy. As showed in evaluation with two AP systems called FACT and EMM, over a dataset with 1M+ images, our method achieves 100% identification accuracy and 0.67% registration error for FACT; For EMM, our method outperforms the state-of-the-art image identification approach by achieving 4% improvements in detection rate and almost perfect precision, while saving 40% and 70% memory and time cost.