Radu-Daniel Vatavu
Lisa Anthony
Jacob O. Wobbrock
ABSTRACT
Rapid prototyping of gesture interaction for emerging touch platforms requires that developers have access to fast, simple, and accurate gesture recognition approaches. The $-family of recognizers ($1, $N) addresses this need, but the current most advanced of these, $N-Protractor, has significant memory and execution costs due to its combinatoric gesture representation approach. We present $P, a new member of the $-family, that remedies this limitation by considering gestures as clouds of points. $P performs similarly to $1 on unistrokes and is superior to $N on multistrokes. Specifically, $P delivers >99% accuracy in user-dependent testing with 5+ training samples per gesture type and stays above 99% for user-independent tests when using data from 10 participants. We provide a pseudocode listing of $P to assist developers in porting it to their specific platform and a "cheat sheet" to aid developers in selecting the best member of the $-family for their specific application needs.
- Agarwal, P., and Varadarajan, K. A near-linear constant-factor approximation for euclidean bipartite matching? In SCG '04 (2004), 247--252. Google Scholar
Digital Library
- Anthony, L., and Wobbrock, J. O. A lightweight multistroke recognizer for user interface prototypes. In GI '10 (2010), 245--252. Google ScholarDigital Library
- Anthony, L., and Wobbrock, J. O. $N-Protractor: A fast and accurate multistroke recognizer. In GI'2012 (2012), 117--120. Google ScholarDigital Library
- Avis, D. A survey of heuristics for the weighted matching problem. Networks 13 (1983), 475--493.Google ScholarCross Ref
- Besl, P. J., and McKay, N. D. A method for registration of 3-d shapes. IEEE TPAMI 14, 2 (Feb. 1992), 239--256. Google ScholarDigital Library
- Burkard, R., Dell'Amico, M., and Martello, S. Assignment Problems. Society for Industrial and Applied Mathematics, Philadelphia, PA, USA, 2009. Google ScholarDigital Library
- Cormen, T. H., Leiserson, C. E., Rivest, R. L., and Stein, C. Introduction to algorithms. MIT Press, Cambridge, MA, USA, 2001. Google ScholarDigital Library
- Dubuisson, M.-P., and Jain, A. A modified Hausdorff distance for object matching. In IAPR'94 (1994), 566--568.Google ScholarCross Ref
- Edmonds, J. Paths, trees, and flowers. Canad. J. Math. 17 (1965), 449--467.Google Scholar
- Friedman, M. The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J. Am. Statist. Assoc. 32, 200 (1937), 675--701.Google ScholarCross Ref
- Hammond, T., and Paulson, B. Recognizing sketched multistroke primitives. ACM TIIS 1, 1 (2011), 4:1--4:34. Google ScholarDigital Library
- Kara, L. B., and Stahovich, T. F. Hierarchical parsing and recognition of hand-sketched diagrams. In UIST '04 (2004), 13--22. Google ScholarDigital Library
- Kristensson, P.-O., and Zhai, S. SHARK2: a large vocabulary shorthand writing system for pen-based computers. In UIST '04 (2004), 43--52. Google ScholarDigital Library
- Li, Y. Protractor: a fast and accurate gesture recognizer. In CHI '10 (2010), 2169--2172. Google ScholarDigital Library
- Papadimitriou, C. H., and Steiglitz, K. Combinatorial optimization: algorithms and complexity. Dover Publications, Mineola, New York, USA, 1998. Google ScholarDigital Library
- Plamondon, R., and Srihari, S. N. On-line and off-line handwriting recognition: A comprehensive survey. IEEE TPAMI 22, 1 (Jan. 2000), 63--84. Google ScholarDigital Library
- Rubine, D. Specifying gestures by example. In SIGGRAPH '91 (1991), 329--337. Google ScholarDigital Library
- Rucklidge, W. Efficient Visual Recognition Using the Hausdorff Distance. Springer-Verlag New York, 1996. Google ScholarDigital Library
- Sezgin, T. M., and Davis, R. HMM-based efficient sketch recognition. In IUI '05 (2005), 281--283. Google ScholarDigital Library
- Vatavu, R.-D. The effect of sampling rate on the performance of template-based gesture recognizers. In ICMI '11 (2011), 271--278. Google ScholarDigital Library
- Vatavu, R.-D. Small gestures go a long way: how many bits per gesture do recognizers actually need? In DIS '12 (2012), 328--337. Google ScholarDigital Library
- Willems, D., Niels, R., Gerven, M. v., and Vuurpijl, L. Iconic and multi-stroke gesture recognition. Pattern Recognition 42, 12, 3303--3312. Google ScholarDigital Library
- Wobbrock, J. O., Wilson, A. D., and Li, Y. Gestures without libraries, toolkits or training: a $1 recognizer for user interface prototypes. In UIST '07 (2007), 159--168. Google ScholarDigital Library
Index Terms
- Gestures as point clouds: a $P recognizer for user interface prototypes
Recommendations
$Q: a super-quick, articulation-invariant stroke-gesture recognizer for low-resource devices
MobileHCI '18: Proceedings of the 20th International Conference on Human-Computer Interaction with Mobile Devices and ServicesWe introduce $Q, a super-quick, articulation-invariant point-cloud stroke-gesture recognizer for mobile, wearable, and embedded devices with low computing resources. $Q ran up to 142X faster than its predecessor $P in our benchmark evaluations on ...
Gestures à Go Go: Authoring Synthetic Human-Like Stroke Gestures Using the Kinematic Theory of Rapid Movements
Special Issue on Causal Discovery and InferenceTraining a high-quality gesture recognizer requires providing a large number of examples to enable good performance on unseen, future data. However, recruiting participants, data collection, and labeling, etc., necessary for achieving this goal are ...
A lightweight multistroke recognizer for user interface prototypes
GI '10: Proceedings of Graphics Interface 2010With the expansion of pen- and touch-based computing, new user interface prototypes may incorporate stroke gestures. Many gestures comprise multiple strokes, but building state-of-the-art multistroke gesture recognizers is nontrivial and time-consuming. ...
Comments