Sketch recognition allows computers to understand and model hand drawn sketches and diagrams. Traditionally sketch recognition systems required a pen based PC interface, but powerful mobile devices such as tablets and smartphones can provide a new platform for sketch recognition systems. We describe a new sketch recognition library, Strontium (SrL) that combines several existing sketch recognition libraries modified to run on both personal computers and on the Android platform. We analyzed the recognition speed and accuracy implications of performing low-level shape recognition on smartphones with touch screens. We found that there is a large gap in recognition speed on mobile devices between recognizing simple shapes and more complex ones, suggesting that mobile sketch interface designers limit the complexity of their sketch domains. We also found that a low sampling rate on mobile devices can affect recognition accuracy of complex and curved shapes. Despite this, we found no evidence to suggest that using a finger as an input implement leads to a decrease in simple shape recognition accuracy. These results show that the same geometric shape recognizers developed for pen applications can be used in mobile applications, provided that developers keep shape domains simple and ensure that input sampling rate is kept as high as possible.

The present study aimed to investigate whether students¡¦ error types in word recognition would be contingent upon teaching strategies. Based on the perspectives of feature-matching theory in pattern recognition, it was predicted that, the phonetic compound strategy would reduce the error rate in the recognition of the picto-phonetic character, whereas the radical recognition strategy would lower the error rate in the recognition of the radical character. A quasi-experiment was conducted in which ninety-nine 4th-grade elementary students were assigned to three groups receiving phonetic compound strategy, radical recognition strategy, and distributed recognition strategy respectively. The dependent measures consisted of shape error rate and pronunciation error rate. The results showed that those students who received the phonetic compound strategy exhibited lower shape and pronunciation error rates of the picto-phonetic character than the students who received the distributed recognition strategy. On the other hand, those students who received the radical recognition strategy exhibited lower shape error rate of the radical character than the students who received the distributed recognition strategy. Regarding the interaction of character types and error types within a specific teaching strategy, for those students who received the phonetic compound strategy, the shape error rate of the picto-phonetic character was lower than the pronunciation error rate of the radical character. For those students who received the radical recognition strategy, both the shape and pronunciation error rates of the radical character were lower than those of the picto-phonetic character. The contingent relationships between teaching strategies and error types in word recognition were partially supported by empirical data. Possible reason would be that the pronunciation might produce a more prominent facilitation effect than that of the shape in Chinese word recognition. Finally, implications for teaching strategies in word recognition and directions for future research are also discussed.