Yanming Zou

Overlapped Handwriting Input on Mobile Phones

In this paper, we propose an overlapped handwriting input method on handheld devices, which allows users to write continuously without breaks on a single size-restricted writing area. 2 issues have been considered during the implementation of the overlapped input method: previous characters on the background may obstruct the clear viewing of current character and the messy overlapped handwriting is difficult to be segmented and recognized. In our method, a quick segmentation method based on an artificial neural network is used to tackle the first problem and a novel system is implemented to recognize the messy handwriting based on the output of an isolated character recognition engine and a language model. The recognition rate for Chinese characters is about 92.5\% for a testing database containing GB2312 Chinese characters and other frequently used symbols. The positive feedbacks from testers have also confirmed the validity of the proposed method.

On-line Chinese Character Recognition System for Overlapping Samples

We proposed a new process strategy for on-line handwriting Chinese Character recognition and applied it to overlapping samples. On one hand, those samples are evaluated on stroke level by support vector machine, on the other hand, we do character level evaluation basing on a character pair search model. Then a merging strategy was proposed to filter out correct segmentation positions. We test our strategy on samples from real context, verifying that our strategy performs better than traditional over-segmentation and merging method.