Sensors, Vol. 20, Pages 6548: A Novel GAN-Based Synthesis Method for In-Air HandwrittenWords

Sensors, Vol. 20, Pages 6548: A Novel GAN-Based Synthesis Method for In-Air HandwrittenWords Sensors doi: 10.3390/s20226548 Authors: Zhang Xue In recent years, with the miniaturization and high energy efficiency of MEMS(micro-electro-mechanical systems), in-air handwriting technology based on inertial sensors hascome to the fore. Most of the previous works have focused on character-level in-air handwritingrecognition. In contrast, few works focus on word-level in-air handwriting tasks. In the fieldof word-level recognition, researchers have to face the problems of insufficient data and poorgeneralization performance of recognition methods. On one hand, the training of deep neurallearning networks usually requires a particularly large dataset, but collecting data will take a lot oftime and money. On the other hand, a deep recognition network trained on a small dataset can hardlyrecognize samples whose labels do not appear in the training set. To address these problems, wepropose a two-stage synthesis method of in-air handwritten words. The proposed method includesa splicing module guided by an additional corpus and a generating module trained by adversariallearning. We carefully design the proposed network so that it can handle word sample inputs ofarbitrary length and pay more attention to the details of the samples. We design multiple sets ofexperiments on a public dataset. The experimental results demonstrate the success of the proposedmethod. What is impressiv...
Source: Sensors - Category: Biotechnology Authors: Tags: Article Source Type: research