Conference paper Open Access

Liu, Hao; Ye, Hanting; Yang, Jie; Wang, Qing

JSON-LD (schema.org) Export

{
"description": "<p>Motivated by the trend of realizing full screens on devices such as smartphones, in this work we propose through-screen sensing with visible light for the application of fingertip air-writing. The system can recognize handwritten digits with under-screen photodiodes as the receiver. The key idea is to recognize the weak light reflected by the finger when the finger writes the digits on top of a screen. The proposed air-writing system has immunity to scene changes because it has a fixed screen light source. However, the screen is a double-edged sword as both a signal source and a noise source. We propose a data preprocessing method to reduce the interference of the screen as a noise source. We design an embedded deep learning model, a customized model ConvRNN, to model the spatial and temporal patterns in the dynamic and weak reflected signal for air-writing digits recognition. The evaluation results show that our through-screen fingertip air-writing system with visible light can achieve accuracy up to 91%. Results further show that the size of the customized ConvRNN model can be reduced by 94% with less<br>\nthan a 10% drop in performance.</p>",
"creator": [
{
"affiliation": "TU Delft",
"@type": "Person",
"name": "Liu, Hao"
},
{
"affiliation": "TU Delft",
"@type": "Person",
"name": "Ye, Hanting"
},
{
"affiliation": "TU Delft",
"@type": "Person",
"name": "Yang, Jie"
},
{
"affiliation": "TU Delft",
"@type": "Person",
"name": "Wang, Qing"
}
],
"datePublished": "2021-11-05",
"url": "https://zenodo.org/record/5646942",
"@type": "ScholarlyArticle",
"@context": "https://schema.org/",
"identifier": "https://doi.org/10.1145/3485730.3493454",
"@id": "https://doi.org/10.1145/3485730.3493454",
"workFeatured": {
"url": "https://aichallengeiot.github.io/",
"alternateName": "AIChallengeIoT",
"location": "Coimbra, Portugal",
"@type": "Event",
"name": "Workshop on Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things in conjuction with ACM SenSys 2021"
},
}