This repository provides our code used for the paper:
SpectroPhone: Enabling Material Surface Sensing with RearCamera and Flashlight LEDs
Our contribution includes:
- Dataset
- Application
The repository is licensed under MIT licsense.
- Dataset: includes the recorded data
- Android App: Application for communicating with server, camera and additional hardware for controlling the LED
- Arduino: Software for the external RN2040 bluetooth connection
- Hardware: Eagle files for the board
- Phone case: case for the Huawei P20 smartphone
- Python Software: Server software for classifying images, training SVM models and viewing spectograms. Simply start main.py
Our dataset includes:
30 different materials
prepared .csv files with calculated spectroscopic features
If you use our app and/or dataset in your projects, please use the following BibTeX citation:
@inproceedings{10.1145/3411763.3451753,
author = {Schrapel, Maximilian and Etgeton, Philipp and Rohs, Michael},
title = {SpectroPhone: Enabling Material Surface Sensing with RearCamera and Flashlight LEDs},
year = {2021},
isbn = {978-1-4503-8095-9/21/05},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3411763.3451753 },
doi = {10.1145/3411763.3451753},
booktitle = {Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems},
articleno = {5},
numpages = {5},
keywords = {Material sensing, Pattern recognition, Mobile Interaction},
location = {Yokohama, Japan},
series = {CHI EA '21}
}
This repository is provided by the Human-Computer Interaction Group at the University Hannover, Germany. The code was mainly developed by Philipp Etgeton during his masters thesis. For additional details, see our CHI'21 Extended Abstract.
The dataset and code is licsened under MIT license. For inquiries, please contact [email protected]
📷 ➕ 📱 ➡️ 📊