Demo Abstract: UnseenCode: Invisible On-screen Barcode with Image-based Extraction (Demo)

In this demo, we present UnseenCode, an invisible on-screen barcode scheme. We borrow inter-frame embedment method from VLC-based screen-camera communication techniques to achieve invisibility. Unlike existing VLC-based methods, UnseenCode does not require video-based extraction which is more unreliable and computationally expensive on off-the-shelf smartphones when compared to image-based extraction of traditional barcode methods. We design a delicate image-based barcode extraction method based on cross-component correlation of color images. Our demo implementation includes a transmitter running on desktop computers, and a scanner application running on any off-the-shelf Android smartphones. We would like to exhibit the applicability of UnseenCode in the real world.

[1]  Guobin Shen,et al.  InFrame++: Achieve Simultaneous Screen-Human Viewing and Hidden Screen-Camera Communication , 2015, MobiSys.

[2]  Feng Li,et al.  Uber-in-light: Unobtrusive visible light communication leveraging complementary color channel , 2016, IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications.

[3]  In-So Kweon,et al.  Identigram/watermark removal using cross-channel correlation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Tianxing Li,et al.  Real-Time Screen-Camera Communication Behind Any Scene , 2015, MobiSys.

[5]  Uri Polat,et al.  Evaluation of Critical Flicker-Fusion Frequency Measurement Methods for the Investigation of Visual Temporal Resolution , 2017, Scientific Reports.

[6]  Ramesh Raskar,et al.  VRCodes: Unobtrusive and active visual codes for interaction by exploiting rolling shutter , 2012, 2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR).