VisCode: Embedding Information in Visualization Images using Encoder-Decoder Network



Peiying Zhang, Chenhui Li, Changbo Wang

 External link (DOI) 

 View presentation:2020-10-27T18:45:00ZGMT-0600Change your timezone on the schedule page
2020-10-27T18:45:00Z

Exemplar figure — We present a novel information embedding approach for visualization images, called VisCode. VisCode can be used in a variety of practical applications. The input is a static visualization image. According to the encoding rules, we can retarget the original visual style after performing the decoding operation. Visualization retargeting includes representation (a) and theme color (b). VisCode can be also applied to metadata embedding as shown in (c) and large-scale information embedding. After decoding the source code into a static image, we can quickly build a visualization application and apply a common interaction such as selection as shown in (d).

Keywords

Image and Video Data, Algorithms, Application Motivated Visualization, Other Application Areas, Perception & Cognition, Image and Signal Processing

Abstract

We present an approach called VisCode for embedding information into visualization images. This technology can implicitly embed data information specified by the user into a visualization while ensuring that the encoded visualization image is not distorted. The VisCode framework is based on a deep neural network. We propose to use visualization images and QR codes data as training data and design a robust deep encoder-decoder network. The designed model considers the salient features of visualization images to reduce the explicit visual loss caused by encoding. To further support large-scale encoding and decoding, we consider the characteristics of information visualization and propose a saliency-based QR code layout algorithm. We present a variety of practical applications of VisCode in the context of information visualization and conduct a comprehensive evaluation of the perceptual quality of encoding, decoding success rate, anti-attack capability, time performance, etc. The evaluation results demonstrate the effectiveness of VisCode.