Analysis of text layout quality using wearable eye trackers

Seyyed Saleh Mozaffari Chanijani, Syed Saqib Bukhari, Andreas Dengel

In: Workshop on Wearable and Ego-vision Systems for Augmented Experience (WEsAX). IEEE International Conference on Multimedia and Expo (ICME-15) Turin Italy IEEE 2015.


How would considering the aesthetics of text layout, particularly line spacing with the Golden Ratio (GR) parameter, influence the ease of reading and retention? To answer this question we introduced a novel method by employing a wearable eye tracker instead of a table-mounted eye tracker. Because of their lower price, portability, and growing market, as well as convenience to setup, such head-mounted devices are suitable use for ubiquitous reading behavior analysis. For mapping gaze information from captured video scenes to the original document, we adopted the Locally Likely Arrangement Hashing (LLAH) method for robust document retrieval. In our experimental system, participants read digital documents from the screen with and without the aesthetic GR parameter. Then, gaze data captured by the eye tracker's embedded camera is mapped to the corresponding original document. Finally, our gaze analysis system extracts the intended information for statistical evaluation. Regarding to the results, significant differences in reading performance were found in the documents with and without the GR aesthetic parameter for line spacing.


Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence