利用眼動資料分析閱讀與動態物件凝視行為

Analysis of Reading Behavior and Dynamic Object Fixation with Gaze Tracking Data

沈君維(Shen Chun-Wei)

指導教授 ： 高文忠

國立臺灣師範大學/科技與工程學院/電機工程學系/碩士(2018年)

https://doi.org/10.6345/THE.NTNU.DEE.008.2018.E08

摘要

隨著科技的進步，眼動儀發展日漸迅速。眼動儀在人機介面的互動中具有相當高的重要性，眼動儀的取樣率規格需求越來越高，而如何分析所蒐集到的眼動資料，也逐漸成為大家所關注的議題。

本文提出了一套眼動資料自動分析的工具。透過不同條件的特徵抽取，利用支持向量機分類對資料進行分析，實驗結果亦顯示這項工具的可行性。另外本文亦針對使用者眼動資料與觀看物件之間的專注程度進行分析，透過觀看連續影像中的移動物件。除了給予使用者專注力分析，同時以動態及靜態的方式顯示分析結果，將資料以視覺化的方式呈現，以利觀察眼動資料分佈情形。

關鍵字

閱讀行為 ； 眼動資料分析 ； 特徵抽取 ； 注意力分析

並列摘要

With the advancement of technology, the eye tracker has developed rapidly. The eye tracker plays an important role in the interaction of the human machine interface. That is, the sampling rate of the eye tracker has been required to be highly accurate, correspondingly, how to analyze the collected gaze data has prompted worldwide concern.

This paper proposes a set of tools for automatic analysis of gaze data. With the feature extraction of different conditions, the Support Vector Machine (SVM) algorithm is used to analyze the data and the evaluation has proved the feasibility of this tool. In addition, this paper also analyzes the degree of focus between the gaze data and the dynamic object. The gaze data is displayed with a dynamic and static video, and the analysis result is presented in a visual figure, which makes it easier to observe the distribution of eye movement data.

並列關鍵字

reading behavior ； gaze data analysis ； feature extraction ； attention analysis

參考文獻

[1] K. Zhang, L. Zhang, and M. H. Yang, “Real-time compressive tracking,” in Proc. Eur. Conf. Comput. Vis., Florence, Oct. 2012, pp. 864-877.

[2] D. D. Salvucci and J. H. Goldberg, “Identifying fixations and saccades in eye- tracking protocols,” in Proc. ACM Symp. Eye Tracking Research and Applications, New York, Nov. 2000, pp. 71-78.

[3] J. H. Lin and S. J. Lin, “Integrating eye trackers with handwriting tablets to discover difficulties of solving geometry problems,” J. Educational Technol., vol. 49, no. 1, pp. 17-29, Jan. 2018.

[4] S. C. Chen, M. S. Hsiao, and H. C. She, “The effects of static versus dynamic 3D representations on 10th grade students atomic orbital mental model construction: evidence from eye movement behaviors,” Comput. in Human Behavior, vol. 53, pp. 169-180, Dec. 2015.

[5] L. D. Copeland and T. D. Gedeon, “Tutorials in elearning—how presentation affects outcomes,” IEEE Trans. Emerging Topics in Comput., vol. 5, no. 1, pp. 20-31, Mar. 2017.