Visual saliency model based on crowdsourcing eye tracking data and its application in visual design
- PDF / 3,948,922 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 83 Downloads / 192 Views
ORIGINAL ARTICLE
Visual saliency model based on crowdsourcing eye tracking data and its application in visual design Shiwei Cheng 1
&
Jing Fan 1 & Yilin Hu 1
Received: 14 June 2020 / Accepted: 12 September 2020 # Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract The visual saliency models based on low-level features of an image have the problem of low accuracy and scalability, while the visual saliency models based on deep neural networks can effectively improve the prediction performance, but require a large amount of training data, e.g., eye tracking data, to achieve good results. However, the traditional eye tracking method is limited by high equipment and time cost, complex operation process, low user experience, etc. Therefore, this paper proposed a visual saliency model based on crowdsourcing eye tracking data, which was collected by gaze recall with self-reporting from crowd workers. Parameter optimization on our crowdsourcing method was explored, and it came out that the accuracy of gaze data reached 1° of visual angle, which was 3.6% higher than other existed crowdsourcing methods. On this basis, we collected a webpage dataset of crowdsourcing gaze data and constructed a visual saliency model based on a fully convolutional neural network (FCN). The evaluation results showed that after trained by crowdsourcing gaze data, the model performed better, such as prediction accuracy increased by 44.8%. Also, our model outperformed the existing visual saliency models. We also applied our model to help webpage designers evaluate and revise their visual designs, and the experimental results showed that the revised design obtained improved ratings by 8.2% compared to the initial design. Keywords Visual saliency model . Visual attention . Crowd computing . Eye tracking . Human-computer interaction
1 Introduction The visual saliency model simulates the mechanism of human visual perception, and it can predict the distribution of visual attention received by different regions in the image. The visual saliency model can be applied to the fields of image processing and visual design [1]. Previous research work used lowfeatures of an image, such as color, density, and direction, to predict the visual saliency [2] [3]. However, these features cannot well characterize the visual perception characteristics of the human. Besides, the visual saliency model based on hand-crafted features and specific detectors [4, 5] requires the artificial selection of features and detectors. The modeling process is also complicated, and the scalability is poor. The use of deep neural network and eye tracking data allows the visual saliency model to learn relevant features autonomously,
* Shiwei Cheng [email protected] 1
Zhejiang University of Technology, Hangzhou, China
which can produce a more accurate and stable prediction. However, these methods require a large scale data set for model training [6, 7], while traditional eye tracking methods are limited by expensive hardware cost, complicated operation process, and envi
Data Loading...
