Visual saliency model based on crowdsourcing eye tracking data and its application in visual design

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.