Machado Penousal, Romero Juan, Nadal Marcos, Santos Antonino, Correia João, Carballal Adrián
CISUC, Department of Informatics Engineering, University of Coimbra, Portugal.
Faculty of Computer Science, University of A Coruña, Spain.
Acta Psychol (Amst). 2015 Sep;160:43-57. doi: 10.1016/j.actpsy.2015.06.005. Epub 2015 Jul 10.
Visual complexity influences people's perception of, preference for, and behaviour toward many classes of objects, from artworks to web pages. The ability to predict people's impression of the complexity of different kinds of visual stimuli holds, therefore, great potential for many domains, basic and applied. Here we use edge detection operations and several image metrics based on image compression error and Zipf's law to estimate the visual complexity of images. The experiments involved 800 images, each previously rated by thirty participants on perceived complexity. In a first set of experiments we analysed the correlation of individual features with the average human response, obtaining correlations up to rs = .771. In a second set of experiments we employed Machine Learning techniques to predict the average visual complexity score attributed by humans to each stimuli. The best configurations obtained a correlation of rs = .832. The average prediction error of the Machine Learning system over the set of all stimuli was .096 in a normalized 0 to 1 interval, showing that it is possible to predict, with high accuracy human responses. Overall, edge density and compression error were the strongest predictors of human complexity ratings.
视觉复杂性会影响人们对许多类别的物体的感知、偏好及行为，这些物体涵盖从艺术品到网页等。因此，预测人们对不同种类视觉刺激复杂性的印象的能力，在基础和应用等许多领域都具有巨大潜力。在这里，我们使用边缘检测操作以及基于图像压缩误差和齐普夫定律的几种图像指标来估计图像的视觉复杂性。实验涉及800张图像，每张图像之前都由30名参与者对其感知到的复杂性进行了评分。在第一组实验中，我们分析了各个特征与人类平均反应之间的相关性，得到的相关系数高达rs = 0.771。在第二组实验中，我们采用机器学习技术来预测人类赋予每个刺激的平均视觉复杂性得分。最佳配置的相关系数为rs = 0.832。在0到1的归一化区间内，机器学习系统在所有刺激集上的平均预测误差为0.096，这表明可以高精度地预测人类反应。总体而言，边缘密度和压缩误差是人类复杂性评级的最强预测指标。
