The results of layers were added and the dynamic threshold was used to reach the final saliency regions. 把各层计算所得的结果叠加，通过引入动态阈值，得到最后的显著区域。
Our method tries to model the composition styles of professional photographs by analyzing the structural features and the layout of visual saliency. 我们的方法是尝试藉由分析影像的结构特色和影像里视觉上显著部分的安排，以模组化专业摄影师的构图风格。
