基于眼动仪和 LBP 的抽象画方向审美与识别-《计算机技术与发展》

文章信息/Info

Title:: Aesthetics and Detection of Orientation of Abstract Painting Based on Eye Tracker and LBP

Author(s):: BAI Ru-yi; School of Software Engineering,Shanxi University,Taiyuan 030013,China

Keywords:: abstract paintings; eye-movement; aesthetic; LBP; orientation detection

摘要:: 艺术家根据自己的灵感来决定抽象画的悬挂方向,但对于其他业余观众来说,抽象画的正确悬挂方向是不明显的。传统的审美评价主要通过问卷调查等方法获取,这使得绘画样本及实验数据偏重主观性,缺乏客观的量化表示。文中通过客观的眼动实验,分析了抽象绘画在不同悬挂方向上的审美评价。实验结果表明,悬挂方向正确的抽象画通常能获得较高的审美评价。然而,如何在没有明确提示的情况下, 自动确定抽象画的正确悬挂方向是一个有待解决的问题。因此, 采用局部二值模式(LBP)提取绘画特征, 使用支持向量机 (SVM)作为分类模型,实现抽象画正确方向的自动识别,将抽象画分为正确(向上)和不正确(不向上)两类。实验结果表明,该方法能有效识别抽象画的正确方向,也为抽象画的审美评价提供了一个新的研究视角。

Abstract:: Artists decide the orientation on which an abstract painting should be hung according to their inspiration,but for other amateur viewers,the correct hanging orientation that creates the highest aesthetic appreciation for an abstract painting is usually unknown. The traditional aesthetic evaluation is mainly obtained by questionnaire,which makes the painting samples and experimental data emphasize subjectivity and lack of objective quantitative expression. In this paper,we analyze the aesthetic evaluation of abstract painting from different hanging orientations through eye movement exper-iments. The experiment shows that abstract paintings with the correct hanging orientation usually get higher aesthetic evaluations. However,how to determine the correct hanging orientation is still unclear. Therefore, we use local binary pattern (LBP) to extract the features of the painting, and finally use SVM to realize the automatic detection of the correct direction of the abstract painting. We classify the abstract painting into correct (up) and incorrect (not up). The experiment shows that the proposed method can effectively identify the correct direction of abstract drawing,which also provides a new perspective for the study of abstract painting image.