欢迎访问《图学学报》 分享到:

图学学报 ›› 2025, Vol. 46 ›› Issue (1): 221-232.DOI: 10.11996/JG.j.2095-302X.2025010221

• 工业设计 • 上一篇    下一篇

基于深度学习的电影海报视觉互动意义评价方法

汪颜(), 张牧雨, 刘秀珍()   

  1. 中国地质大学(武汉)艺术与传媒学院,湖北 武汉 430074
  • 收稿日期:2024-05-23 接受日期:2024-09-29 出版日期:2025-02-28 发布日期:2025-02-14
  • 通讯作者:刘秀珍(1972-),女,副教授,硕士。主要研究方向为数字媒体与交互设计、智能创新应用设计与评价等。E-mail:361692234@qq.com
  • 第一作者:汪颜(1997-),女,硕士研究生。主要研究方向为交互媒体设计。E-mail:ahnahnbibi@foxmail.com
  • 基金资助:
    广东省耕地保护监管平台项目(220Z12301171);湖北省教学研究项目(2017144);中国地质大学(武汉)教学研究项目(2017A37)

Visual interactive meaning evaluation method of movie posters based on deep learning

WANG Yan(), ZHANG Muyu, LIU Xiuzhen()   

  1. School of Arts and Communication, China University of Geosciences (Wuhan), Wuhan Hubei 430074, China
  • Received:2024-05-23 Accepted:2024-09-29 Published:2025-02-28 Online:2025-02-14
  • Contact: LIU Xiuzhen (1972-), associate professor, master. Her main research interests cover digital media and interaction design, intelligent innovative application design and evaluation, etc. E-mail:361692234@qq.com
  • First author:WANG Yan (1997-), master student. Her main research interest covers interactive media design. E-mail:ahnahnbibi@foxmail.com
  • Supported by:
    Farmland Protection Supervision Platform Project of Guangdong Province(220Z12301171);Teaching Research Project of Hubei Province(2017144);Teaching Research Project of China University of Geosciences (Wuhan)(2017A37)

摘要:

近年来,应用深度学习技术进行图像美学智能评价已成为一种趋势,然而,高层级美学描述任务所需标注数据量有待增加,数据集标注质量与多样性也有待提高。为此,以视觉语法的互动意义为切入点,引入深度卷积神经网络对电影海报视觉互动意义进行评价研究。首先,使用分词工具从电影海报评议学术文献中提取视觉互动意义核心语义,并借助形态分析法,归纳出视觉互动意义与电影海报特征元素的映射关系;然后,收集优秀电影海报作品,结合专家评议,构建电影海报视觉互动意义评价数据集;最后,运用深度卷积神经网络对电影海报样本进行特征提取,建立电影海报视觉互动意义评价模型,并通过实践创作验证模型的可行性。该方法将计算机美学评价拓展到电影海报设计领域,模拟人类视觉及审美思维,构建客观的评价模型,为设计师提供更加精准的用户审美需求并为前瞻性的设计提供参考。

关键词: 电影海报, 视觉语法, 互动意义, 美学评价, 深度学习

Abstract:

In recent years, the application of deep learning technology for the intelligent evaluation of image aesthetics has become a trend. However, there remains a need for an increase in the amount of annotated data required for high-level aesthetic description tasks, as well as an improvement in the quality and diversity of dataset annotations. To address this, the research took the interactive meaning of visual grammar as a starting point and introduced deep convolutional neural networks for evaluating the visual interactive meaning of movie posters. Firstly, a word segmentation tool was utilized to extract the core semantics of visual interactive meaning from academic literature on movie poster reviews, and the mapping relationship between visual interactive meaning and the characteristic elements of movie posters was summarized, with the aid of morphological analysis. Secondly, a collection of outstanding movie posters was gathered, and a dataset for evaluating the visual interactive meaning of movie posters was constructed in collaboration with expert reviews. Finally, a convolutional neural network was employed to extract features from movie poster samples, establishing a model for evaluating the visual interactive meaning of movie posters, which was verified through practical creation for its feasibility. This method expanded computer aesthetic evaluation to the field of movie poster design, constructing an objective evaluation model by simulating human vision and aesthetic cognition. This model will provide designers with more precise insights into user aesthetic needs and offer references for forward-looking design.

Key words: movie poster, visual grammar, interactive meaning, aesthetic evaluation, deep learning

中图分类号: