过程纹理的语义描述与预测

Semantic Descriptions and Prediction for Procedural Texture

摘要: 不同模式的过程纹理，往往是由带有不同参数的数学模型产生，这些参数又是经过有经验的研究人员的精心挑选而得到。而大多数人在日常生活与工作中，常常会用一些语言描述例如“规则的”，“蕾丝状的”和“重复的”等来定义或者寻找想要得到的纹理，希望能够借此被推荐合适的生成模型和参数来产生符合条件的纹理图像。然而这就造成了人的思维描述和纹理图像的生成模型和参数之间巨大的鸿沟。因此，对纹理图像添加语义描述，可以建立起人的视觉感知与图像之间沟通的桥梁。通过对人们所定义的语义进行分析，可以帮助人们找到合适的生成模型和参数来产生符合自己描述的纹理图像。本文以纹理图像语义描述为切入点，通过收集人们对纹理图像的语义描述，借助于多标签学习算法构建预测模型，为人们和过程纹理图像之间的沟通奠定基础。

Abstract: Procedural textures with different patterns are normally generated from mathematical models with parameters carefully selected by experienced users. However, for naive users, the intuitive way to obtain a desired texture is to provide semantic descriptions such as “regular”, “lacelike” and “repetitive” and then a procedural model with proper parameters will be automatically suggested to generate the corresponding textures. By contrast, it is less practical for users to learn mathematical models and tune parameters based on multiple examinations of large numbers of generated textures. Taken the semantic description of textures as the breakthrough point, this study explores the way to automatically generate human desired textures by collecting and analyzing people’s descriptions, so that it can lay the foundation for the communication between human descriptions and procedural textures.