Rating Image Aesthetics Using Deep Learning
Rating Image Aesthetics Using Deep Learning
复制标题
DOI：
10.1109/tmm.2015.2477040
复制
发表时间：
2015-11-01
影响因子：
7.3
通讯作者：
Wang, James. Z.
中科院分区：
文献类型：
--
作者：
Lu, Xin;Lin, Zhe;Wang, James. Z.
本文研究了图像美学评估的统一功能学习和分类器培训方法。现有的方法是基于手工制作或通用图像功能，并使用培训示例开发的机器学习和统计建模技术。我们采用一种新颖的深神网络方法，允许统一的功能学习和分类器培训来估计图像美学。特别是，我们开发了一个双列深度卷积神经网络，以支持异质输入，即全球和本地观点，以捕获图像的全球和局部特征。此外，我们采用图像的样式和语义属性来进一步提高美学分类性能。实验结果表明，我们的方法产生的结果明显优于AVA数据集上的早期报道的通用图像美学和基于内容的图像美学的结果。此外，我们引入了150万图像数据集（IAD），以进行图像美学评估，并通过训练IAD数据集中提出的深神经网络，进一步提高AVA测试集中的性能。
This paper investigates unified feature learning and classifier training approaches for image aesthetics assessment. Existing methods built upon handcrafted or generic image features and developed machine learning and statistical modeling techniques utilizing training examples. We adopt a novel deep neural network approach to allow unified feature learning and classifier training to estimate image aesthetics. In particular, we develop a double-column deep convolutional neural network to support heterogeneous inputs, i.e., global and local views, in order to capture both global and local characteristics of images. In addition, we employ the style and semantic attributes of images to further boost the aesthetics categorization performance. Experimental results show that our approach produces significantly better results than the earlier reported results on the AVA dataset for both the generic image aesthetics and content-based image aesthetics. Moreover, we introduce a 1.5-million image dataset (IAD) for image aesthetics assessment and we further boost the performance on the AVA test set by training the proposed deep neural networks on the IAD dataset.