van de Weijer Joost, Schmid Cordelia, Verbeek Jakob, Larlus Diane
Computer Vision Center, Barcelona, Spain.
IEEE Trans Image Process. 2009 Jul;18(7):1512-23. doi: 10.1109/TIP.2009.2019809. Epub 2009 May 27.
Color names are required in real-world applications such as image retrieval and image annotation. Traditionally, they are learned from a collection of labeled color chips. These color chips are labeled with color names within a well-defined experimental setup by human test subjects. However, naming colors in real-world images differs significantly from this experimental setting. In this paper, we investigate how color names learned from color chips compare to color names learned from real-world images. To avoid hand labeling real-world images with color names, we use Google Image to collect a data set. Due to the limitations of Google Image, this data set contains a substantial quantity of wrongly labeled data. We propose several variants of the PLSA model to learn color names from this noisy data. Experimental results show that color names learned from real-world images significantly outperform color names learned from labeled color chips for both image retrieval and image annotation.
在诸如图像检索和图像标注等实际应用中，颜色名称是必需的。传统上，它们是从一组带标签的颜色样本中学习得到的。这些颜色样本由人类测试对象在定义明确的实验设置中用颜色名称进行标注。然而，在真实世界图像中命名颜色与这种实验设置有很大不同。在本文中，我们研究从颜色样本中学习到的颜色名称与从真实世界图像中学习到的颜色名称相比如何。为避免用颜色名称手动标注真实世界图像，我们使用谷歌图像收集了一个数据集。由于谷歌图像的局限性，这个数据集包含大量错误标注的数据。我们提出了几种概率潜在语义分析（PLSA）模型的变体，以便从这些有噪声的数据中学习颜色名称。实验结果表明，对于图像检索和图像标注这两个任务，从真实世界图像中学习到的颜色名称显著优于从带标签的颜色样本中学习到的颜色名称。
