Clothes search in consumer photos via color matching and attribute learning
Clothes search in consumer photos via color matching and attribute learning
复制标题
DOI：
10.1145/2072298.2072013
复制
发表时间：
2011-11
期刊：
影响因子：
--
通讯作者：
Xianwang Wang;Tong Zhang
中科院分区：
文献类型：
--
作者：
Xianwang Wang;Tong Zhang
消费者照片中的自动服装搜索不是一个小问题，因为照片通常是在完全不受控制的逼真成像条件下拍摄的。在本文中，提出了一种新的框架来解决这个问题，通过利用低级特征（例如，颜色）和衣服的高级特征（属性）。首先，一个基于内容的图像检索（CBIR）的方法的基础上的视觉词袋（BOW）模型的基础上开发作为我们的基线系统，其中的码本是从提取的主色块。然后，提出了一种重新排序的方法，以提高搜索质量，通过利用衣服的属性，包括类型的衣服，袖子，图案等照片集的实验表明，我们的方法是鲁棒的大变化的图像在不受约束的环境中，和基于属性学习的重新排序算法显着提高检索性能结合建议的基线。
Automatic clothes search in consumer photos is not a trivial problem as photos are usually taken under completely uncontrolled realistic imaging conditions. In this paper, a novel framework is presented to tackle this issue by leveraging low-level features (e.g., color) and high-level features (attributes) of clothes. First, a content-based image retrieval(CBIR) approach based on the bag-of-visual-words (BOW) model is developed as our baseline system, in which a codebook is constructed from extracted dominant color patches. A reranking approach is then proposed to improve search quality by exploiting clothes attributes, including the type of clothes, sleeves, patterns, etc. The experiments on photo collections show that our approach is robust to large variations of images taken in unconstrained environment, and the reranking algorithm based on attribute learning significantly improves retrieval performance in combination with the proposed baseline.