arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1410.5224cs.CV
收藏

用于词图像表示的有监督中层特征

Supervised mid-level features for word image representation

Xerox Research Centre Europe(施乐欧洲研究中心)

Albert Gordo

摘要:

本文讨论了学习单词图像表示的问题:给定一个单词的裁剪图像,我们有兴趣找到一个描述性的,鲁棒的,紧凑的固定长度的表示。然后,可以向机器学习技术提供这些表示,以产生对单词检索或识别任务有用的模型。虽然许多作品都集中在机器学习方面,一旦一个全局表示已经产生,很少的工作一直致力于这些基础图像表示的建设:大多数作品使用标准的编码和聚合技术直接在标准计算机视觉功能,如SIFT或HOG。我们建议学习适合构建单词图像表示的本地中级特征。这些特征是通过在一小组训练图像上利用字符限界框注释来学习的。然而,与使用字符限界框信息的其他方法相反,我们的方法不依赖于在测试时显式地检测单个字符。然后,我们可以聚合本地中级特征以生成全局单词图像签名。当将这些特征与Almazán等人最近的词属性框架配对时,我们获得了与使用仅96维的全局描述符的匹配和识别任务的现有技术相当或更好的结果。

英文摘要:

This paper addresses the problem of learning word image representations: given the cropped image of a word, we are interested in finding a descriptive, robust, and compact fixed-length representation. Machine learning techniques can then be supplied with these representations to produce models useful for word retrieval or recognition tasks. Although many works have focused on the machine learning aspect once a global representation has been produced, little work has been devoted to the construction of those base image representations: most works use standard coding and aggregation techniques directly on top of standard computer vision features such as SIFT or HOG. We propose to learn local mid-level features suitable for building word image representations. These features are learnt by leveraging character bounding box annotations on a small set of training images. However, contrary to other approaches that use character bounding box information, our approach does not rely on detecting the individual characters explicitly at testing time. Our local mid-level features can then be aggregated to produce a global word image signature. When pairing these features with the recent word attributes framework of Almazán et al., we obtain results comparable with or better than the state-of-the-art on matching and recognition tasks using global descriptors of only 96 dimensions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑