arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1505.00529cs.CV
收藏

从数据中学习文档图像二值化

Learning Document Image Binarization from Data

Information Sciences Institute(信息科学研究所);University of South California(南加州大学)

Yue Wu, Stephen Rawls, Wael AbdAlmageed, Premkumar Natarajan

摘要:

在本文中,我们提出了一个完全可训练的退化文档图像的二值化解决方案。与以前的尝试不同,以前的尝试通常使用简单的特征和一系列的预处理和后处理,我们的解决方案将所有关于像素是否是前景文本的属性编码为高维特征向量,并学习更复杂的决策函数。特别是,我们准备了三种类型的特征:1)用于二值化的现有特征,例如强度[1],对比度[2],[3]和拉普拉斯[4],[5]; 2)从现有的二值化决策函数重新制定的特征,例如[6]和[7]中的那些;及3)我们新开发的功能,即对数强度百分位数(LIP)及相对黑暗指数(RDI)。我们最初的实验结果表明,只使用选定的样本(约1.5%的所有可用的训练数据),我们可以实现的二值化性能媲美那些微调(通常是手工),国家的最先进的方法。此外,经过训练的文档二值化分类器对域外数据表现出良好的泛化能力。

英文摘要:

In this paper we present a fully trainable binarization solution for degraded document images. Unlike previous attempts that often used simple features with a series of pre- and post-processing, our solution encodes all heuristics about whether or not a pixel is foreground text into a high-dimensional feature vector and learns a more complicated decision function. In particular, we prepare features of three types: 1) existing features for binarization such as intensity [1], contrast [2], [3], and Laplacian [4], [5]; 2) reformulated features from existing binarization decision functions such those in [6] and [7]; and 3) our newly developed features, namely the Logarithm Intensity Percentile (LIP) and the Relative Darkness Index (RDI). Our initial experimental results show that using only selected samples (about 1.5% of all available training data), we can achieve a binarization performance comparable to those fine-tuned (typically by hand), state-of-the-art methods. Additionally, the trained document binarization classifier shows good generalization capabilities on out-of-domain data.

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。

↑