arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.09441cs.CVcs.LG
收藏

OCR的LSTM中的隐式语言模型

Implicit Language Model in LSTM for OCR

Information Sciences Institute(信息科学研究所);University of Southern California(南加利福尼亚大学)

Ekraam Sabir, Stephen Rawls, Prem Natarajan

摘要:

神经网络已经成为OCR的首选技术,但它们如何以及为什么提供卓越性能的许多方面仍然是未知的。使用LSTM的当前神经网络技术与先前最先进的HMM系统之间的一个关键区别在于HMM系统具有强独立性假设。相比之下,LSTM对在解码期间可以考虑的上下文的量没有明确的约束。在本文中,我们表明,他们学习一个隐式LM,并试图在等价的n-gram上下文来表征LM的强度。我们表明,与随机字符(即非自然发生的序列)的测试集相比,这种隐式学习的语言模型在我们的合成测试集上提供了2.4\%的CER改进,并且LSTM学习使用多达5个字符的上下文(在我们的配置中大约是88帧)。我们相信这是首次尝试在基于LSTM的OCR系统中表征隐式LM的强度。

英文摘要:

Neural networks have become the technique of choice for OCR, but many aspects of how and why they deliver superior performance are still unknown. One key difference between current neural network techniques using LSTMs and the previous state-of-the-art HMM systems is that HMM systems have a strong independence assumption. In comparison LSTMs have no explicit constraints on the amount of context that can be considered during decoding. In this paper we show that they learn an implicit LM and attempt to characterize the strength of the LM in terms of equivalent n-gram context. We show that this implicitly learned language model provides a 2.4\% CER improvement on our synthetic test set when compared against a test set of random characters (i.e. not naturally occurring sequences), and that the LSTM learns to use up to 5 characters of context (which is roughly 88 frames in our configuration). We believe that this is the first ever attempt at characterizing the strength of the implicit LM in LSTM based OCR systems.

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。

↑