本文探讨Transformer在OCR任务中的潜力，分析其相对于CRNN中LSTM的优势，特别是Transformer的注意力机制如何解决长期依赖问题并提高并行计算效率。通过理解attention机制，展示其在捕捉输入序列关系上的能力，并讨论其在图像识别中的应用，尤其是对于OCR中的多角度和混排识别问题的解决方案。
由于OCR是序列到序列，NMT或者通用的任务Transformer也是Sequence 2 Sequence。而OCR识别经典论文是CRNN，其中是CNN+RNN+softmax，这个RNN可以试试LSTM，GRU，或者其他变种。也可以是机器翻译的端到端的序列识别。
本文试图分析Transformer与OCR任务，试图将Transformer替换CRNN中的LSTM
N-Grams
N-grams refer to the process of combining the nearby words together for representation purposes where N represents the number of words to be combined together.
- For eg, consider a sentence, “Natural Language Processing is essential to Computer Science.”
- A 1-gram or unigram model will tokenize the sentence into one word combinations and thus the output will be “Natural, Language, Processing, is, essential, to, Computer, Science”
- A bigram model on the other hand will tokenize it into combination of 2 words each and the output will be “Natural Language, Language Processing, Processing is, is essential, essential to, to Computer, Computer Science”
最低0.47元/天 解锁文章
675
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
