OCR的Tensorflow模型 [英] Tensorflow model for OCR

问题描述

我是Tensorflow的新手，我正在尝试构建能够对图像执行OCR的模型.我必须阅读9个字符(固定在所有图像中)，数字和字母.我的模型将与此类似

https://matthewearl.github.io/2016/05/06 /cnn-anpr/

我的问题是，是否应该首先针对每个角色训练我的模型，然后再组合角色以获得完整的标签表示.还是我应该直接在全标签上训练?

我知道我需要传递模型，图像+对应图像的标签，这些标签的格式是什么，它是文本文件，我对该部分有点困惑，所以关于标签格式的任何解释都是传递给模型会有所帮助吗?谢谢，谢谢.

解决方案

我建议特别注意训练端到端OCR模型.您可以尝试使用我们用来记录街道名称的注意OCR"(OCR)， https://github. com/tensorflow/models/tree/master/research/attention_ocr

我猜想它应该适合您的情况.请参阅答案 https://stackoverflow.com/a/44461910 ，以获取有关如何为其准备数据的说明.

I am new in Tensorflow and I am trying to build model which will be able to perform OCR on my images. I have to read 9 characters (fixed in all images), numbers and letters. My model would be similar to this

https://matthewearl.github.io/2016/05/06/cnn-anpr/

My questions would be, should I train my model against each character firstly and after combine characters to get full label represented. Or I should train on full label straight ?

I know that I need to pass to model, images + labels for corresponding image, what is the format of those labels, is it textual file, I am bit confused about that part, so any explanation about format of labels which are passed to model would be helpful ? I appreciate, thanks.

解决方案

I'd recommend to train an end-to-end OCR model with attention. You can try the Attention OCR which we used to transcribe street names https://github.com/tensorflow/models/tree/master/research/attention_ocr

My guess it should work pretty well for your case. Refer to the answer https://stackoverflow.com/a/44461910 for instructions on how to prepare the data for it.

这篇关于OCR的Tensorflow模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！