---
tags: 實習日記
---
# 實習日記11/28~12/2
[TOC]

# 進度
## 整理紅綠燈辨識照片
- 0-1000:339/3=113
- 1001-2000=291/3=97
- 2001-3000=285/3=95
- 3001-4000=294/=98
- 4001-Fianl= 486/3=162

<font color="#f00">共1695張，565組</font>

## EasyOCR
1. examples:

2. 使用深度學習

與Tesseract不同，EasyOCR是基於深度學習的OCR套件，它使用CRAFT模型（Character Region Awareness for Text Detection）來進行文字偵測，再依不同的語言載入對應的CRNN（Convolutional Recurrent Neural Network，卷積循環神經網路）模型進行檢測。

每個CRNN模型包含了三個組件:
1.特徵萃取Resnet
2.序列標記LSTM
3.文字解譯CTC （connectionist temporal classification）

3. 較適合靜態的印刷字體

4. 實作1：使用easyocr

5. 實作2: easyocr vs keras_ocr
Conclusion:

- While keras_ocr is good in terms of accuracy but it is costly in terms of time. Also if you’re using CPU, time might be an issue for you. Keras-OCR is image specific OCR tool. If text is inside the image and their fonts and colors are unorganized.

- Easy-OCR is lightweight model which is giving a good performance for receipt or PDF conversion. It is giving more accurate results with organized texts like PDF files, receipts, bills. Easy OCR also performs well on noisy images.

- All these results can be further improved by performing specific image operations. OCR Prediction is not only dependent on the model and also on a lot of other factors like clarity, grey scale of the image, hyper parameter, weight age given, etc.

6.
- https://www.youtube.com/watch?v=ZVKaWPW9oQY
- https://github.com/nicknochnack/EasyOCR/blob/main/OCR%20Basics-EasyOCR.ipynb
- https://www.kaggle.com/code/robikscube/extracting-text-from-images-youtube-tutorial
- https://www.youtube.com/watch?v=oyqNdcbKhew
## Github基本教學
https://hackmd.io/_7_uEcksQu-XfSr4-YJhfw