手振りモデルのノート

モデルの結果の使い方のファイルパス
//mediapipe/mediapipe/python/solutions/drawing_utils.py

handlandmarksから手振り認証
https://dev.classmethod.jp/articles/mediapipe-recognize-hand-pose-with-multi-hand-tracking/

OpenCV Python
https://github.com/skvark/opencv-python

tesseractでのOCR
https://nanonets.com/blog/ocr-with-tesseract/　　一番いい

https://www.pyimagesearch.com/2018/09/17/opencv-ocr-and-text-recognition-with-tesseract/
Tesseract OCRの結果を改善のため
https://github.com/tesseract-ocr/tessdoc/blob/master/ImproveQuality.md

画像をスキュー除去の方法
https://stackoverflow.com/questions/46731947/detect-angle-and-rotate-an-image-in-python　わかりやすい

https://www.pyimagesearch.com/2017/02/20/text-skew-correction-opencv-python/
http://felix.abecassis.me/2011/10/opencv-rotation-deskewing/

参考：https://gist.github.com/endolith/334196bac1cac45a4893

OCRステップバイステップ
https://nanonets.com/blog/ocr-with-tesseract/

Raspberry 32bit か 64bit　か

$ uname -m

You will get a response something like armv7l or armv8.
ARMv7 and below are 32-bit. AMRv8 introduces the 64-bit instruction set.

install miniconda
https://stackoverflow.com/questions/61508312/installing-anaconda-on-raspberry-pi-4-with-ubuntu-20-04

# Update linux
sudo yum update -y

# Install python3
sudo yum install -y python3

# Download miniconda installation (32-bit version)
curl "https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-armv7l.sh" -o "Miniconda.sh"

# Run miniconda installation
bash ./Miniconda.sh

# Add Raspberry Pi channel for conda installations
conda config --add channels rpi

# Update conda
conda update conda

connect camera module to raspberry
https://projects.raspberrypi.org/en/projects/getting-started-with-picamera

install opencv
https://www.tomshardware.com/uk/how-to/raspberry-pi-facial-recognition
https://qengineering.eu/install-opencv-4.5-on-raspberry-pi-4.html

Pythonのnamedtuple
https://qiita.com/Seny/items/add4d03876f505442136
https://www.geeksforgeeks.org/namedtuple-in-python/