1.文本檢測(cè)批量分塊傳入tesseract識(shí)別

2.翻譯后映射到原票據(jù)字體問題

3.圖片去噪（難點(diǎn)），參考方案：

[https://dsp.stackexchange.com/questions/33540/binarization-of-image-for-varying-background-and-foreground-colors-for-ocr](https://dsp.stackexchange.com/questions/33540/binarization-of-image-for-varying-background-and-foreground-colors-for-ocr]

http://mile.ee.iisc.ernet.in/mile/publications/softCopy/DocumentAnalysis/CBDAR_Kasar_2007.pdf

https://arxiv.org/pdf/1506.04395.pdf

4.GNU并行，參考方案：

https://github.com/tesseract-ocr/tesseract/wiki/FAQ-Old#how-do-i-uninstall-tesseract

http://www.gnu.org/software/parallel/

5.流程解析
Useful parameters

https://github.com/tesseract-ocr/tesseract/wiki/ControlParams

https://github.com/tesseract-ocr/tesseract/wiki/FAQ-Old#error-message-font-id---10-class-id--1105-on-sample-0

訓(xùn)練基本參數(shù)配置

https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#config-files-and-augmenting-with-user-data

訓(xùn)練模型說明4.0

https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00

Data Files

https://github.com/tesseract-ocr/tesseract/wiki/Data-Files

tesseract常見問題論壇

https://github.com/tesseract-ocr/tesseract/issues

parameters config(./configs)

http://www.sk-spell.sk.cx/tesseract-ocr-parameters-in-302-version

https://pastebin.com/av7huwQP

Tesseract 4.00中新的神經(jīng)網(wǎng)絡(luò)系統(tǒng)概述

https://github.com/tesseract-ocr/tesseract/wiki/NeuralNetsInTesseract4.00

Noise characters recognized with bbox as the entire page（去噪框到了一張圖片）

https://github.com/tesseract-ocr/tesseract/issues/1192

tesseract for python

pyocr

https://gitlab.gnome.org/World/OpenPaperwork/pyocr

https://github.com/tesseract-ocr/tesseract/wiki/FAQ-Old#how-do-i-uninstall-tesseract

并行處理多個(gè)圖像

parallel "tesseract {} {} -l eng hocr; hocr2pdf -i {} -n -o {}.pdf < {}.html" ::: *.tif

線程線程

OMP_THREAD_LIMIT

https://groups.google.com/forum/#!forum/tesseract-ocr

https://groups.google.com/forum/#!topic/tesseract-ocr/pL6GELDd9Yg

How can define character size for tesseract?

config='--psm 8'

https://groups.google.com/forum/#!topic/tesseract-ocr/MbFSNPtXt84

Really poor performance with decimal numbers

try --psm 6

https://groups.google.com/forum/#!searchin/tesseract-ocr/l.bolzani%7Csort:date/tesseract-ocr/be4-rjvY2tQ/32evtMHlAQAJ

微調(diào)模型

https://groups.google.com/forum/#!topic/tesseract-ocr/Fkv2omJWxNw

-l eng --psm 8 --textord_min_linesize 2.5 hocr 1>/null 2>&1

幾何圖像變換（包含許多圖像縮放算法）

https://docs.opencv.org/2.4/modules/imgproc/doc/geometric_transformations.html#resize

Harris Corner Detection(找到物體頂點(diǎn))

https://docs.opencv.org/3.0-beta/doc/py_tutorials/py_feature2d/py_features_harris/py_features_harris.html

Camera Calibration

https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_calib3d/py_calibration/py_calibration.html

Interactive Foreground Extraction using GrabCut Algorithm

https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_imgproc/py_grabcut/py_grabcut.html#grabcut

圖像金字塔

https://docs.opencv.org/3.1.0/dc/dff/tutorial_py_pyramids.html

可結(jié)合pyimagesearch了解

https://www.pyimagesearch.com/2015/11/02/watershed-opencv/

Image Denoising

https://docs.opencv.org/3.3.1/d5/d69/tutorial_py_non_local_means.html

使用數(shù)據(jù)預(yù)處理不做處理的對(duì)比

https://www.pyimagesearch.com/2017/07/10/using-tesseract-ocr-python/

4 Point OpenCV getPerspective Transform Example（圖片旋轉(zhuǎn)）

https://www.pyimagesearch.com/2014/08/25/4-point-opencv-getperspective-transform-example/

imutils包(pip install imutils)作者自己封裝了一些圖像平移、旋轉(zhuǎn)、調(diào)整等，OpenCV也可實(shí)現(xiàn)，但比OpenCV結(jié)構(gòu)稍簡(jiǎn)單

https://www.pyimagesearch.com/2015/02/02/just-open-sourced-personal-imutils-package-series-opencv-convenience-functions/

提取獲取票據(jù)的邊框和提取票據(jù)（僅票據(jù)與背景顏色有明顯區(qū)別）

How to Build a Kick-Ass Mobile Document Scanner in Just 5 Minutes

https://www.pyimagesearch.com/2014/09/01/build-kick-ass-mobile-document-scanner-just-5-minutes/

字體傾斜矯正

Text skew correction with OpenCV and Python

https://www.pyimagesearch.com/2017/02/20/text-skew-correction-opencv-python/

Extract object from background with OpenCv and Python（前景物體提取）

http://faqpython.com/extract-object-from-background-with-opencv-and-python/

基于OpenCV識(shí)別游戲機(jī)的口袋怪物（共6step）

Building a Pokedex in Python: Finding the Game Boy Screen(find screen)

https://www.pyimagesearch.com/2014/03/10/building-pokedex-python-getting-started-step-1-6/

https://www.pyimagesearch.com/2014/03/24/building-pokedex-python-scraping-pokemon-sprites-step-2-6/

https://www.pyimagesearch.com/2014/04/07/building-pokedex-python-indexing-sprites-using-shape-descriptors-step-3-6/

https://www.pyimagesearch.com/2014/04/21/building-pokedex-python-finding-game-boy-screen-step-4-6/

https://www.pyimagesearch.com/2014/05/05/building-pokedex-python-opencv-perspective-warping-step-5-6/

https://www.pyimagesearch.com/2014/05/19/building-pokedex-python-comparing-shape-descriptors-opencv/

標(biāo)準(zhǔn)多邊形檢測(cè)

https://www.pyimagesearch.com/2016/02/08/opencv-shape-detection/

https://www.pyimagesearch.com/2014/10/20/finding-shapes-images-using-python-opencv/

圖片旋轉(zhuǎn)，可根據(jù)旋轉(zhuǎn)圖片大小改變旋轉(zhuǎn)后圖片大小

https://www.pyimagesearch.com/2017/01/02/rotate-images-correctly-with-opencv-and-python/

信用卡下的數(shù)字識(shí)別

Credit card OCR with OpenCV and Python

https://www.pyimagesearch.com/2017/07/17/credit-card-ocr-with-opencv-and-python/

Detecting Barcodes in Images with Python and OpenCV

https://www.pyimagesearch.com/2014/11/24/detecting-barcodes-images-python-opencv/

Sorting Contours using Python and OpenCV

https://www.pyimagesearch.com/2015/04/20/sorting-contours-using-python-and-opencv/

背景與前景提取

Extract object from background with OpenCv and Python

http://faqpython.com/extract-object-from-background-with-opencv-and-python/

使用圖像紋理對(duì)圖像做加工，然后進(jìn)行分類

Local Binary Patterns with Python & OpenCV

https://www.pyimagesearch.com/2015/12/07/local-binary-patterns-with-python-opencv/

流域分割硬幣（分水嶺算法）

https://www.pyimagesearch.com/2015/11/02/watershed-opencv/

OpenCV+深度學(xué)習(xí)學(xué)習(xí)資料

https://www.pyimagesearch.com/static/cv_dl_resource_guide.pdf

https://www.pyimagesearch.com/pyimagesearch-gurus/