Tso tawm cov ntawv nyeem qhov system Tesseract 4.1

Npaj tso tawm optical text recognition system Tesseract 4.1, txhawb kev lees paub ntawm UTF-8 cov cim thiab cov ntawv hauv ntau dua 100 hom lus, suav nrog Lavxias, Kazakh, Belarusian thiab Ukrainian. Cov txiaj ntsig tuaj yeem khaws cia hauv cov ntawv nyeem dawb lossis hauv HTML (hOCR), ALTO (XML), PDF thiab TSV hom. Lub kaw lus tau tsim nyob rau hauv 1985-1995 hauv chav kuaj ntawm Hewlett Packard; hauv 2005, cov cai tau qhib raws li daim ntawv tso cai Apache thiab tau tsim ntxiv nrog kev koom tes ntawm Google cov neeg ua haujlwm. Qhov project qhov chaw kis mus muaj ntawv tso cai nyob rau hauv Apache 2.0.

Tesseract suav nrog kev siv hluav taws xob console thiab lub tsev qiv ntawv libtesseract rau embedding OCR functionality rau lwm yam kev siv. Los ntawm peb tog uas txhawb Tesseract GUI interfaces koj tuaj yeem sau tseg gImageReader, VietOCR ΠΈ YAGF. Muaj ob lub cav paub txog: ib qho classic uas lees paub cov ntawv nyob rau theem ntawm tus kheej tus cwj pwm qauv, thiab ib qho tshiab raws li kev siv tshuab kev kawm raws li LSTM recurrent neural network, optimized rau paub tag nrho cov hlua thiab tso cai rau ib tug qhov tseem ceeb ntawm qhov tseeb. Npaj ua qauv qhia tau luam tawm rau 123 lus. Txhawm rau txhim kho kev ua tau zoo, cov qauv siv OpenMP thiab AVX2, AVX lossis SSE4.1 SIMD cov lus qhia muaj.

ntsiab kev txhim kho hauv Tesseract 4.1:

  • Ntxiv lub peev xwm los tso tawm hauv XML hom ALTO (Tshaj Tawm Layout thiab Cov Lus Qhia). Txhawm rau siv hom ntawv no, koj yuav tsum khiav daim ntawv thov ua "tessarac image_name alto output_dir";
  • Ntxiv tshiab rendering modules LSTMBox thiab WordStrBox, simplifying engine kev cob qhia;
  • Ntxiv kev txhawb nqa rau pseudographics hauv hOCR (HTML) tso zis;
  • Ntxiv lwm cov ntawv sau hauv Python rau kev cob qhia lub cav raws li kev kawm tshuab;
  • Kev nthuav dav optimizations siv AVX, AVX2 thiab SSE cov lus qhia;
  • OpenMP kev them nyiaj yug yog neeg xiam oob qhab los ntawm lub neej ntawd vim teeb meem nrog kev tsim khoom;
  • Ntxiv kev txhawb nqa rau cov npe dawb thiab dub hauv LSTM lub cav;
  • Txhim kho tsim cov ntawv sau raws li Cmake.

Tau qhov twg los: opennet.ru

Ntxiv ib saib