kusunungurwa kwe optical text recognition system , inotsigira kucherechedzwa kwemavara eUTF-8 uye zvinyorwa mumitauro inopfuura zana, kusanganisira chiRussian, Kazakh, Belarusian neUkraine. Mhedzisiro yacho inogona kuchengetwa mumavara akajeka kana muHTML (hOCR), ALTO (XML), PDF uye TSV mafomati. Iyo sisitimu yakatanga kugadzirwa muna 100-1985 murabhoritari yeHewlett Packard; muna 1995, iyo kodhi yakavhurwa pasi perezinesi reApache uye yakagadziridzwa zvakare nekutora chikamu kwevashandi veGoogle. Project sources ine rezinesi pasi peApache 2.0.
Tesseract inosanganisira koni yekushandisa uye libtesseract raibhurari yekumisikidza OCR mashandiro mune mamwe maapplication. Kubva kumapato echitatu anotsigira Tesseract unogona kucherechedza , ΠΈ . Injini mbiri dzekuzivikanwa dzinopihwa: yemhando yepamusoro inoziva zvinyorwa padanho rematanho emunhu ega, uye imwe nyowani yakavakirwa pakushandiswa kwemuchina wekudzidza system yakavakirwa pane LSTM inodzokororwa neural network, yakagadziridzwa yekuziva tambo dzese uye kubvumira kuwedzera kukuru kwechokwadi. Mamodheru akagadzirwa akadzidziswa anotsikiswa . Kukwenenzvera kuita, mamodules anoshandisa OpenMP uye AVX2, AVX kana SSE4.1 SIMD mirayiridzo inopihwa.
chikuru muTesseract 4.1:
- Yakawedzera kugona kuburitsa mu XML fomati (Akaongororwa Magadzirirwo uye Chinyorwa Chinhu). Kuti ushandise iyi fomati, unofanirwa kumhanyisa application se "tessaract image_name alto output_dir";
- Yakawedzera mamodule matsva ekupa LTMBox uye WordStrBox, kurerutsa injini kudzidziswa;
- Yakawedzerwa rutsigiro rwepseudographics muhOCR (HTML) inobuda;
- Yakawedzera mamwe magwaro akanyorwa muPython ekudzidzisa injini zvichienderana nekudzidza kwemichina;
- Yakawedzera optimizations uchishandisa AVX, AVX2 uye SSE mirairo;
- Tsigiro yeOpenMP yakadzimwa nekusarudzika nekuda kwe nekubudirira;
- Yakawedzera rutsigiro rwemavara machena uye matema muinjini yeLSTM;
- Yakavandudzwa kuvaka zvinyorwa zvinoenderana neCmake.
Source: opennet.ru