Background

uyghurocr project trying to build an open source OCR software to recognize Uyghur language. uyghurocr will start job based on current open source ocr projects - Tesseract OCR and ocropus via enhancing their Arabic (right to left language) support and user interface. I will put everything step by step in order to make Tesseract support Uyghur language here. Later maybe I will create nice user interface and more feature even integrate it with ocropus project.

Since most of the audience of this project are Uyghur people, left part of the project details written in Uyghur language, sorry for those audience do not know Uyghur. Please comment your questions here if you are interested.

Qisqiche Chüshendürüsh

uyghurocr türi uyghurche ocr yumtal qurup chiqishni meqset qilip qurulghan. ocr yumtali déginimiz sayilen'gen uyghurche kitablarning süret höjjitidin tékist höjjitini hasil qilishqa ishlitildighan qoraldin ibaret. Hazirqi pilanimizda bu uyghurocr yumtalini hazir bar bolghan ochuq kodluq ocr matori Tesseract ocr asasida ishlep chiqmaqchi. Hazir bu ochuq kodluq ocr matori téxi erebchige oxshash ongdin-solgha qarap yézilidighan herpliri özara ulinip yézilidighan tillarni qollimaydighan bolghachqa biz shu mesililerge qarita tüzitishlerni elip barmaqchi, hem ishligen xizmetlirimizni moshu jaygha toplap retlimekchi. Kelgüside belkim bu yumtalgha chirayliq körunme yüz yasishimiz mumkin we yene bet yüzini analiz qilish iqtidarigha ige ocropus turinimu biriktürüp téximu mukemmelleshtürüshimiz mumkin. Keng ochuq kod heweskarlirining akitip awaz qoshushini ümid qilimiz!

Hörmet bilen: - Uyghur OCR gurupisi

Basqan Yollirimiz

1. Qandaq qilip tesseract ocr kodigha érishish we uni toghra kompayillashqa ait yéngi wiki béti qoshuldi - Tesseractni kompayillash