Tesseract nedir? Tesseract kurulumu

Tesseract nedir? OCR işlemi yapan kütüphanedir. Resim lerin üzerindeki textleri okumaya yarar.

Debian Squeeze üzerinde Tesseract 3.x notları

# Kurulum
	aptitude install autogen autoconf automake libtool

	- leptonica
	http://www.leptonica.com/download.html
		wget http://www.leptonica.com/source/leptonica-1.69.tar.gz
		tar zxf leptonica-1.69.tar.gz
		cd leptonica-1.69
		./configure
		make
		su
		make install
		ldconfig
		exit

	- tesseract
	http://code.google.com/p/tesseract-ocr/downloads/list
		wget http://code.google.com/p/tesseract-ocr/downloads/detail?name=tesseract-3.01.tar.gz
		tar zxf tesseract-3.01.tar.gz
		cd tesseract-3.01
		./autogen
		./configure
		make
		su
		make install
		ldconfig
		exit

	- Dil dosyası
		su
		cd /usr/local/share/tessdata/
		wget http://code.google.com/p/tesseract-ocr/downloads/detail?name=tur.traineddata.gz
		wget http://code.google.com/p/tesseract-ocr/downloads/detail?name=eng.traineddata.gz
		gunzip tur.traineddata.gz
		gunzip eng.traineddata.gz


# Kullanım
	tesseract resim.jpg output.txt -l tur


# Kaynaklar
	training: http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3



# -----------------------------------------------------------------------------
# HOCR NOTLARI
# -----------------------------------------------------------------------------

# Kurulum
	aptitude install exactimage



# Kullanım
	tesseract resim.jpg output.txt -l tur hocr
	hocr2pdf -i resim.tif -o output.pdf < output.html

Not: Kaldırım