Method: PDFextract#extract_with_ocr

Defined in:
lib/pdf_extract.rb

#extract_with_ocr(page_path, dimensions) ⇒ Object 



180
181
182
183
184
185
186
187
 
# File 'lib/pdf_extract.rb', line 180

def extract_with_ocr(page_path,dimensions)
  engine = Tesseract::Engine.new(language: :eng)
  engine.image = page_path
  engine.select 1,34,59,281
  text = engine.text.strip
  dimensions[:result] = text 
  return text
end