def ocr(img,idioma):
ocr_img = Image.fromarray(img)
ocr = Tesseract(lang=idioma)
ocr.set_image(ocr_img)
pattern = re.compile('[a-zA-Z0-9]')
text = ocr.get_utf8_text()
text = text.splitlines()
text = [x for x in text if x != '']
text = [x for x in text if pattern.search(x)]
ocr.clear()
return (text)
def ocrImage(tagDest,tessdataPrefix,lang,charWhitelist,pageMode):
destOcrImg = "/tmp/"+genymotion_vm_name+"-"+tagDest+".png"
print "OCR : "+str(destOcrImg)
#OCR Def
tr = Tesseract(tessdataPrefix, lang)
tr.set_variable("tessedit_char_whitelist", charWhitelist)
tr.set_page_seg_mode(pageMode)
#OCR
image = Image.open(destOcrImg)
tr.set_image(image)
return tr.get_utf8_text()
