def velocity_ocr(image,coords,f1app):
# crop and convert image to greyscale
img = Image.fromarray(image).crop(coords).convert('L')
img = img.resize([img.width*2,img.height*2])
if f1app:
# filters for video from the f1 app
img = ImageEnhance.Brightness(img).enhance(3.0)
img = ImageEnhance.Contrast(img).enhance(2.0)
else:
# filters for onboard video graphic
img = ImageEnhance.Brightness(img).enhance(0.1)
img = ImageEnhance.Contrast(img).enhance(2.0)
img = ImageEnhance.Contrast(img).enhance(4.0)
img = ImageEnhance.Brightness(img).enhance(0.2)
img = ImageEnhance.Contrast(img).enhance(16.0)
try:
# vel = pytesseract.image_to_string(img,config='digits')
vel = pytesseract.image_to_string(img)
except UnicodeDecodeError:
vel = -1
return vel
python类image_to_string()的实例源码
def image_recognize():
import pytesseract
from PIL import Image
class GetImageDate(object):
def m(self):
image = Image.open("data/0.jpg")
text = pytesseract.image_to_string(image)
return text
def SaveResultToDocument(self):
text = self.m()
f = open(u"Verification.txt", "w")
print text
f.write(str(text))
f.close()
g = GetImageDate()
g.SaveResultToDocument()
def recognize(self):
def format_captcha(captcha):
temp = ''
for i in captcha:
if (ord(i)>=48 and ord(i)<=57) or (ord(i)>=65 and ord(i)<=90) or (ord(i)>=97 and ord(i)<=122):
temp = temp + i
if temp=='':
temp = 'aaaa'
return temp
cookie = self.browser.cookies.all()
opener = urllib2.build_opener()
opener.addheaders.append(('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'))
opener.addheaders.append(('Host','jaccount.sjtu.edu.cn'))
opener.addheaders.append(('Referer',self.browser.url))
opener.addheaders.append(('Cookie', "; ".join('%s=%s' % (k,v) for k,v in cookie.items())))
f = opener.open("https://jaccount.sjtu.edu.cn/jaccount/captcha?1488154642719")
data = f.read()
with file('captcha.png','wb') as f:
f.write(data)
img = Image.open("captcha.png").convert('L')
result = format_captcha(pytesseract.image_to_string(img,lang="eng"))
return result
def detect_gf_result(image_path):
from PIL import ImageFilter, Image
import pytesseract
img = Image.open(image_path)
for x in range(img.width):
for y in range(img.height):
if img.getpixel((x, y)) < (100, 100, 100):
img.putpixel((x, y), (256, 256, 256))
gray = img.convert('L')
two = gray.point(lambda x: 0 if 68 < x < 90 else 256)
min_res = two.filter(ImageFilter.MinFilter)
med_res = min_res.filter(ImageFilter.MedianFilter)
for _ in range(2):
med_res = med_res.filter(ImageFilter.MedianFilter)
res = pytesseract.image_to_string(med_res, config='-psm 6')
return res.replace(' ', '')
def readCaptcha(self):#?????
headers = {
'Accept-Language':'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:53.0) Gecko/20100101 Firefox/53.0',
'Referer':'http://******/login.jsp',
'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8',
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'X-Forwarded-For':self.captchaId
}
url = 'http://******/common/captcha.jhtml?captchaId='+self.captchaId
try:
res = requests.get(url,headers=headers)
except requests.exceptions.ConnectionError:
print '??????'
path = "i:/img/"+self.captchaId+".png"
fp = open(path,'wb')
fp.write(res.content)
fp.close()
image = Image.open(path)
code = pytesseract.image_to_string(image)
self.captcha = code
#print code
def test(image_name):
"""
??????????????
:param image_name:
:return:
"""
with Image.open(image_name) as image:
# ??????????????????????????????????RBG???HSI???????L???
image = image.convert("L")
# ???????????????????????????????????????threshold?????1??????0??????????????????????????
image = cut_noise(image)
tools = pyocr.get_available_tools()
if len(tools) == 0:
print("No OCR tool found")
sys.exit(1)
tool = tools[0]
image.save("test.jpg")
txt = tool.image_to_string(image, lang="eng", builder=pyocr.builders.TextBuilder())
# Digits - Only Tesseract
digits = tool.image_to_string(image, lang="eng", builder=pyocr.tesseract.DigitBuilder())
print(txt)
print(digits)
def __post_data_with_captcha(self,postdata,captchaurl):
session = requests.session()
response = session.get(captchaurl)
imagedata = response.content
time = datetime.datetime.now().time()
f = open('image.jpg','wb')
f.write(imagedata)
f.close()
#decode the captcha
try:
imgstr =image_to_string(Image.open('image.jpg'))
print(imgstr)
postdata[self.formdata.maindata['captcha']] = imgstr
except UnicodeDecodeError:
pass
postdata.update(self.formdata.extradata)
postresponse = session.post(self.formdata.post_url,data=postdata,headers=self.formdata.headers)
responseHtml = postresponse.text
pageLength = len(responseHtml)
return pageLength
def __post_data_with_captcha(self,postdata,captchaurl):
session = requests.session()
response = session.get(captchaurl)
imagedata = response.content
time = datetime.datetime.now().time()
f = open('image.jpg','wb')
f.write(imagedata)
f.close()
#decode the captcha
try:
imgstr =image_to_string(Image.open('image.jpg'))
print(imgstr)
postdata[self.formdata.maindata['captcha']] = imgstr
except UnicodeDecodeError:
pass
postdata.update(self.formdata.extradata)
postresponse = session.post(self.formdata.post_url,data=postdata,headers=self.formdata.headers)
responseHtml = postresponse.text
pageLength = len(responseHtml)
return pageLength
def main():
# parse command line options
if len(sys.argv) != 2:
print 'Usage: python input_name output_name'
exit(1)
filePath = sys.argv[1]
print "<----- processing %s ----->" % filePath
#???????????????????????????????
img = cv2.imread(filePath, 0)
img = cv2.resize(img, (1200, 900))
# ??????
# imgArr = np.array(img)
# imgMean = np.mean(img)
# imgcopy = imgArr - imgMean
# imgcopy = imgcopy * 2 + imgMean * 3
# imgcopy = imgcopy / 255
canny = cv2.Canny(img, 60, 300)
inverted = cv2.bitwise_not(canny)
cv2.imshow('Canny', inverted)
test1 = Image.fromarray(canny)
test2 = Image.fromarray(inverted)
result = pytesseract.image_to_string(test1, lang="eng", config="-c tessedit_char_whitelist=0123456789X")
print result
print "-------"
result = pytesseract.image_to_string(test2, lang="eng")
print result
k = cv2.waitKey(0)
def vcode(self):
r = self._session.get(
'https://jy.yongjinbao.com.cn/winner_gj/gjzq/user/extraCode.jsp',
params={'randomStamp': random.random()}
)
r.raise_for_status()
# ????????
img_buffer = BytesIO(r.content)
img = Image.open(img_buffer)
code = pytesseract.image_to_string(img)
img.close()
img_buffer.close()
if self.code_rule.findall(code) == []:
raise VerifyCodeError('Wrong verify code: %s' % code)
else:
logger.debug('Verify Code is: %s' % code)
return code
def gg(name):
# ????
im = Image.open(name)
# ??????
imgry = im.convert('L')
# ????
imgry.save(name)
# ????????????threshold????
out = imgry.point(table, '1')
out.save(name)
# ??
text = pytesseract.image_to_string(out)
# ????
text = text.strip()
text = text.upper()
for r in rep:
text = text.replace(r, rep[r])
# out.save(text+'.jpg')
print(text)
# gg(CAPTCHA_PATH)
def __post_data_with_captcha(self,postdata,captchaurl):
session = requests.session()
response = session.get(captchaurl)
imagedata = response.content
time = datetime.datetime.now().time()
f = open('image.jpg','wb')
f.write(imagedata)
f.close()
#decode the captcha
try:
imgstr =image_to_string(Image.open('image.jpg'))
print(imgstr)
postdata[self.formdata.maindata['captcha']] = imgstr
except UnicodeDecodeError:
pass
postdata.update(self.formdata.extradata)
postresponse = session.post(self.formdata.post_url,data=postdata,headers=self.formdata.headers)
responseHtml = postresponse.text
pageLength = len(responseHtml)
return pageLength
def extracttext(imgpath, preprocess):
if imgpath.startswith('http://') or imgpath.startswith('https://') or imgpath.startswith('ftp://'):
image = url_to_image(imgpath)
else:
image = cv2.imread(imgpath)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
if preprocess == "thresh":
gray = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
elif preprocess == "blur":
gray = cv2.medianBlur(gray, 3)
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
text = pytesseract.image_to_string(Image.open(filename))
os.remove(filename)
return {"text": text}
def recognize_url(url):
import urllib
urllib.urlretrieve(url, "imgs/tmp-img.jpg")
img = Image.open('imgs/tmp-img.jpg')
img = img.convert('RGBA')
w, h = img.size[0], img.size[1]
print w, h
point_list = gen_white_black_points(img)
print_char_pic(w, h, point_list)
reduce_noisy(w, h, point_list)
print_char_pic(w, h, point_list)
img.putdata(point_list)
img.save("imgs/rebuild.jpg")
return pytesseract.image_to_string(Image.open('imgs/rebuild.jpg'))
def rec_img(imgPath):
img = Image.open(imgPath).convert("L")
binarizing(img,170)
# img.save('C:\\NotBackedUp\\00.png')
depoint(img)
depoint(img,True)
# img.save('C:\\NotBackedUp\\01.png')
seperated_img = split_image(img,save_temp=True)
recdString = ""
for cur_img in seperated_img:
recNum = pytesseract.image_to_string(cur_img,config='-psm 10 outputbase digits')
recdString = recdString + recNum
print recdString
#img.save('temp/%s.png' % recdString)
if len(recdString)==4:
# img.save('temp/%s.png' % recdString)
print "success"
else:
print "error ..."
img.save('temp/error_%s.png' % recdString)
return recdString
def tesser_money_image(image):
image = cv2.resize(image, (0,0), fx=2, fy=2)
image = PIL.Image.fromarray(image)
txt = pytesseract.image_to_string(image, config='-psm 7')
txt_list = list(txt)
for i in range(len(txt_list)):
if txt_list[i] == 'o':
txt_list[i] = '0'
elif txt_list[i] == 'O':
txt_list[i] = '0'
elif txt_list[i] == 'l':
txt_list[i] = '1'
elif txt_list[i] == 'I':
txt_list[i] = '1'
elif txt_list[i] == 'i':
txt_list[i] = '1'
elif txt_list[i] == 'M':
txt_list[i] = '000000'
elif txt_list[i] == 'K':
txt_list[i] = '000'
elif txt_list[i] == 'm':
txt_list[i] = '000000'
elif txt_list[i] == 'k':
txt_list[i] = '000'
elif txt_list[i] == 's':
txt_list[i] = '5'
elif txt_list[i] == 'S':
txt_list[i] = '5'
elif txt_list[i] == 'W':
txt_list[i] = '40'
txt = int(''.join(txt_list))
return(txt)
def tesser(image):
txt = pytesseract.image_to_string(image, config='-psm 7')
print(txt)
return(txt)
def get_capture(self):
data = requests.get(self.capture_url, cookies=self.cookies)
with open("./img_cache/" + self.cookies['PHPSESSID'] + ".gif", "wb+") as f:
f.write(data.content)
gif = Image.open("./img_cache/" + self.cookies['PHPSESSID'] + ".gif")
png = Image.new("RGB", gif.size)
png.paste(gif)
str = image_to_string(png).strip()
remove("./img_cache/" + self.cookies['PHPSESSID'] + ".gif")
return str
def getOcr(filename):
#,config='-psm 10') option for single digit recognition
#return image_to_string(Image.open(filename),config="-psm 6") #5
#return image_to_string(Image.open(filename)) #3
#return image_to_string(Image.open(filename),config="-psm 7") #5
return image_to_string(Image.open(filename),config="-psm 8 digits") #4
def genNC(image=None, listofwords=[], artist=None, song=None):
Words = {}
Information = {}
for i, image in enumerate(image):
i = i + 1
Words[i] = pytesseract.image_to_string(Image.open(image))
Information['GuessedWords'] = Words
Information["Real_Lyrics"] = listofwords
with open('{}Transcript.json'.format(Words[1]), 'w') as f:
json.dump(Information, f)
def ocrList(image):
response = pytesseract.image_to_string(Image.open(image)).encode('utf-8','replace')
if len(response) > 5:
response = response.replace('\n', ' ').replace(' ', ' ').split(' ')
return response
def calcSpaces(image):
response = pytesseract.image_to_string(Image.open(image)).encode('utf-8','replace')
print response
response = response.replace('\n', '').split(' ')
return len(response)
def genNC(image=None, listofwords=[], artist=None, song=None):
threads = []
Words = {}
def batchExtract(listofimages):
for image in listofimages:
try:
extractText(image)
except Exception as exp:
print(exp)
pass
def doCommand(image, listofwords):
a = pytesseract.image_to_string(Image.open(image)).encode('utf-8','replace').split(' ')
for a in a:
if len(a) > 3:
print difflib.get_close_matches(str(a), listofwords)[0]
Information = {}
listofwords = GrabSongLyrics(artist, song)
d = []
for i in range(len(image) / 5):
t = threading.Thread(target=batchExtract, args=([image[i*5:(i*5) + 4]]))
d.append(t)
t.start()
for t in d:
t.join()
for i, image in enumerate(image):
t = threading.Thread(target=doCommand, args=(image, i))
threads.append(t)
t.start()
for t in threads:
t.join()
Information["GuessedWords"] = Words
Information["Real_Lyrics"] = listofwords
with open('{}Transcript.json'.format(Words[1]), 'w') as f:
json.dump(Information, f)
def ocr(img):
# threshold the image to ignore background and keep text
gray = img.convert('L')
#gray.save('captcha_greyscale.png')
bw = gray.point(lambda x: 0 if x < 1 else 255, '1')
#bw.save('captcha_threshold.png')
word = pytesseract.image_to_string(bw)
ascii_word = ''.join(c for c in word if c in string.letters).lower()
return ascii_word
def is_text_on_screen(target, notify=True):
if notify:
_notify("starting is_text_on_screen")
if isinstance(target, str):
target = target.decode('utf-8')
#GET SCREENSHOT
path_to_screenshot = take_a_screenshot()
sleep(1)
#FIND TEXTS
im = cv2.imread(path_to_screenshot)
im = cv2.resize(im, (0,0), fx=2, fy=2)
imgray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
#ret,thresh = cv2.threshold(imgray,127,255,0)
ret,thresh = cv2.threshold(imgray,127,255,cv2.THRESH_BINARY)
contours, hierarchy = find_contours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
for index, contour in enumerate(contours):
b = Box(cv2.boundingRect(contour))
if b.width > 10 and b.height > 6:
cropped = im[b.ymin:b.ymax, b.xmin:b.xmax]
text = image_to_string(Image.fromarray(cropped))
print("text:", text)
if target in text.decode("utf-8"):
return True
return False
def process_ocr(force=False):
"""Invokes tesseract-ocr and translate_hex_values(), after which, the
converted text is displayed to the screen
:param force: If True, all images will be scanned regardless if they've been processed previously.
force=True also skips the message/filename process
"""
path = TesseractConfig()
scan_logs = ScanLogs()
skipped_files = 0
tessdata = '--tessdata-dir "{}"'.format(path.tessdata)
for file in os.listdir(path.screenshots):
if force or not scan_logs.check_if_scanned(file):
image = Image.open('{}\\{}'.format(path.screenshots, file))
converted_text = TextConversion(pytesseract.image_to_string(image, config=tessdata))
print(converted_text)
if not force:
scan_logs.logs = {file: str(converted_text)}
else:
skipped_files += 1
print("\n----------Scan Complete-----------")
if skipped_files:
print_delay("{} Files Skipped (Already Scanned)".format(skipped_files))
def extract_text(self):
temp_path = 'text_temp.png'
cv2.imwrite(temp_path, self.image)
self.text = pytesseract.image_to_string(Image.open(temp_path), lang=self.lang)
os.remove(temp_path)
return self.text
def recognize_card(original_image, country='kg', preview=False):
from processing.border_removal import resize
from processing.crop import process_image
result = []
cropped_image = "croped-image.jpg"
process_image(original_image, cropped_image)
idcard = cv2.imread(cropped_image, cv2.COLOR_BGR2GRAY)
idcard = resize(idcard, width=720)
scale_down = (8 * 170 / detect_dpi(idcard))
if scale_down <= 4:
rows, cols = idcard.shape[:2]
idcard = cv2.resize(idcard, (scale_down * cols / 8, scale_down * rows / 8))
contours, hierarchy = recognize_text(idcard)
for index, contour in enumerate(contours):
[x, y, w, h] = cv2.boundingRect(contour)
gray = cv2.cvtColor(idcard, cv2.COLOR_RGB2GRAY)
roi = gray[y:y + h, x:x + w]
if cv2.countNonZero(roi) / h * w > 0.55:
if h > 16 and w > 16:
filename = '%s.jpg' % index
cv2.imwrite(filename, roi)
text = pytesseract.image_to_string(
Image.open(filename), lang="kir+eng", config="-psm 7"
)
item = {'x': x, 'y': y, 'w': w, 'h': h, 'text': text}
result.append(item)
cv2.rectangle(idcard, (x, y), (x + w, y + h), (255, 0, 255), 2)
if preview:
original_image = original_image.split('/')[-1]
location = save_image('regions' + original_image, idcard)
return location, regionskir(result)
return regionskir(result)
def init_ui(self):
self._fileDialog = QFileDialog(self)
self._v_layout = QVBoxLayout()
self._v_layout.setSpacing(2)
self.setLayout(self._v_layout)
self._path = "TEXT.png"
self._pixmap = QPixmap(self._path)
self._btnFile = QPushButton("Open")
self._hWidget = QWidget()
self._hLayout = QHBoxLayout()
self._hWidget.setLayout(self._hLayout)
self._image = Image.open(self._path)
self._line = QLineEdit()
self._hLayout.addWidget(self._btnFile)
self._hLayout.addWidget(self._line)
size = QSize(160, 90)
pix = self._pixmap.scaled(size, transformMode=Qt.SmoothTransformation)
self._lbl = QLabel()
self._lbl.setPixmap(pix)
self._v_layout.addWidget(self._lbl)
self._v_layout.addWidget(self._hWidget)
self._btnFile.clicked.connect(self.openFilePressed)
self._line.setText(pytesseract.image_to_string(Image.open('TEXT.png')))
def openFilePressed(self):
self._path = self._fileDialog.\
getOpenFileName(self, "Image Files (*.png *.jpg)")
if self._path[0] != "":
self._pixmap = QPixmap(self._path[0])
size = QSize(160, 90)
pix = self._pixmap.scaled(size,
transformMode=Qt.SmoothTransformation)
self._lbl.setPixmap(pix)
self._image = Image.open(self._path[0])
text = pytesseract.image_to_string(self._image)
self._line.setText(text)
