90 lines
2.6 KiB
Python
90 lines
2.6 KiB
Python
import cv2
|
|
import pytesseract
|
|
import numpy as np
|
|
from pytesseract import Output
|
|
|
|
# img_source = cv2.VideoCapture(0)
|
|
|
|
|
|
def get_grayscale(image):
|
|
return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
|
|
|
|
|
|
def thresholding(image):
|
|
return cv2.threshold(image, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
|
|
|
|
|
|
def opening(image):
|
|
kernel = np.ones((5, 5), np.uint8)
|
|
return cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel)
|
|
|
|
|
|
def canny(image):
|
|
return cv2.Canny(image, 100, 200)
|
|
|
|
|
|
def test_performance():
|
|
img_source = cv2.imread('./img.png')
|
|
gray = get_grayscale(img_source)
|
|
thresh = thresholding(gray)
|
|
opening = opening(gray)
|
|
canny = canny(gray)
|
|
|
|
for img in [img_source, gray, thresh, opening, canny]:
|
|
d = pytesseract.image_to_data(img, output_type=Output.DICT)
|
|
print(d.keys())
|
|
|
|
n_boxes = len(d['text'])
|
|
|
|
# back to RGB
|
|
if len(img.shape) == 2:
|
|
img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
|
|
|
|
for i in range(n_boxes):
|
|
if int(d['conf'][i]) > 60:
|
|
(text, x, y, w, h) = (d['text'][i], d['left'][i], d['top'][i], d['width'][i], d['height'][i])
|
|
# don't show empty text
|
|
if text and text.strip() != "":
|
|
img = cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
|
|
img = cv2.putText(img, text, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 255, 0), 3)
|
|
|
|
cv2.imshow('img', img)
|
|
cv2.waitKey(0)
|
|
|
|
# print(pytesseract.image_to_data(img_source, output_type=Output.DICT)['text'])
|
|
|
|
def identy_char(img_path=None, img_source=None):
|
|
'''
|
|
@description: 识别单个字符
|
|
@param {img_path} 图片路径
|
|
@param {img_source} 图片源
|
|
@return {ident_char} 识别到的字符
|
|
'''
|
|
|
|
ident_char = None
|
|
if img_path != None and img_source == None:
|
|
source_img = cv2.imread(img_path)
|
|
|
|
elif img_path == None and img_source.any() != None:
|
|
source_img = img_source
|
|
|
|
else:
|
|
raise ValueError('img_path and img_source cannot be None OR Exist at the same time')
|
|
|
|
d = pytesseract.image_to_data(source_img, output_type=Output.DICT, config='--psm 10') # --psm 10: single char
|
|
print(d['text'])
|
|
for text in d['text']:
|
|
# print(text)
|
|
if len(text) == 1:
|
|
ident_char = text
|
|
break
|
|
if ident_char:
|
|
return ident_char
|
|
else:
|
|
return None
|
|
|
|
if __name__ == "__main__":
|
|
# identy_char('./img.png')
|
|
# source_img = cv2.imread('./img.png')
|
|
# print(identy_char(img_source=source_img))
|
|
print(identy_char('./coffee-ocr.jpg')) |