I am trying to read the numbers of a gas meter using Python and OpenCV. I have found the numbers as seen here
I then try to run pytesseract on the extracted black and white numbers as seen here
But I can't get pytesseract to find the numbers. I have tried the other segmentation modes without any luck, so I guess it must be the preprocessing? any suggestions?
My code:
img = cv2.imread("gasmeter.jpg")
# Resize image
scale_percent = 40
width = int(img.shape[1] * scale_percent / 100)
height = int(img.shape[0] * scale_percent / 100)
dim = (width, height)
resized_img = cv2.resize(img, dim, interpolation=cv2.INTER_AREA)
grayscale = cv_funcs.get_grayscale(resized_img)
thresh = cv_funcs.thresholding(grayscale)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
sorted_contours = []
for cnt in contours:
area = cv2.contourArea(cnt)
approx = cv2.approxPolyDP(cnt,0.01*cv2.arcLength(cnt,True),True) # Find number of edges of the contours
if area > 840.0 and area < 1000.0 and len(approx) > 4 and len(approx) < 12:
sorted_contours.append(cnt)
if area > 6000.0 and area < 6500.0 and len(approx) < 12:
sorted_contours.append(cnt)
all_contours_img = resized_img.copy()
correct_contours_img = resized_img.copy()
con = cv2.drawContours(all_contours_img, contours, -1, (0,255,0), 3)
con2 = cv2.drawContours(correct_contours_img, sorted_contours, -1, (0,255,0), 3)
print("Finding numbers:")
bounding_rect_img = resized_img.copy()
# Find bounding rectangle
for i,cnt in enumerate(sorted_contours):
x,y,w,h = cv2.boundingRect(cnt)
cv2.rectangle(bounding_rect_img,(x,y),(x+w,y+h),(0,255,0),2)
# Find number
crop_img = thresh[y:y+h, x:x+w]
invert_img = cv2.bitwise_not(crop_img)
erode_img = cv_funcs.erode(invert_img)
dialate_img = cv_funcs.dilate(erode_img)
cv2.imshow(str(i), erode_img)
cv2.imwrite(str(i)+'.jpg', erode_img)
text = pytesseract.image_to_string(erode_img, config='--psm 10 digits')
print(text)
