ocr / preproccess.py
senel's picture
first
cf195da verified
Raw History Blame Contribute Delete
3.06 kB
import cv2
import numpy as np
def getSkewAngle(cvImage) -> float:
# Prep image, copy, convert to gray scale, blur, and threshold
newImage = cvImage.copy()
gray = cv2.cvtColor(newImage, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (9, 9), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Apply dilate to merge text into meaningful lines/paragraphs.
# Use larger kernel on X axis to merge characters into single line, cancelling out any spaces.
# But use smaller kernel on Y axis to separate between different blocks of text
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (30, 5))
dilate = cv2.dilate(thresh, kernel, iterations=2)
# Find all contours
contours, hierarchy = cv2.findContours(dilate, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
contours = [cnt for cnt in contours if cv2.contourArea(cnt) > 1000]
contours = sorted(contours, key = cv2.contourArea, reverse = True)
for c in contours:
rect = cv2.boundingRect(c)
x,y,w,h = rect
cv2.rectangle(newImage,(x,y),(x+w,y+h),(0,255,0),2)
# Find largest contour and surround in min area box
largestContour = contours[0]
minAreaRect = cv2.minAreaRect(largestContour)
# Determine the angle. Convert it to the value that was originally used to obtain skewed image
angle = minAreaRect[-1]
if angle < -45:
angle = 90 + angle
return -1.0 * angle
# Rotate the image around its center
def rotateImage(cvImage, angle: float):
newImage = cvImage.copy()
(h, w) = newImage.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, angle, 1.0)
newImage = cv2.warpAffine(newImage, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
return newImage
def deskew(cvImage):
angle = getSkewAngle(cvImage)
check_angle = angle * -1.0
if check_angle > -60 and check_angle < 60:
rotated_image = rotateImage(cvImage, -1.0 * angle)
else:
rotated_image = cvImage
return rotated_image
def preprocess_image(img):
norm_img = np.zeros((img.shape[0], img.shape[1]))
img = cv2.normalize(img, norm_img, 0, 255, cv2.NORM_MINMAX)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
noiseless_image_bw = cv2.fastNlMeansDenoising(thresh, None, 10, 7, 21)
kernel = np.ones((2,2),np.uint8)
dilate = cv2.dilate(noiseless_image_bw, kernel, iterations = 1)
erosion = cv2.erode(dilate, kernel, iterations = 1)
image = cv2.morphologyEx(erosion, cv2.MORPH_CLOSE, kernel)
image = cv2.medianBlur(image, 3)
image = cv2.bitwise_not(image)
kernel = np.ones((2,2),np.uint8)
image = cv2.dilate(image, kernel, iterations=1)
image = cv2.erode(image, kernel, iterations = 1)
image = cv2.bitwise_not(image)
image = cv2.cvtColor(image, cv2.COLOR_GRAY2RGB)
image = cv2.detailEnhance(img, sigma_s=80, sigma_r=0.8)
image = deskew(image)
return image