import cv2 import pytesseract import numpy as np import re pytesseract.pytesseract.tesseract_cmd = "C:\\Program Files\\Tesseract-OCR\\tesseract.exe" # get grayscale image def get_grayscale(image): return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) # noise removal def remove_noise(image): return cv2.medianBlur(image, 5) # thresholding def thresholding(image): return cv2.threshold(image, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1] # dilation def dilate(image): kernel = np.ones((5, 5), np.uint8) return cv2.dilate(image, kernel, iterations=1) # erosion def erode(image): kernel = np.ones((5, 5), np.uint8) return cv2.erode(image, kernel, iterations=1) # opening - erosion followed by dilation def opening(image): kernel = np.ones((5, 5), np.uint8) return cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel) # canny edge detection def canny(image): return cv2.Canny(image, 100, 200) 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=5) # Find all contours contours, hierarchy = cv2.findContours(dilate, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE) contours = sorted(contours, key = cv2.contourArea, reverse = True) # 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 # Deskew image def deskew(cvImage): angle = getSkewAngle(cvImage) return rotateImage(cvImage, -1.0 * angle) # # top: value.bboxScaled[1] + "px", # left: value.bboxScaled[0] + "px", # width: value.bboxScaled[2] - value.bboxScaled[0] + "px", # height: value.bboxScaled[3] - value.bboxScaled[1] + "px", def getText(filename): s = [ 217, 160, 1505, 390 ] Y = s[1] X = s[0] # W = s[2] - s[0] - 40 # H = s[3] - s[1] - 220 W = s[2] - s[0] H = s[3] - s[1] img = cv2.imread(filename) cropped_image = img[Y:Y + H, X:X + W] cv2.imshow("cropped_image", cropped_image) cv2.waitKey(0) cv2.destroyAllWindows() grey_img = get_grayscale(cropped_image) cv2.imshow("grey_image", grey_img) cv2.waitKey(0) cv2.destroyAllWindows() binary = cv2.adaptiveThreshold(grey_img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 7) cv2.imshow("binary_image", binary) cv2.waitKey(0) cv2.destroyAllWindows() txt1 = pytesseract.image_to_string(binary, config="-l fra --psm 1 --oem 1") txt2 = pytesseract.image_to_string(grey_img, config="-l fra --psm 1 --oem 1") txt3 = pytesseract.image_to_string(cropped_image, config="-l fra --psm 1 --oem 1") txt4 = pytesseract.image_to_string(binary, config="-l fra --psm 12 --oem 1") txt5 = pytesseract.image_to_string(grey_img, config="-l fra --psm 12 --oem 1") txt6 = pytesseract.image_to_string(cropped_image, config="-l fra --psm 12 --oem 1") txt7 = pytesseract.image_to_string(binary, config="-l fra --psm 6 --oem 1") txt8 = pytesseract.image_to_string(grey_img, config="-l fra --psm 6 --oem 1") txt9 = pytesseract.image_to_string(cropped_image, config="-l fra --psm 6 --oem 1") txt10 = pytesseract.image_to_string(binary, config="-l fra+eng --psm 6 --oem 1") txt11 = pytesseract.image_to_string(grey_img, config="-l fra+eng --psm 6 --oem 1") txt12 = pytesseract.image_to_string(cropped_image, config="-l fra+eng --psm 6 --oem 1") txt13 = pytesseract.image_to_string(binary, config="-l fra+eng --psm 12 --oem 1") txt14 = pytesseract.image_to_string(grey_img, config="-l fra+eng --psm 12 --oem 1") txt15 = pytesseract.image_to_string(cropped_image, config="-l fra+eng --psm 12 --oem 1") txt16 = pytesseract.image_to_string(binary, config="-l fra+eng --psm 1 --oem 1") txt17 = pytesseract.image_to_string(grey_img, config="-l fra+eng --psm 1 --oem 1") txt18 = pytesseract.image_to_string(cropped_image, config="-l fra+eng --psm 1 --oem 1") print(txt1) print("----------------") print(txt2) print("----------------") print(txt3) print("----------------") print(txt4) print("----------------") print(txt5) print("----------------") print(txt6) print("----------------") print(txt7) print("----------------") print(txt8) print("----------------") print(txt9) print("----------------") print(txt10) print("----------------") print(txt11) print("----------------") print(txt12) print("----------------") print(txt13) print("----------------") print(txt14) print("----------------") print(txt15) print("----------------") print(txt16) print("----------------") print(txt17) print("----------------") print(txt18) # txt = pytesseract.image_to_string(cropped_image, config="-l fra --psm 6 --oem 3") # txt = pytesseract.image_to_string(cropped_image, config="-l fra --psm 7 ") # osd = pytesseract.image_to_osd(img) # angle = re.search('(?<=Rotate: )\d+', osd).group(0) # script = re.search('(?<=Script: )\d+', osd).group(0) # print("angle: ", angle) # print("script: ", script) return txt1 text = getText('../static/files/6260df4785e6a5b326b6b390/Page6.jpeg') print(text)