»ùÓÚ OpenCV µÄ±í¸ñÎı¾ÄÚÈÝÌáÈ¡

import cv2 as cvimport numpy as npfilename = 'filename.png'img = cv.imread(cv.samples.findFile(filename))cImage = np.copy(img) #image to draw linescv.imshow("image", img) #name the window as "image"cv.waitKey(0)cv.destroyWindow("image") #close the window

gray = cv.cvtColor(img, cv.COLOR_BGR2GRAY)cv.imshow("gray", gray)cv.waitKey(0)cv.destroyWindow("gray")canny = cv.Canny(gray, 50, 150)cv.imshow("canny", canny)cv.waitKey(0)cv.destroyWindow("canny")

# cv.HoughLinesP(image, rho, theta, threshold[, lines[, minLineLength[, maxLineGap]]]) ¡ú linesrho = 1theta = np.pi/180threshold = 50minLinLength = 350maxLineGap = 6linesP = cv.HoughLinesP(canny, rho , theta, threshold, None, minLinLength, maxLineGap)

def is_vertical(line):    return line[0]==line[2]def is_horizontal(line):    return line[1]==line[3]horizontal_lines = []vertical_lines = []
if linesP is not None:    for i in range(0, len(linesP)):        l = linesP[i][0]        if (is_vertical(l)):            vertical_lines.append(l)
        elif (is_horizontal(l)):            horizontal_lines.append(l)for i, line in enumerate(horizontal_lines):    cv.line(cImage, (line[0], line[1]), (line[2], line[3]), (0,255,0), 3, cv.LINE_AA)
for i, line in enumerate(vertical_lines):    cv.line(cImage, (line[0], line[1]), (line[2], line[3]), (0,0,255), 3, cv.LINE_AA)
cv.imshow("with_line", cImage)cv.waitKey(0)cv.destroyWindow("with_line") #close the window

def overlapping_filter(lines, sorting_index):    filtered_lines = []
    lines = sorted(lines, key=lambda lines: lines[sorting_index])    separation = 5    for i in range(len(lines)):            l_curr = lines[i]            if(i>0):                l_prev = lines[i-1]                if ( (l_curr[sorting_index] - l_prev[sorting_index]) > separation):                    filtered_lines.append(l_curr)            else:                filtered_lines.append(l_curr)
    return filtered_lines

horizontal_lines = []vertical_lines = []
if linesP is not None:    for i in range(0, len(linesP)):        l = linesP[i][0]        if (is_vertical(l)):             vertical_lines.append(l)
        elif (is_horizontal(l)):            horizontal_lines.append(l)    horizontal_lines = overlapping_filter(horizontal_lines, 1)    vertical_lines = overlapping_filter(vertical_lines, 0)for i, line in enumerate(horizontal_lines):    cv.line(cImage, (line[0], line[1]), (line[2], line[3]), (0,255,0), 3, cv.LINE_AA)    cv.putText(cImage, str(i) + "h", (line[0] + 5, line[1]), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1, cv.LINE_AA)                      for i, line in enumerate(vertical_lines):    cv.line(cImage, (line[0], line[1]), (line[2], line[3]), (0,0,255), 3, cv.LINE_AA)    cv.putText(cImage, str(i) + "v", (line[0], line[1] + 5), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1, cv.LINE_AA)
cv.imshow("with_line", cImage)cv.waitKey(0)cv.destroyWindow("with_line") #close the window

## set keywordskeywords = ['no', 'kabupaten', 'kb_otg', 'kl_otg', 'sm_otg', 'ks_otg', 'not_cvd_otg',            'kb_odp', 'kl_odp', 'sm_odp', 'ks_odp', 'not_cvd_odp', 'death_odp',            'kb_pdp', 'kl_pdp', 'sm_pdp', 'ks_pdp', 'not_cvd_pdp', 'death_pdp',            'positif', 'sembuh', 'meninggal']
dict_kabupaten = {}    for keyword in keywords:        dict_kabupaten[keyword] = []
## set counter for image indexingcounter = 0
## set line indexfirst_line_index = 1last_line_index = 14

def get_cropped_image(image, x, y, w, h):    cropped_image = image[ y:y+h , x:x+w ]    return cropped_imagedef get_ROI(image, horizontal, vertical, left_line_index, right_line_index, top_line_index, bottom_line_index, offset=4):    x1 = vertical[left_line_index][2] + offset    y1 = horizontal[top_line_index][3] + offset    x2 = vertical[right_line_index][2] - offset    y2 = horizontal[bottom_line_index][3] - offset
    w = x2 - x1    h = y2 - y1
    cropped_image = get_cropped_image(image, x1, y1, w, h)
    return cropped_image, (x1, y1, w, h)

import pytesseractpytesseract.pytesseract.tesseract_cmd = r'C:\Program Files (x86)\Tesseract-OCR\tesseract.exe'def draw_text(src, x, y, w, h, text):    cFrame = np.copy(src)    cv.rectangle(cFrame, (x, y), (x+w, y+h), (255, 0, 0), 2)    cv.putText(cFrame, "text: " + text, (50, 50), cv.FONT_HERSHEY_SIMPLEX, 2, (0, 0, 0), 5, cv.LINE_AA)
    return cFramedef detect(cropped_frame, is_number = False):    if (is_number):        text = pytesseract.image_to_string(cropped_frame,                                           config ='-c tessedit_char_whitelist=0123456789 --psm 10 --oem 2')    else:        text = pytesseract.image_to_string(cropped_frame, config='--psm 10')
    return text

counter = 0print("Start detecting text...")(thresh, bw) = cv.threshold(gray, 100, 255, cv.THRESH_BINARY)for i in range(first_line_index, last_line_index):    for j, keyword in enumerate(keywords):        counter += 1
        left_line_index = j        right_line_index = j+1        top_line_index = i        bottom_line_index = i+1
        cropped_image, (x,y,w,h) = get_ROI(bw, horizontal, vertical, left_line_index, right_line_index, top_line_index, bottom_line_index)
        if (keywords[j]=='kabupaten'):           text = detect(cropped_image)           dict_kabupaten[keyword].append(text)
        else:            text = detect(cropped_image, is_number=True)            dict_kabupaten[keyword].append(text)        image_with_text = draw_text(img, x, y, w, h, text)

def invert_area(image, x, y, w, h, display=False):    ones = np.copy(image)    ones = 1
    image[ y:y+h , x:x+w ] = ones*255 - image[ y:y+h , x:x+w ]
    if (display):         cv.imshow("inverted", image)        cv.waitKey(0)        cv.destroyAllWindows()    return imageleft_line_index = 17right_line_index = 20top_line_index = 0bottom_line_index = -1
cropped_image, (x, y, w, h) = get_ROI(img, horizontal, vertical, left_line_index, right_line_index, top_line_index, bottom_line_index)gray = get_grayscale(img)bw = get_binary(gray)bw = invert_area(bw, x, y, w, h, display=True)