added options to flip/rotate and specify different input resolutions also f...

Constantin Wenger

2022-02-03 b95bf33cb5b296efb70a0c4b1c82c0f62286f52a

 opencv_dnn.py

old mode 100644
new mode 100755
@@ -12,6 +12,7 @@
from multiprocessing import Pool
from config import Config
import fetch_data
import pytesseract


"""
@@ -28,7 +29,7 @@
    new_pool = pd.DataFrame(columns=list(card_pool.columns.values))
    for hs in hash_size:
        new_pool['card_hash_%d' % hs] = np.NaN
        new_pool['set_hash_%d' % hs] = np.NaN
        new_pool['set_hash_%d' % 64] = np.NaN
        #new_pool['art_hash_%d' % hs] = np.NaN
    for ind, card_info in card_pool.iterrows():
        if ind % 100 == 0:
@@ -49,31 +50,52 @@
        for card_name in card_names:
            # Fetch the image - name can be found based on the card's information
            card_info['name'] = card_name
            cname = card_name
            if cname == 'con':
                cname == 'con__'
            img_name = '%s/card_img/png/%s/%s_%s.png' % (Config.data_dir, card_info['set'],
                                                         card_info['collector_number'],
                                                         fetch_data.get_valid_filename(card_info['name']))
                                                         fetch_data.get_valid_filename(cname))
            card_img = cv2.imread(img_name)

            # If the image doesn't exist, download it from the URL
            if card_img is None:
                set_name = card_info['set']
                if set_name == 'con':
                    set_name = 'con__'
                fetch_data.fetch_card_image(card_info,
                                            out_dir='%s/card_img/png/%s' % (Config.data_dir, card_info['set']))
                                            out_dir='%s/card_img/png/%s' % (Config.data_dir, set_name))
                card_img = cv2.imread(img_name)
            if card_img is None:
                print('WARNING: card %s is not found!' % img_name)
                continue

            set_img = card_img[575:638, 567:700]
            """
            img_cc = cv2.cvtColor(card_img, cv2.COLOR_BGR2GRAY)
            img_thresh = cv2.adaptiveThreshold(img_cc, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 11, 5)
            # Dilute the image, then erode them to remove minor noises
            kernel = np.ones((3, 3), np.uint8)
            img_dilate = cv2.dilate(img_thresh, kernel, iterations=1)
            img_erode = cv2.erode(img_dilate, kernel, iterations=1)
            cnts, hier = cv2.findContours(img_erode, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
            cnts2 = sorted(cnts, key=cv2.contourArea, reverse=True)
            cnts2 = cnts2[:10]
            if True:
                cv2.rawContours(img_cc, cnts2, -1, (0, 255, 0), 3)
                #cv2.imshow('Contours', card_img)
                #cv2.waitKey(10000)
            """
            set_img = card_img[595:635, 600:690]
            #cv2.imshow(card_info['name'], set_img)
            # Compute value of the card's perceptual hash, then store it to the database
            #img_art = Image.fromarray(card_img[121:580, 63:685])  # For 745*1040 size card image
            img_card = Image.fromarray(card_img)
            img_set = Image.fromarray(set_img)
            #cv2.imshow('Set' + card_names[0], set_img)
            for hs in hash_size:
                card_hash = ih.phash(img_card, hash_size=hs)
                set_hash = ih.whash(img_set, hash_size=hs)
                set_hash = ih.phash(img_set, hash_size=64)
                card_info['card_hash_%d' % hs] = card_hash
                card_info['set_hash_%d' % hs] = set_hash
                card_info['set_hash_%d' % 64] = set_hash
                #print('Setting set_hash_%d' % hs)
                #art_hash = ih.phash(img_art, hash_size=hs)
                #card_info['art_hash_%d' % hs] = art_hash
@@ -93,8 +115,8 @@
    elif isinstance(hash_size, int):
        hash_size = [hash_size]

    num_cores = 15
    num_partitions = round(card_pool.shape[0]/100)
    num_cores = 16
    num_partitions = round(card_pool.shape[0]/1000)
    if num_partitions < min(num_cores, card_pool.shape[0]):
        num_partitions = min(num_cores, card_pool.shape[0])
    pool = Pool(num_cores)
@@ -242,14 +264,14 @@
    # Find the contour
    cnts, hier = cv2.findContours(img_erode, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    if len(cnts) == 0:
        #print('no contours')
#        print('no contours')
        return []
    img_cont = cv2.cvtColor(img_erode, cv2.COLOR_GRAY2BGR)
    img_cont_base = img_cont.copy()
    cnts2 = sorted(cnts, key=cv2.contourArea, reverse=True)
    cnts2 = cnts2[:10]
    for i in range(0, len(cnts2)):
        print(i, len(cnts2[i]))
#    for i in range(0, len(cnts2)):
#        print(i, len(cnts2[i]))
    if debug:
        cv2.drawContours(img_cont, cnts2, -1, (0, 255, 0), 3)
        cv2.imshow('Contours', img_cont)
@@ -268,6 +290,8 @@
        size = cv2.contourArea(cnt)
        peri = cv2.arcLength(cnt, True)
        approx = cv2.approxPolyDP(cnt, 0.04 * peri, True)
        #print('Base Size:', size)
        #print('Len Approx:', len(approx))
        if size >= size_thresh and len(approx) == 4:
            # lets see if we got a contour very close in size as child
            if i_child != -1:
@@ -284,28 +308,28 @@
                c_cnt = c_list[0]  # the biggest child
                if debug:
                    cv2.drawContours(img_ccont, c_list[:1], -1, (0, 255, 0), 1)
                    cv2.imshow('CCont %d' % i_cnt, img_ccont)
                    cv2.imshow('CCont', img_ccont)
                c_size = cv2.contourArea(c_cnt)
                c_approx = cv2.approxPolyDP(c_cnt, 0.04 * peri, True)
                if len(c_approx) == 4 and (c_size/size) > 0.85:
                    rect = cv2.minAreaRect(c_cnt)
                    box = cv2.boxPoints(rect)
                    box = np.intp(box)
                    print(c_cnt)
                    print(box)
                    #print(c_cnt)
                    #print(box)

                    print('CSize:', c_size, '%:', c_size/size)
                    #print('CSize:', c_size, '%:', c_size/size)
                    b2 = []
                    for x in box:
                        b2.append([x])
                    cnts_rect.append(np.array(b2))
                else:
                    print('CF:', (c_size/size))
                    print('Size:', size)
                    #print('CF:', (c_size/size))
                    #print('Size:', size)
                    cnts_rect.append(approx)
            else:
                #print('CF:', (c_size/size))
                print('Size:', size)
                #print('Size:', size)
                cnts_rect.append(approx)
        else:
            if i_child != -1:
@@ -313,7 +337,7 @@
    return cnts_rect


def draw_card_graph(exist_cards, card_pool, f_len):
def draw_card_graph(exist_cards, card_pool, f_len, text_scale=0.8):
    """
    Given the history of detected cards in the current and several previous frames, draw a simple graph
    displaying the detected cards with its confidence level
@@ -329,7 +353,7 @@
    gap_sm = 10  # Small offset
    w_bar = 300  # Length of the confidence bar at 100%
    h_bar = 12
    txt_scale = 0.8
    txt_scale = text_scale
    n_cards_p_col = 4  # Number of cards displayed per one column
    w_img = gap + (w_card + gap + w_bar + gap) * 2  # Dimension of the entire graph (for 2 columns)
    h_img = 480
@@ -374,8 +398,8 @@
    return img_graph


def detect_frame(img, card_pool, hash_size=32, size_thresh=100000,
                 out_path=None, display=True, debug=False):
def detect_frame(img, card_pool, hash_size=32, size_thresh=10000,
                 out_path=None, display=True, debug=False, scale=1.0, tesseract=False):
    """
    Identify all cards in the input frame, display or save the frame if needed
    :param img: input frame
@@ -392,7 +416,9 @@
    det_cards = []
    # Detect contours of all cards in the image
    cnts = find_card(img_result, size_thresh=size_thresh, debug=debug)
    #print('Contours:', len(cnts))
    for i in range(len(cnts)):
        #print('Contour', i)
        cnt = cnts[i]
        # For the region of the image covered by the contour, transform them into a rectangular image
        pts = np.float32([p[0] for p in cnt])
@@ -411,14 +437,63 @@
        '''
        img_card = Image.fromarray(img_warp.astype('uint8'), 'RGB')
        img_card_size = img_warp.shape
        print(img_card_size)

        # cut out the part of the image that has the set icon
        #print(img_card_size)
        cut = [round(img_card_size[0]*0.57),round(img_card_size[0]*0.615),round(img_card_size[1]*0.81),round(img_card_size[1]*0.940)]
        print(cut)
        #print(cut)
        img_set_part = img_warp[cut[0]:cut[1], cut[2]:cut[3]]
        print(img_set_part.shape)
        #print(img_set_part.shape)
        img_set = Image.fromarray(img_set_part.astype('uint8'), 'RGB')
        #print('img set')
        if debug:
            cv2.imshow("Set Img#%d" % i, img_set_part)
        # tesseract takes a long time (200ms+), so if at all we should collect pictures
        # and then if a card is detected successfully, add it to detected cards and run a background check with
        # tesseract, if the identification with tesseract fails, mark somehow
        # or only use tesseract in case of edition conflicts idk yet
        # we will need to see what is needed
        # also it is hard to detect with bad 500x600 px image
        # maybe training it for the font would make it better or getting better resolution images
        prefilter = True
        if tesseract:
            height, width, channels = img_warp.shape
            blank_image = np.zeros((height, width, 3), np.uint8)
            threshold = 70
            athreshold = -30
            athreshold = -cv2.getTrackbarPos("Threshold", "mainwindow")
            cut = [round(img_card_size[0]*0.94),round(img_card_size[0]*0.98),round(img_card_size[1]*0.02),round(img_card_size[1]*0.3)]
            blank_image = img_warp[cut[0]:cut[1], cut[2]:cut[3]]
            cv2.imshow("Tesseract Image", blank_image) 
            if prefilter:
                blank_image = cv2.cvtColor(blank_image, cv2.COLOR_BGR2GRAY)
                blank_image = cv2.normalize(blank_image, None,  0, 255, cv2.NORM_MINMAX)
                cv2.imshow("Normalized", blank_image)
                result_image = cv2.adaptiveThreshold(blank_image, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 501, athreshold)
                #_, result_image = cv2.threshold(blank_image, threshold, 255, cv2.THRESH_BINARY_INV)
                cv2.imshow("TessImg", result_image)
                tesseract_output = pytesseract.image_to_string(cv2.cvtColor(result_image, cv2.COLOR_GRAY2RGB))
            else:
                tesseract_output = pytesseract.image_to_string(cv2.cvtColor(blank_image, cv2.COLOR_BGR2RGB))
            if "M20" in tesseract_output or 'm20' in tesseract_output:
                tesseract_output = "M20"
                print(tesseract_output)
            else:
                print(tesseract_output)
                tesseract_output = "Set not detected"

            #cv2.imshow("Tesseract Image", img_warp)
            #img_gray = cv2.cvtColor(img_warp, cv2.COLOR_BGR2GRAY)
            #img_blur = cv2.medianBlur(img_gray, 5)
            #img_thresh = cv2.adaptiveThreshold(img_gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 11, 5)
            #cv2.imshow('Thres', img_thresh)
            #tesseract_output = pytesseract.image_to_string(cv2.cvtColor(img_thresh, cv2.COLOR_GRAY2RGB))
            #if "M20" in tesseract_output or 'm20' in tesseract_output:
            #    tesseract_output = "M20"
            #    print(tesseract_output)
            #else:
            #    print(tesseract_output)
            #    tesseract_output = "Set not detected"

        # the stored values of hashes in the dataframe is pre-emptively flattened already to minimize computation time
        card_hash = ih.phash(img_card, hash_size=hash_size).hash.flatten()
@@ -434,20 +509,20 @@
        if card_one['name'] == card_two['name'] and card_one['set'] != card_two['set']:
            set_img_hash = ih.whash(img_set, hash_size=hash_size).hash.flatten()
            cd_data = pd.DataFrame(columns=list(card_pool.columns.values))
            print(list(card_pool.columns.values))
#            print(list(card_pool.columns.values))
            candidates = []
            for ix in range(0, 2):
                cd = card_pool[card_pool['hash_diff'] == top_matches[ix]].iloc[0]
                cd_data.loc[0 if cd_data.empty else cd_data.index.max()+1] = cd
                print('Idx:', ix, 'Name:', cd['name'], 'Set:', cd['set'], 'Diff:', top_matches[ix])
#                print('Idx:', ix, 'Name:', cd['name'], 'Set:', cd['set'], 'Diff:', top_matches[ix])


            cd_data['set_hash_diff'] = cd_data['set_hash_%d' % hash_size]
            cd_data['set_hash_diff'] = cd_data['set_hash_%d' % 64]
            cd_data['set_hash_diff'] = cd_data['set_hash_diff'].apply(lambda x: np.count_nonzero(x != set_img_hash))
            conf = sorted(cd_data['set_hash_diff'])
            print('Confs:', conf)
            #print('Confs:', conf)
            best_match = cd_data[cd_data['set_hash_diff'] == min(cd_data['set_hash_diff'])].iloc[0]
            print('Best Match', 'Name:', best_match['name'], 'Set:', best_match['set'])
            #print('Best Match', 'Name:', best_match['name'], 'Set:', best_match['set'])

            min_card = best_match
        card_name = min_card['name']
@@ -455,25 +530,32 @@
        det_cards.append((card_name, card_set))

        # Render the result, and display them if needed
        image_header = card_name
        if tesseract:
            image_header += ' TS: ' + tesseract_output
        cv2.drawContours(img_result, [cnt], -1, (0, 255, 0), 2)
        cv2.putText(img_result, card_name, (min(pts[0][0], pts[1][0]), min(pts[0][1], pts[1][1])),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)
        cv2.putText(img_result, image_header, (int(min(pts[0][0], pts[1][0])), int(min(pts[0][1], pts[1][1]))),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.5*scale+0.1, (255, 255, 255), 2)
        if debug:
            # cv2.rectangle(img_warp, (22, 47), (294, 249), (0, 255, 0), 2)
            cv2.putText(img_warp, card_name + ':' + card_set + ', ' + str(hash_diff), (0, 20),
                        cv2.FONT_HERSHEY_SIMPLEX, 0.4, (255, 255, 255), 1)
                        cv2.FONT_HERSHEY_SIMPLEX, 0.4*scale+0.1, (255, 255, 255), 1)
            cv2.imshow('card#%d' % i, img_warp)
    if display:
        cv2.imshow('Result', img_result)
        cv2.waitKey(0)
        inp = cv2.waitKey(0)

    if out_path is not None:
        print(out_path)
        cv2.imwrite(out_path, img_result.astype(np.uint8))
    return det_cards, img_result

def trackbardummy(v):
    pass

def detect_video(capture, card_pool, hash_size=32, size_thresh=10000,
                 out_path=None, display=True, show_graph=True, debug=False, crop_x=0, crop_y=0):
                 out_path=None, display=True, show_graph=True, debug=False,
                 crop_x=0, crop_y=0, rotate=None, flip=None, tesseract=False):
    """
    Identify all cards in the continuous video stream, display or save the result if needed
    :param capture: input video stream
@@ -487,38 +569,75 @@
    :return: list of detected card's name/set and resulting image
    :return:
    """
    if tesseract:
        cv2.namedWindow('mainwindow')
        cv2.createTrackbar("Threshold", "mainwindow", 30, 255, trackbardummy)
    list_names_from = 0
    # get some frame numers
    f_width = 0
    f_height = 0
    f_scale = 1.0
    if rotate is not None and (rotate == 0 or rotate == 2):
        f_height = round(capture.get(cv2.CAP_PROP_FRAME_WIDTH)-2*crop_y)
        f_width = round(capture.get(cv2.CAP_PROP_FRAME_HEIGHT)-2*crop_x)
    else:
        f_width = round(capture.get(cv2.CAP_PROP_FRAME_WIDTH) - 2*crop_x)
        f_height = round(capture.get(cv2.CAP_PROP_FRAME_HEIGHT) - 2*crop_y)

    if f_width > 800 or f_height > 800:
        f_max = max(f_width, f_height)
        f_scale = (800.0/float(f_max))

    # Get the dimension of the output video, and set it up
    if show_graph:
        img_graph = draw_card_graph({}, pd.DataFrame(), -1)  # Black image of the graph just to get the dimension
        width = round(capture.get(cv2.CAP_PROP_FRAME_WIDTH)) - 2*crop_x  + img_graph.shape[1]
        height = max(round(capture.get(cv2.CAP_PROP_FRAME_HEIGHT)) - 2*crop_y, img_graph.shape[0])
        width = int(f_width * f_scale)  + img_graph.shape[1]
        height = max(int(f_height * f_scale), img_graph.shape[0])
        height += 200  # some space to display last detected cards
    else:
        width = round(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
        height = round(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
        width = int(f_width * f_scale)
        height = int(f_height * f_scale)
    if out_path is not None:
        vid_writer = cv2.VideoWriter(out_path, cv2.VideoWriter_fourcc(*'MJPG'), 10.0, (width, height))
    max_num_obj = 0
    f_len = 10  # number of frames to consider to check for existing cards
    exist_cards = {}

    #print(f"fw{f_width} fh{f_height} w{width} h{height} fs{f_scale}")
    exist_card_single = {}
    written_out_cards = set()
    found_cards = []
    try:
        while True:
            ret, frame = capture.read()
            croped_img = frame[crop_y:-crop_y, crop_x:-crop_x]
            fimg = cv2.flip(croped_img, -1)
            if not ret:
                continue

            if flip is not None:
                frame = cv2.flip(frame, flip)
            if rotate is not None:
                frame = cv2.rotate(frame, rotate)

            y_max_index = -crop_y
            if crop_y == 0:
                y_max_index = frame.shape[0]
            x_max_index = -crop_x
            if crop_x == 0:
               x_max_index = frame.shape[1]

            croped_img = frame[crop_y:y_max_index, crop_x:x_max_index]
            fimg = croped_img
            start_time = time.time()
            if not ret:
                # End of video
                print("End of video. Press any key to exit")
                cv2.waitKey(0)
                break
            if fimg is None:
                print("flipped image is none")
                break
            # Detect all cards from the current frame
            det_cards, img_result = detect_frame(fimg, card_pool, hash_size=hash_size, size_thresh=size_thresh,
                                                 out_path=None, display=False, debug=debug)
                                                 out_path=None, display=False, debug=debug, scale=1.0/f_scale, tesseract=tesseract)
            if show_graph:
                # If the card was already detected in the previous frame, append 1 to the list
                # If the card previously detected was not found in this trame, append 0 to the list
@@ -561,6 +680,7 @@
                        if key not in written_out_cards and key in det_card_map:
                            written_out_cards.add(key)
                            found_cards.append(det_card_map[key])
                            list_names_from += 1

                for key in det_card_map:
                    if key not in exist_card_single.keys():
@@ -579,9 +699,16 @@
                # Draw the graph based on the history of detected cards, then concatenate it with the result image
                img_graph = draw_card_graph(exist_cards, card_pool, f_len)
                img_save = np.zeros((height, width, 3), dtype=np.uint8)
                # resize result to out predefined area
                if f_scale != 1.0:
                    img_result = cv2.resize(img_result, (min(800, int(img_result.shape[1]*f_scale)), min(800, int(img_result.shape[0] * f_scale))), interpolation=cv2.INTER_LINEAR)
                #print(f'ri_w{img_result.shape[1]} ri_h{img_result.shape[0]}')
                #print(f"gi_w{img_graph.shape[1]} gi_h{img_graph.shape[0]}")
                img_save[0:img_result.shape[0], 0:img_result.shape[1]] = img_result
                img_save[0:img_graph.shape[0], img_result.shape[1]:img_result.shape[1] + img_graph.shape[1]] = img_graph
                for c, card in enumerate(reversed(found_cards[-10:]), 1):
                start_at = max(0,list_names_from-10) 
                end_at = min(len(found_cards), list_names_from)
                for c, card in enumerate(reversed(found_cards[start_at:end_at]), 1):
                    cv2.putText(img_save, f'{card[0]} ({card[1].upper()})',(0, height-200+18*c), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0))
            else:
                img_save = img_result
@@ -598,17 +725,37 @@
            print('Elapsed time: %.2f ms' % elapsed_ms)
            if out_path is not None:
                vid_writer.write(img_save.astype(np.uint8))
            cv2.waitKey(1)
            if debug:
                print("Waiting for keypress to continue")
                inp = cv2.waitKey(0)
            else:
                inp = cv2.waitKey(1)
            if 'u' == chr(inp & 255):
                if len(found_cards) > 0:
                    del found_cards[list_names_from-1]
                    list_names_from = min(len(found_cards), max(0, list_names_from))

                #os.sleep(1000)
            elif 'p' == chr(inp & 255):
                list_names_from = max(1, list_names_from - 1)
            elif 'o' == chr(inp & 255):
                list_names_from = min(len(found_cards),list_names_from + 1)
            elif 'q' == chr(inp & 255):
                break
    except KeyboardInterrupt:
        print("KeyboardInterrupt happened")
    finally:
        write_found_cards(found_cards)
        capture.release()
        if out_path is not None:
            vid_writer.release()
        cv2.destroyAllWindows()

        with open('detect.txt', 'w') as of:
            counter = collections.Counter(found_cards)
            for key in counter:
                of.write(f'{counter[key]} [{key[1].upper()}] {key[0]}\n')
def write_found_cards(found_cards):
    with open('detect.txt', 'w') as of:
        counter = collections.Counter(found_cards)
        for key in counter:
            of.write(f'{counter[key]} {key[0]} [{key[1].upper()}]\n')



@@ -624,6 +771,8 @@
        # Merge database for all cards, then calculate pHash values of each, store them
        df_list = []
        for set_name in Config.all_set_list:
            if set_name == 'con':
                set_name = 'con__'
            csv_name = '%s/csv/%s.csv' % (Config.data_dir, set_name)
            df = fetch_data.load_all_cards_text(csv_name)
            df_list.append(df)
@@ -632,7 +781,7 @@
        card_pool.drop('Unnamed: 0', axis=1, inplace=True, errors='ignore')
        card_pool = calc_image_hashes(card_pool, save_to=pck_path, hash_size=hash_sizes)
    ch_key = 'card_hash_%d' % args.hash_size
    set_key = 'set_hash_%d' % args.hash_size
    set_key = 'set_hash_%d' % 64
    if ch_key not in card_pool.columns:
        # we did not generate this hash_size yet
        print('We need to add hash_size=%d' % (args.hash_size,))
@@ -642,23 +791,38 @@

    # Processing time is almost linear to the size of the database
    # Program can be much faster if the search scope for the card can be reduced
    card_pool = card_pool[card_pool['set'].isin(Config.set_2003_list)]
    #card_pool = card_pool[card_pool['set'].isin(Config.set_2003_list)]

    # ImageHash is basically just one numpy.ndarray with (hash_size)^2 number of bits. pre-emptively flattening it
    # significantly increases speed for subtracting hashes in the future.
    card_pool[ch_key] = card_pool[ch_key].apply(lambda x: x.hash.flatten())
    card_pool[set_key] = card_pool[set_key].apply(lambda x: x.hash.flatten())

    print("Hash-Database setup done")
    # If the test file isn't given, use webcam to capture video
    if args.in_path is None:
        capture = cv2.VideoCapture(0, cv2.CAP_V4L)
        capture.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*"MJPG"))
        capture.set(cv2.CAP_PROP_FRAME_WIDTH, 1920)
        capture.set(cv2.CAP_PROP_FRAME_HEIGHT, 1080)
        detect_video(capture, card_pool, hash_size=args.hash_size, out_path='%s/result.avi' % args.out_path,
                     display=args.display, show_graph=args.show_graph, debug=args.debug, crop_x=500, crop_y=200)
        if args.stream_url is None:
            print("Using webcam") 
            capture = cv2.VideoCapture(0)
            capture.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*"MJPG"))
            capture.set(cv2.CAP_PROP_FRAME_WIDTH, args.rx)
            capture.set(cv2.CAP_PROP_FRAME_HEIGHT, args.ry)
        else:
            print(f"Using stream {args.stream_url}")
            capture = cv2.VideoCapture(args.stream_url)

        thres = int((args.rx-2*args.crop_x)*(args.ry-2*args.crop_y)*(float(args.threshold_percent)/100))
        print('Threshold:', thres)
        if args.out_path is None:
            out_path = None
        else:
            out_path = '%s/result.avi' % args.out_path
        detect_video(capture, card_pool, hash_size=args.hash_size, out_path=out_path,
                     display=args.display, show_graph=args.show_graph, debug=args.debug,
                     crop_x=args.crop_x, crop_y=args.crop_y, size_thresh=thres,
                     rotate=args.rotate, flip=args.flip, tesseract=args.tesseract)
        capture.release()
    else:
        print(f"Using image or video {args.in_path}")
        # Save the detection result if args.out_path is provided
        if args.out_path is None:
            out_path = None
@@ -674,13 +838,17 @@
        if test_ext in ['jpg', 'jpeg', 'bmp', 'png', 'tiff']:
            # Test file is an image
            img = cv2.imread(args.in_path)
            if img is None:
                print('Could not read', args.in_path)
            detect_frame(img, card_pool, hash_size=args.hash_size, out_path=out_path, display=args.display,
                         debug=args.debug)
        else:
            # Test file is a video
            capture = cv2.VideoCapture(args.in_path)
            detect_video(capture, card_pool, hash_size=args.hash_size, out_path=out_path, display=args.display,
                         show_graph=args.show_graph, debug=args.debug)
                         show_graph=args.show_graph, debug=args.debug,
                         rotate=args.rotate, flip=args.flip, tesseract=args.tesseract)

            capture.release()
    pass

@@ -698,6 +866,15 @@
    parser.add_argument('-dbg', '--debug', dest='debug', help='Enable debug mode', action='store_true', default=False)
    parser.add_argument('-gph', '--show_graph', dest='show_graph', help='Display the graph for video output', 
                        action='store_true', default=False)
    parser.add_argument('-s', '--stream', dest='stream_url', type=str)
    parser.add_argument('-cx', '--crop-x', dest='crop_x', help='crop x amount of pixel on each side in x-axis', type=int, default=0)
    parser.add_argument('-cy', '--crop-y', dest='crop_y', help='crop x amount of pixel on each side in y-axis', type=int, default=0)
    parser.add_argument('-tp', '--threshold-percent', dest='threshold_percent', help='percentage amount that the card image needs to take up to be detected',type=int, default=5)
    parser.add_argument('-r', '--rotate', dest='rotate', help='Rotate image before usage 0 90_CLOCK, 1 180, 2 90 COUNTER_CLOCK', type=int, default=None)
    parser.add_argument('-f', '--flip', dest='flip', help='flip image before using, this is done before rotation -1(both axis), 0(x-axis), 1(y-axis)', type=int, default=None)
    parser.add_argument('-rx', '--resolution-x', dest='rx', help='X-Resolution of the source, defaults to 1920', type=int, default=1920)
    parser.add_argument('-ry', '--resulution-y', dest='ry', help="Y-Resolution of the source, defaults to 1080", type=int, default=1080)
    parser.add_argument('-t', '--tesseract', dest='tesseract', help='enable tesseract edition detection (not used only displayed)', action='store_true', default=False)
    args = parser.parse_args()
    if not args.display and args.out_path is None:
        # Then why the heck are you running this thing in the first place?