~speedprog/mtg/mtg_card_detector.git

			@@ -12,6 +12,7 @@
			from multiprocessing import Pool
			from config import Config
			import fetch_data
			import pytesseract


			"""
			@@ -79,7 +80,7 @@
			cnts2 = sorted(cnts, key=cv2.contourArea, reverse=True)
			cnts2 = cnts2[:10]
			if True:
			cv2.drawContours(img_cc, cnts2, -1, (0, 255, 0), 3)
			cv2.rawContours(img_cc, cnts2, -1, (0, 255, 0), 3)
			#cv2.imshow('Contours', card_img)
			#cv2.waitKey(10000)
			"""
			@@ -336,7 +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
			@@ -352,7 +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
			@@ -398,7 +399,7 @@


			def detect_frame(img, card_pool, hash_size=32, size_thresh=10000,
			out_path=None, display=True, debug=False):
			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
			@@ -436,6 +437,8 @@
			'''
			img_card = Image.fromarray(img_warp.astype('uint8'), 'RGB')
			img_card_size = img_warp.shape

			# 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)
			@@ -445,6 +448,52 @@
			#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()
			@@ -481,13 +530,16 @@
			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, (int(min(pts[0][0], pts[1][0])), int(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)
			@@ -498,9 +550,12 @@
			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
			@@ -514,22 +569,40 @@
			: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 = []
			@@ -538,6 +611,12 @@
			ret, frame = capture.read()
			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]
			@@ -546,7 +625,7 @@
			x_max_index = frame.shape[1]

			croped_img = frame[crop_y:y_max_index, crop_x:x_max_index]
			fimg = cv2.flip(croped_img, -1)
			fimg = croped_img
			start_time = time.time()
			if not ret:
			# End of video
			@@ -558,7 +637,7 @@
			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
			@@ -620,6 +699,11 @@
			# 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
			start_at = max(0,list_names_from-10)
			@@ -720,20 +804,22 @@
			print("Using webcam")
			capture = cv2.VideoCapture(0)
			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)
			capture.set(cv2.CAP_PROP_FRAME_WIDTH, args.rx)
			capture.set(cv2.CAP_PROP_FRAME_HEIGHT, args.ry)
			else:
			print(f"Using streami {args.stream_url}")
			print(f"Using stream {args.stream_url}")
			capture = cv2.VideoCapture(args.stream_url)

			thres = int((1920-2args.crop_x)(1080-2args.crop_y)(float(args.threshold_percent)/100))
			thres = int((args.rx-2args.crop_x)(args.ry-2args.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)
			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}")
			@@ -760,7 +846,9 @@
			# 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

			@@ -782,6 +870,11 @@
			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?