import argparse
|
import ast
|
import collections
|
import cv2
|
import imagehash as ih
|
import numpy as np
|
from operator import itemgetter
|
import os
|
import pandas as pd
|
from PIL import Image
|
import time
|
from multiprocessing import Pool
|
from config import Config
|
import fetch_data
|
import pytesseract
|
|
|
"""
|
As of the current version, the YOLO network has been removed from this code during optimization.
|
It was found out that YOLO was adding too much processing delay, and the benefits from using it couldn't justify
|
such heavy cost.
|
If you're interested to see the implementation using YOLO, please check out the previous commit:
|
https://github.com/hj3yoo/mtg_card_detector/tree/dea64611730c84a59c711c61f7f80948f82bcd31
|
"""
|
|
def do_calc(args):
|
card_pool = args[0]
|
hash_size = args[1]
|
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' % 64] = np.NaN
|
#new_pool['art_hash_%d' % hs] = np.NaN
|
for ind, card_info in card_pool.iterrows():
|
if ind % 100 == 0:
|
print('Calculating hashes: %dth card' % ind)
|
|
card_names = []
|
# Double-faced cards have a different json format than normal cards
|
if card_info['layout'] in ['transform', 'double_faced_token']:
|
if isinstance(card_info['card_faces'], str):
|
card_faces = ast.literal_eval(card_info['card_faces'])
|
else:
|
card_faces = card_info['card_faces']
|
for i in range(len(card_faces)):
|
card_names.append(card_faces[i]['name'])
|
else: # if card_info['layout'] == 'normal':
|
card_names.append(card_info['name'])
|
|
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(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, set_name))
|
card_img = cv2.imread(img_name)
|
if card_img is None:
|
print('WARNING: card %s is not found!' % img_name)
|
continue
|
"""
|
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.phash(img_set, hash_size=64)
|
card_info['card_hash_%d' % hs] = card_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
|
new_pool.loc[0 if new_pool.empty else new_pool.index.max() + 1] = card_info
|
return new_pool
|
|
def calc_image_hashes(card_pool, save_to=None, hash_size=None):
|
"""
|
Calculate perceptual hash (pHash) value for each cards in the database, then store them if needed
|
:param card_pool: pandas dataframe containing all card information
|
:param save_to: path for the pickle file to be saved
|
:param hash_size: param for pHash algorithm
|
:return: pandas dataframe
|
"""
|
if hash_size is None:
|
hash_size = [16, 32]
|
elif isinstance(hash_size, int):
|
hash_size = [hash_size]
|
|
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)
|
df_split = np.array_split(card_pool, num_partitions)
|
new_pool = pd.concat(pool.map(do_calc, [(split, hash_size) for split in df_split]))
|
pool.close()
|
pool.join()
|
# Since some double-faced cards may result in two different cards, create a new dataframe to store the result
|
|
if save_to is not None:
|
new_pool.to_pickle(save_to)
|
return new_pool
|
|
|
# www.pyimagesearch.com/2014/08/25/4-point-opencv-getperspective-transform-example/
|
def order_points(pts):
|
"""
|
initialzie a list of coordinates that will be ordered such that the first entry in the list is the top-left,
|
the second entry is the top-right, the third is the bottom-right, and the fourth is the bottom-left
|
:param pts: array containing 4 points
|
:return: ordered list of 4 points
|
"""
|
rect = np.zeros((4, 2), dtype="float32")
|
|
# the top-left point will have the smallest sum, whereas
|
# the bottom-right point will have the largest sum
|
s = pts.sum(axis=1)
|
rect[0] = pts[np.argmin(s)]
|
rect[2] = pts[np.argmax(s)]
|
|
# now, compute the difference between the points, the
|
# top-right point will have the smallest difference,
|
# whereas the bottom-left will have the largest difference
|
diff = np.diff(pts, axis=1)
|
rect[1] = pts[np.argmin(diff)]
|
rect[3] = pts[np.argmax(diff)]
|
|
# return the ordered coordinates
|
return rect
|
|
|
def four_point_transform(image, pts):
|
"""
|
Transform a quadrilateral section of an image into a rectangular area
|
From: www.pyimagesearch.com/2014/08/25/4-point-opencv-getperspective-transform-example/
|
:param image: source image
|
:param pts: 4 corners of the quadrilateral
|
:return: rectangular image of the specified area
|
"""
|
# obtain a consistent order of the points and unpack them
|
# individually
|
rect = order_points(pts)
|
(tl, tr, br, bl) = rect
|
|
# compute the width of the new image, which will be the
|
# maximum distance between bottom-right and bottom-left
|
# x-coordiates or the top-right and top-left x-coordinates
|
widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
|
widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
|
maxWidth = max(int(widthA), int(widthB))
|
|
# compute the height of the new image, which will be the
|
# maximum distance between the top-right and bottom-right
|
# y-coordinates or the top-left and bottom-left y-coordinates
|
heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
|
heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
|
maxHeight = max(int(heightA), int(heightB))
|
|
# now that we have the dimensions of the new image, construct
|
# the set of destination points to obtain a "birds eye view",
|
# (i.e. top-down view) of the image, again specifying points
|
# in the top-left, top-right, bottom-right, and bottom-left
|
# order
|
dst = np.array([
|
[0, 0],
|
[maxWidth - 1, 0],
|
[maxWidth - 1, maxHeight - 1],
|
[0, maxHeight - 1]], dtype="float32")
|
|
# compute the perspective transform matrix and then apply it
|
mat = cv2.getPerspectiveTransform(rect, dst)
|
warped = cv2.warpPerspective(image, mat, (maxWidth, maxHeight))
|
|
# If the image is horizontally long, rotate it by 90
|
if maxWidth > maxHeight:
|
center = (maxHeight / 2, maxHeight / 2)
|
mat_rot = cv2.getRotationMatrix2D(center, 270, 1.0)
|
warped = cv2.warpAffine(warped, mat_rot, (maxHeight, maxWidth))
|
|
# return the warped image
|
return warped
|
|
|
def remove_glare(img):
|
"""
|
Reduce the effect of glaring in the image
|
Inspired from:
|
http://www.amphident.de/en/blog/preprocessing-for-automatic-pattern-identification-in-wildlife-removing-glare.html
|
The idea is to find area that has low saturation but high value, which is what a glare usually look like.
|
:param img: source image
|
:return: corrected image with glaring smoothened out
|
"""
|
img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
|
_, s, v = cv2.split(img_hsv)
|
non_sat = (s < 32) * 255 # Find all pixels that are not very saturated
|
|
# Slightly decrease the area of the non-satuared pixels by a erosion operation.
|
disk = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
|
non_sat = cv2.erode(non_sat.astype(np.uint8), disk)
|
|
# Set all brightness values, where the pixels are still saturated to 0.
|
v[non_sat == 0] = 0
|
# filter out very bright pixels.
|
glare = (v > 200) * 255
|
|
# Slightly increase the area for each pixel
|
glare = cv2.dilate(glare.astype(np.uint8), disk)
|
glare_reduced = np.ones((img.shape[0], img.shape[1], 3), dtype=np.uint8) * 200
|
glare = cv2.cvtColor(glare, cv2.COLOR_GRAY2BGR)
|
corrected = np.where(glare, glare_reduced, img)
|
return corrected
|
|
|
def find_card(img, thresh_c=5, kernel_size=(3, 3), size_thresh=10000, debug=False):
|
"""
|
Find contours of all cards in the image
|
:param img: source image
|
:param thresh_c: value of the constant C for adaptive thresholding
|
:param kernel_size: dimension of the kernel used for dilation and erosion
|
:param size_thresh: threshold for size (in pixel) of the contour to be a candidate
|
:return: list of candidate contours
|
"""
|
# Typical pre-processing - grayscale, blurring, thresholding
|
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
|
img_blur = cv2.medianBlur(img_gray, 5)
|
img_thresh = cv2.adaptiveThreshold(img_blur, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 11, thresh_c)
|
if debug:
|
cv2.imshow('Thres', img_thresh)
|
# Dilute the image, then erode them to remove minor noises
|
kernel = np.ones(kernel_size, np.uint8)
|
img_dilate = cv2.dilate(img_thresh, kernel, iterations=1)
|
img_erode = cv2.erode(img_dilate, kernel, iterations=1)
|
if debug:
|
cv2.imshow('Eroded', img_erode)
|
# Find the contour
|
cnts, hier = cv2.findContours(img_erode, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
|
if len(cnts) == 0:
|
# 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]))
|
if debug:
|
cv2.drawContours(img_cont, cnts2, -1, (0, 255, 0), 3)
|
cv2.imshow('Contours', img_cont)
|
# The hierarchy from cv2.findContours() is similar to a tree: each node has an access to the parent, the first child
|
# their previous and next node
|
# Using recursive search, find the uppermost contour in the hierarchy that satisfies the condition
|
# The candidate contour must be rectangle (has 4 points) and should be larger than a threshold
|
cnts_rect = []
|
stack = [(0, hier[0][0])]
|
while len(stack) > 0:
|
i_cnt, h = stack.pop()
|
i_next, i_prev, i_child, i_parent = h
|
if i_next != -1:
|
stack.append((i_next, hier[0][i_next]))
|
cnt = cnts[i_cnt]
|
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:
|
img_ccont = img_cont_base.copy()
|
# lets collect all children
|
c_list = [cnts[i_child]]
|
h_info = hier[0][i_child]
|
while h_info[0] != -1:
|
cld = cnts[h_info[0]]
|
c_list.append(cld)
|
h_info = hier[0][h_info[0]]
|
# child with biggest area
|
c_list.sort(key=cv2.contourArea, reverse=True)
|
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', 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('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)
|
cnts_rect.append(approx)
|
else:
|
#print('CF:', (c_size/size))
|
#print('Size:', size)
|
cnts_rect.append(approx)
|
else:
|
if i_child != -1:
|
stack.append((i_child, hier[0][i_child]))
|
return cnts_rect
|
|
|
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
|
:param exist_cards: History of all detected cards in the previous (f_len) frames
|
:param card_pool: pandas dataframe of all card's information
|
:param f_len: length of windows (in frames) to consider for confidence level
|
:return:
|
"""
|
# Lots of constants to set the dimension of each elements
|
w_card = 63 # Width of the card image displayed
|
h_card = 88
|
gap = 25 # Offset between each elements
|
gap_sm = 10 # Small offset
|
w_bar = 300 # Length of the confidence bar at 100%
|
h_bar = 12
|
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
|
img_graph = np.zeros((h_img, w_img, 3), dtype=np.uint8)
|
x_anchor = gap
|
y_anchor = gap
|
|
i = 0
|
|
# Cards are displayed from the most confident to the least
|
# Confidence level is calculated by number of frames that the card was detected in
|
for key, val in sorted(exist_cards.items(), key=itemgetter(1), reverse=True)[:n_cards_p_col * 2]:
|
card_name = key[:key.find('(') - 1]
|
card_set = key[key.find('(') + 1:key.find(')')]
|
confidence = sum(val) / f_len
|
card_info = card_pool[(card_pool['name'] == card_name) & (card_pool['set'] == card_set)].iloc[0]
|
img_name = '%s/card_img/tiny/%s/%s_%s.png' % (Config.data_dir, card_info['set'],
|
card_info['collector_number'],
|
fetch_data.get_valid_filename(card_info['name']))
|
# If the card image is not found, just leave it blank
|
if os.path.exists(img_name):
|
card_img = cv2.imread(img_name)
|
else:
|
card_img = np.ones((h_card, w_card, 3)) * 255
|
cv2.putText(card_img, 'X', ((w_card - int(txt_scale * 25)) // 2, (h_card + int(txt_scale * 25)) // 2),
|
cv2.FONT_HERSHEY_SIMPLEX, txt_scale, (0, 0, 0), 2)
|
|
# Insert the card image, card name, and confidence bar to the graph
|
img_graph[y_anchor:y_anchor + h_card, x_anchor:x_anchor + w_card] = card_img
|
cv2.putText(img_graph, '%s (%s)' % (card_name, card_set),
|
(x_anchor + w_card + gap, y_anchor + gap_sm + int(txt_scale * 25)), cv2.FONT_HERSHEY_SIMPLEX,
|
txt_scale, (255, 255, 255), 1)
|
cv2.rectangle(img_graph, (x_anchor + w_card + gap, y_anchor + h_card - (gap_sm + h_bar)),
|
(x_anchor + w_card + gap + int(w_bar * confidence), y_anchor + h_card - gap_sm), (0, 255, 0),
|
thickness=cv2.FILLED)
|
y_anchor += h_card + gap
|
i += 1
|
if i % n_cards_p_col == 0:
|
x_anchor += w_card + gap + w_bar + gap
|
y_anchor = gap
|
pass
|
return img_graph
|
|
|
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
|
:param card_pool: pandas dataframe of all card's information
|
:param hash_size: param for pHash algorithm
|
:param size_thresh: threshold for size (in pixel) of the contour to be a candidate
|
:param out_path: path to save the result
|
:param display: flag for displaying the result
|
:param debug: flag for debug mode
|
:return: list of detected card's name/set and resulting image
|
"""
|
|
img_result = img.copy() # For displaying and saving
|
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])
|
img_warp = four_point_transform(img, pts)
|
|
# To identify the card from the card image, perceptual hashing (pHash) algorithm is used
|
# Perceptual hash is a hash string built from features of the input medium. If two media are similar
|
# (ie. has similar features), their resulting pHash value will be very close.
|
# Using this property, the matching card for the given card image can be found by comparing pHash of
|
# all cards in the database, then finding the card that results in the minimal difference in pHash value.
|
'''
|
img_art = img_warp[47:249, 22:294]
|
img_art = Image.fromarray(img_art.astype('uint8'), 'RGB')
|
art_hash = ih.phash(img_art, hash_size=hash_size).hash.flatten()
|
card_pool['hash_diff'] = card_pool['art_hash'].apply(lambda x: np.count_nonzero(x != art_hash))
|
'''
|
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)
|
img_set_part = img_warp[cut[0]:cut[1], cut[2]:cut[3]]
|
#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()
|
card_pool['hash_diff'] = card_pool['card_hash_%d' % hash_size]
|
card_pool['hash_diff'] = card_pool['hash_diff'].apply(lambda x: np.count_nonzero(x != card_hash))
|
min_card = card_pool[card_pool['hash_diff'] == min(card_pool['hash_diff'])].iloc[0]
|
hash_diff = min_card['hash_diff']
|
|
top_matches = sorted(card_pool['hash_diff'])
|
card_one = card_pool[card_pool['hash_diff'] == top_matches[0]].iloc[0]
|
card_two = card_pool[card_pool['hash_diff'] == top_matches[1]].iloc[0]
|
|
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))
|
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])
|
|
|
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)
|
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'])
|
|
min_card = best_match
|
card_name = min_card['name']
|
card_set = min_card['set']
|
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, 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*scale+0.1, (255, 255, 255), 1)
|
cv2.imshow('card#%d' % i, img_warp)
|
if display:
|
cv2.imshow('Result', img_result)
|
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, 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
|
:param card_pool: pandas dataframe of all card's information
|
:param hash_size: param for pHash algorithm
|
:param size_thresh: threshold for size (in pixel) of the contour to be a candidate
|
:param out_path: path to save the result
|
:param display: flag for displaying the result
|
:param show_graph: flag to show graph
|
:param debug: flag for debug mode
|
: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 = 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 = 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()
|
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, 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
|
# If the card wasn't previously detected, make a new list and add 1 to it
|
# If the same card is detected multiple times in the same frame, keep track of the duplicates
|
# The confidence will be calculated based on the number of frames the card was detected for
|
det_cards_count = collections.Counter(det_cards).items()
|
det_cards_list = []
|
for card, count in det_cards_count:
|
card_name, card_set = card
|
for i in range(count): 1
|
key = '%s (%s) #%d' % (card_name, card_set, i + 1)
|
det_cards_list.append(key)
|
gone = []
|
for key, val in exist_cards.items():
|
if key in det_cards_list:
|
exist_cards[key] = exist_cards[key][1 - f_len:] + [1]
|
else:
|
exist_cards[key] = exist_cards[key][1 - f_len:] + [0]
|
if len(val) == f_len and sum(val) == 0:
|
gone.append(key) # not there anymore
|
|
det_card_map = {}
|
gone_single = []
|
for card_name, card_set in det_cards:
|
skey = '%s (%s)' % (card_name, card_set)
|
det_card_map[skey] = (card_name, card_set)
|
|
for key, val in exist_card_single.items():
|
if key in det_card_map:
|
exist_card_single[key] = exist_card_single[key][1 - f_len:] + [1]
|
else:
|
exist_card_single[key] = exist_card_single[key][1 - f_len:] + [0]
|
|
if len(val) == f_len and sum(val) == 0:
|
gone_single.append(key)
|
if key in written_out_cards:
|
written_out_cards.remove(key)
|
if len(val) == f_len and sum(val) == f_len:
|
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():
|
exist_card_single[key] = [1]
|
for key in gone_single:
|
exist_card_single.pop(key)
|
|
|
for key in det_cards_list:
|
if key not in exist_cards.keys():
|
exist_cards[key] = [1]
|
for key in gone:
|
exist_cards.pop(key)
|
|
|
# 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)
|
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
|
|
# Display the result
|
if display:
|
cv2.imshow('result', img_save)
|
if debug:
|
max_num_obj = max(max_num_obj, len(det_cards))
|
for i in range(len(det_cards), max_num_obj):
|
cv2.imshow('card#%d' % i, np.zeros((1, 1), dtype=np.uint8))
|
|
elapsed_ms = (time.time() - start_time) * 1000
|
print('Elapsed time: %.2f ms' % elapsed_ms)
|
if out_path is not None:
|
vid_writer.write(img_save.astype(np.uint8))
|
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()
|
|
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')
|
|
|
|
def main(args):
|
# Specify paths for all necessary files
|
hash_sizes = {16, 32}
|
hash_sizes.add(args.hash_size)
|
pck_path = os.path.abspath('card_pool.pck')
|
if os.path.isfile(pck_path):
|
card_pool = pd.read_pickle(pck_path)
|
else:
|
print('Warning: pickle for card database %s is not found!' % pck_path)
|
# 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)
|
card_pool = pd.concat(df_list, sort=True)
|
card_pool.reset_index(drop=True, inplace=True)
|
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' % 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,))
|
card_pool = calc_image_hashes(card_pool, save_to=pck_path, hash_size=[args.hash_size])
|
|
card_pool = card_pool[['name', 'set', 'collector_number', ch_key, set_key]]
|
|
# 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)]
|
|
# 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:
|
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
|
else:
|
f_name = os.path.split(args.in_path)[1]
|
out_path = '%s/%s.avi' % (args.out_path, f_name[:f_name.find('.')])
|
|
if not os.path.isfile(args.in_path):
|
print('The test file %s doesn\'t exist!' % os.path.abspath(args.in_path))
|
return
|
# Check if test file is image or video
|
test_ext = args.in_path[args.in_path.find('.') + 1:]
|
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,
|
rotate=args.rotate, flip=args.flip, tesseract=args.tesseract)
|
|
capture.release()
|
pass
|
|
|
if __name__ == '__main__':
|
parser = argparse.ArgumentParser()
|
parser.add_argument('-i', '--in', dest='in_path', help='Path of the input file. For webcam, leave it blank',
|
type=str)
|
parser.add_argument('-o', '--out', dest='out_path', help='Path of the output directory to save the result',
|
type=str)
|
parser.add_argument('-hs', '--hash_size', dest='hash_size',
|
help='Size of the hash for pHash algorithm', type=int, default=16)
|
parser.add_argument('-dsp', '--display', dest='display', help='Display the result', action='store_true',
|
default=False)
|
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?
|
print('The program isn\'t displaying nor saving any output file. Please change the setting and try again.')
|
exit()
|
main(args)
|
