From b7dd760578dbbde908c6779782a91cfcbc916d38 Mon Sep 17 00:00:00 2001
From: Constantin Wenger <constantin.wenger@googlemail.com>
Date: Fri, 21 Jun 2019 10:36:10 +0000
Subject: [PATCH] extra set detection code
---
opencv_dnn.py | 62 +++++++++++++++++++++++++++----
1 files changed, 54 insertions(+), 8 deletions(-)
diff --git a/opencv_dnn.py b/opencv_dnn.py
index 9621267..e9b8d5a 100644
--- a/opencv_dnn.py
+++ b/opencv_dnn.py
@@ -28,6 +28,7 @@
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['art_hash_%d' % hs] = np.NaN
for ind, card_info in card_pool.iterrows():
if ind % 100 == 0:
@@ -60,13 +61,20 @@
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]
+ #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)
for hs in hash_size:
card_hash = ih.phash(img_card, hash_size=hs)
+ set_hash = ih.whash(img_set, hash_size=hs)
card_info['card_hash_%d' % hs] = card_hash
+ card_info['set_hash_%d' % hs] = 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
@@ -220,19 +228,25 @@
# 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, 5, thresh_c)
-
+ img_thresh = cv2.adaptiveThreshold(img_blur, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 11, thresh_c)
+ 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)
-
+ 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)
+ cnts2 = sorted(cnts, key=cv2.contourArea, reverse=True)
+ cnts2 = cnts2[:10]
+ for i in range(0, len(cnts2)):
+ print(i, len(cnts2[i]))
+ 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
@@ -248,7 +262,8 @@
size = cv2.contourArea(cnt)
peri = cv2.arcLength(cnt, True)
approx = cv2.approxPolyDP(cnt, 0.04 * peri, True)
- if size >= size_thresh and len(approx) == 4:
+ if size >= size_thresh and len(approx) < 6:
+ print('Size:', size)
cnts_rect.append(approx)
else:
if i_child != -1:
@@ -317,7 +332,7 @@
return img_graph
-def detect_frame(img, card_pool, hash_size=32, size_thresh=10000,
+def detect_frame(img, card_pool, hash_size=32, size_thresh=100000,
out_path=None, display=True, debug=False):
"""
Identify all cards in the input frame, display or save the frame if needed
@@ -353,15 +368,44 @@
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
+ 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')
+ cv2.imshow("Set Img#%d" % i, img_set_part)
+
# 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'])
+ 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):
+ cdr = 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] = cdr
+ cd = cdr
+ 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_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))
- hash_diff = min_card['hash_diff']
# Render the result, and display them if needed
cv2.drawContours(img_result, [cnt], -1, (0, 255, 0), 2)
@@ -496,12 +540,13 @@
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
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]]
+ 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
@@ -510,6 +555,7 @@
# 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())
# If the test file isn't given, use webcam to capture video
if args.in_path is None:
--
Gitblit v1.10.0