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 |  123 +++++++++++++++++++++++++++++++----------
 1 files changed, 93 insertions(+), 30 deletions(-)

diff --git a/opencv_dnn.py b/opencv_dnn.py
index 7801bc3..e9b8d5a 100644
--- a/opencv_dnn.py
+++ b/opencv_dnn.py
@@ -9,7 +9,7 @@
 import pandas as pd
 from PIL import Image
 import time
-
+from multiprocessing import Pool
 from config import Config
 import fetch_data
 
@@ -22,25 +22,14 @@
 https://github.com/hj3yoo/mtg_card_detector/tree/dea64611730c84a59c711c61f7f80948f82bcd31 
 """
 
-
-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]
-    
-    # Since some double-faced cards may result in two different cards, create a new dataframe to store the result
+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['art_hash_%d' % hs] = np.NaN
+        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:
             print('Calculating hashes: %dth card' % ind)
@@ -72,16 +61,46 @@
                 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
+    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 = 15
+    num_partitions = 60
+    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)
@@ -209,19 +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)
+    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
@@ -237,7 +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:
@@ -306,7 +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
@@ -342,15 +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)
@@ -358,7 +413,7 @@
                     cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)
         if debug:
             # cv2.rectangle(img_warp, (22, 47), (294, 249), (0, 255, 0), 2)
-            cv2.putText(img_warp, card_name + ', ' + str(hash_diff), (0, 20),
+            cv2.putText(img_warp, card_name + ':' + card_set + ', ' + str(hash_diff), (0, 20),
                         cv2.FONT_HERSHEY_SIMPLEX, 0.4, (255, 255, 255), 1)
             cv2.imshow('card#%d' % i, img_warp)
     if display:
@@ -467,7 +522,8 @@
 
 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)
@@ -482,9 +538,15 @@
         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')
-        calc_image_hashes(card_pool, save_to=pck_path)
+        card_pool = calc_image_hashes(card_pool, save_to=pck_path, hash_size=hash_sizes)
     ch_key = 'card_hash_%d' % args.hash_size
-    card_pool = card_pool[['name', 'set', 'collector_number', ch_key]]
+    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, 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
@@ -493,6 +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