Now using FLANN feature matching instead. Still using SIFT feature matcher

runner.py

@@ -6,8 +6,8 @@ dstPoints = np.array([(out_height, 0), (0, 0),  (0, out_width), (out_height, out
 
 
 
-img = cv2.imread("IMG_2070.jpeg")
-img2 = cv2.imread("pls_bo33.jpg")
+img = cv2.imread("IMG_2086.jpeg")
+img2 = cv2.imread("new_baseline_board.png")
 img_tmp = img.copy()
 
 gray_tmp = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
@@ -48,7 +48,7 @@ gray_2 = cv2.cvtColor(img_tmp_tmp, cv2.COLOR_BGR2GRAY)
 gray_3 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)
 
 MAX_FEATURES = 500
-GOOD_MATCH_PERCENT = 0.002
+GOOD_MATCH_PERCENT = 0.0005
 
 
 cv2.imwrite('pls_lasse.jpg', img)
@@ -57,6 +57,8 @@ img_tmp = img.copy()
 gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 
 sift = cv2.xfeatures2d.SIFT_create()
+#sift = cv2.ORB_create(MAX_FEATURES)
+#sift = cv2.xfeatures2d.SURF_create()
 kp = sift.detect(gray_2, None)
 kp2 = sift.detect(gray_3, None)
 
@@ -66,11 +68,68 @@ kp2, des2 = sift.compute(gray_3, kp2)
 cv2.drawKeypoints(img_tmp_tmp, keypoints=kp, outImage=img_tmp_tmp)
 cv2.imwrite('keypoints_img.jpg', img_tmp_tmp)
 
-matcher = cv2.DescriptorMatcher_create(cv2.DESCRIPTOR_MATCHER_BRUTEFORCE_SL2)
-matches = matcher.match(des, des2, None)
+# FLANN parameters
+FLANN_INDEX_KDTREE = 0
+index_params = dict(algorithm = FLANN_INDEX_KDTREE, trees = 8)
+search_params = dict(checks=100)   # or pass empty dictionary
+
+
+#matcher = cv2.DescriptorMatcher_create(cv2.DESCRIPTOR_MATCHER_BRUTEFORCE_HAMMING)
+#matches = matcher.match(des, des2, None)
+
+
+flann = cv2.FlannBasedMatcher(index_params,search_params)
+matches = flann.knnMatch(des, des2, k=2)
+
+# Need to draw only good matches, so create a mask
+matchesMask = [[0,0] for i in range(len(matches))]
+
+
+
+
+good_matches = []
+# ratio test as per Lowe's paper
+for i,(m,n) in enumerate(matches):
+    if m.distance < 0.5*n.distance:
+        matchesMask[i]=[1,0]
+        good_matches.append([m,n])
+
+draw_params = dict(matchColor = (0,255,0),
+                   singlePointColor = (255,0,0),
+                   matchesMask = matchesMask,
+                   flags = 0)
+
+img3 = cv2.drawMatchesKnn(img_tmp_tmp, kp, img2, kp2, matches, None, **draw_params)
+cv2.imwrite("matches.jpg", img3)
+
+
+matches.sort(key=lambda x: x[0].distance, reverse=False)
+# Remove poor matches
+numGoodMatches = int(len(matches) * GOOD_MATCH_PERCENT)
+#good_matches = matches[:numGoodMatches]
+
+# Extract location of good matches
+points1 = np.zeros((len(good_matches), 2), dtype=np.float32)
+points2 = np.zeros((len(good_matches), 2), dtype=np.float32)
+
+for i, (m, n) in enumerate(good_matches):
+    points1[i, :] = kp[m.queryIdx].pt
+    points2[i, :] = kp2[m.trainIdx].pt
+
+print(points1)
+print(len(points2))
+
+h, mask = cv2.findHomography(points1, points2, cv2.RANSAC)
+
+height, width, channels = img2.shape
+im1Reg = cv2.warpPerspective(img_tmp_tmp, h, (width, height))
+
+cv2.imwrite('homo_pls_fuck.jpg', im1Reg)
+
+'''
 
 # Sort matches by score
-matches.sort(key=lambda x: x.distance, reverse=False)
+matches.sort(key=lambda x: x[0].distance, reverse=False)
 
 # Remove poor matches
 numGoodMatches = int(len(matches) * GOOD_MATCH_PERCENT)
@@ -88,13 +147,18 @@ for i, match in enumerate(matches):
     points1[i, :] = kp[match.queryIdx].pt
     points2[i, :] = kp2[match.trainIdx].pt
 
+print(len(points1))
+print(len(points2))
+'''
 
+'''
 h, mask = cv2.findHomography(points1, points2, cv2.RANSAC)
 
 height, width, channels = img2.shape
 im1Reg = cv2.warpPerspective(img_tmp_tmp, h, (width, height))
 
 cv2.imwrite('homo_pls_fuck.jpg', im1Reg)
+'''
 
 
 '''