add

Question_51_60/README.md

@@ -120,7 +120,7 @@ NCCは照明変化に強いと言われる。
 
 ZNCC(Zero means Normalized Cross Correlation)とは零平均正規化相互相関を類似度にする手法であり、Sが**最大**の位置がマッチング位置となる。
 
-画像Iの平均値をmi、画像Tの平均値をmtとすると、Sは次式で計算される。
+画像Iの平均値をmi、画像Tの平均値をmtとすると、Sは次式で計算される。（ただし、平均値はRGB成分ごとに減算する）
 
 ```bash
        Sum_{x=0:w, y=0:h} (I(i+x, j+y)-mi) * (T(x, y)-mt)
@@ -129,7 +129,7 @@ S = ----------------------------------------------------------------------------
 ```
 
 このSは、-1<=S<=1をとる。
-ZNCCは平均値を引くことでNCCよりも照明変化に強いと言われる。（だが今回は検出が失敗する。）
+ZNCCは平均値を引くことでNCCよりも照明変化に強いと言われる。
 
 |入力 (imori.jpg) |テンプレート画像(imori_part.jpg)|出力(answers/answer_57.jpg)|
 |:---:|:---:|:---:|

Question_51_60/answers/answer_51.py

@@ -2,65 +2,109 @@
 import numpy as np
 import matplotlib.pyplot as plt
 
+
+# Gray scale
+def BGR2GRAY(img):
+	b = img[:, :, 0].copy()
+	g = img[:, :, 1].copy()
+	r = img[:, :, 2].copy()
+
+	# Gray scale
+	out = 0.2126 * r + 0.7152 * g + 0.0722 * b
+	out = out.astype(np.uint8)
+
+	return out
+
+# Otsu Binalization
+def otsu_binarization(img, th=128):
+	H, W = img.shape
+	out = img.copy()
+
+	max_sigma = 0
+	max_t = 0
+
+	# determine threshold
+	for _t in range(1, 255):
+		v0 = out[np.where(out < _t)]
+		m0 = np.mean(v0) if len(v0) > 0 else 0.
+		w0 = len(v0) / (H * W)
+		v1 = out[np.where(out >= _t)]
+		m1 = np.mean(v1) if len(v1) > 0 else 0.
+		w1 = len(v1) / (H * W)
+		sigma = w0 * w1 * ((m0 - m1) ** 2)
+		if sigma > max_sigma:
+			max_sigma = sigma
+			max_t = _t
+
+	# Binarization
+	print("threshold >>", max_t)
+	th = max_t
+	out[out < th] = 0
+	out[out >= th] = 255
+
+	return out
+
+
+# Erosion
+def Erode(img, Erode_time=1):
+	H, W = img.shape
+	out = img.copy()
+
+	# kernel
+	MF = np.array(((0, 1, 0),
+				(1, 0, 1),
+				(0, 1, 0)), dtype=np.int)
+
+	# each erode
+	for i in range(Erode_time):
+		tmp = np.pad(out, (1, 1), 'edge')
+		# erode
+		for y in range(1, H+1):
+			for x in range(1, W+1):
+				if np.sum(MF * tmp[y-1:y+2, x-1:x+2]) < 255*4:
+					out[y-1, x-1] = 0
+
+	return out
+
+
+# Dilation
+def Dilate(img, Dil_time=1):
+	H, W = img.shape
+
+	# kernel
+	MF = np.array(((0, 1, 0),
+				(1, 0, 1),
+				(0, 1, 0)), dtype=np.int)
+
+	# each dilate time
+	out = img.copy()
+	for i in range(Dil_time):
+		tmp = np.pad(out, (1, 1), 'edge')
+		for y in range(1, H+1):
+			for x in range(1, W+1):
+				if np.sum(MF * tmp[y-1:y+2, x-1:x+2]) >= 255:
+					out[y-1, x-1] = 255
+
+	return out
+
+
 # Read image
 img = cv2.imread("imori.jpg").astype(np.float32)
-H, W, C = img.shape
-
-# Otsu binary
-## Grayscale
-out = 0.2126 * img[..., 2] + 0.7152 * img[..., 1] + 0.0722 * img[..., 0]
-out = out.astype(np.uint8)
-
-## Determine threshold of Otsu's binarization
-max_sigma = 0
-max_t = 0
-
-for _t in range(1, 255):
-    v0 = out[np.where(out < _t)[0]]
-    m0 = np.mean(v0) if len(v0) > 0 else 0.
-    w0 = len(v0) / (H * W)
-    v1 = out[np.where(out >= _t)[0]]
-    m1 = np.mean(v1) if len(v1) > 0 else 0.
-    w1 = len(v1) / (H * W)
-    sigma = w0 * w1 * ((m0 - m1) ** 2)
-    if sigma > max_sigma:
-        max_sigma = sigma
-        max_t = _t
-
-## Binarization
-#print("threshold >>", max_t)
-th = max_t
-out[out < th] = 0
-out[out >= th] = 255
-
-# Morphology filter
-MF = np.array(((0, 1, 0),
-               (1, 0, 1),
-               (0, 1, 0)), dtype=np.int)
-
-# Morphology - erode
-Erode_time = 1
-erode = out.copy()
-
-for i in range(Erode_time):
-    tmp = np.pad(out, (1, 1), 'edge')
-    for y in range(1, H+1):
-        for x in range(1, W+1):
-            if np.sum(MF * tmp[y-1:y+2, x-1:x+2]) < 255*4:
-                erode[y-1, x-1] = 0
-
-# Morphology - dilate
-Dil_time = 1
-dilate = out.copy()
-
-for i in range(Dil_time):
-    tmp = np.pad(out, (1, 1), 'edge')
-    for y in range(1, H+1):
-        for x in range(1, W+1):
-            if np.sum(MF * tmp[y-1:y+2, x-1:x+2]) >= 255:
-                dilate[y-1, x-1] = 255
-
-out = np.abs(erode - dilate) * 255
+
+# Grayscale
+gray = BGR2GRAY(img)
+
+# Otsu's binarization
+otsu = otsu_binarization(gray)
+
+# Erode image
+eroded = Erode(otsu)
+
+# Delate image
+dilated = Dilate(otsu)
+
+# Morphology
+out = np.abs(eroded - dilated) * 255
 
 # Save result
 cv2.imwrite("out.jpg", out)

Question_51_60/answers/answer_52.py

@@ -2,64 +2,110 @@
 import numpy as np
 import matplotlib.pyplot as plt
 
+# Gray scale
+def BGR2GRAY(img):
+	b = img[:, :, 0].copy()
+	g = img[:, :, 1].copy()
+	r = img[:, :, 2].copy()
+
+	# Gray scale
+	out = 0.2126 * r + 0.7152 * g + 0.0722 * b
+	out = out.astype(np.uint8)
+
+	return out
+
+# Otsu Binalization
+def otsu_binarization(img, th=128):
+	H, W = img.shape
+	out = img.copy()
+
+	max_sigma = 0
+	max_t = 0
+
+	# determine threshold
+	for _t in range(1, 255):
+		v0 = out[np.where(out < _t)]
+		m0 = np.mean(v0) if len(v0) > 0 else 0.
+		w0 = len(v0) / (H * W)
+		v1 = out[np.where(out >= _t)]
+		m1 = np.mean(v1) if len(v1) > 0 else 0.
+		w1 = len(v1) / (H * W)
+		sigma = w0 * w1 * ((m0 - m1) ** 2)
+		if sigma > max_sigma:
+			max_sigma = sigma
+			max_t = _t
+
+	# Binarization
+	print("threshold >>", max_t)
+	th = max_t
+	out[out < th] = 0
+	out[out >= th] = 255
+
+	return out
+
+
+# Erosion
+def Erode(img, Erode_time=1):
+	H, W = img.shape
+	out = img.copy()
+
+	# kernel
+	MF = np.array(((0, 1, 0),
+				(1, 0, 1),
+				(0, 1, 0)), dtype=np.int)
+
+	# each erode
+	for i in range(Erode_time):
+		tmp = np.pad(out, (1, 1), 'edge')
+		# erode
+		for y in range(1, H+1):
+			for x in range(1, W+1):
+				if np.sum(MF * tmp[y-1:y+2, x-1:x+2]) < 255*4:
+					out[y-1, x-1] = 0
+
+	return out
+
+
+# Dilation
+def Dilate(img, Dil_time=1):
+	H, W = img.shape
+
+	# kernel
+	MF = np.array(((0, 1, 0),
+				(1, 0, 1),
+				(0, 1, 0)), dtype=np.int)
+
+	# each dilate time
+	out = img.copy()
+	for i in range(Dil_time):
+		tmp = np.pad(out, (1, 1), 'edge')
+		for y in range(1, H+1):
+			for x in range(1, W+1):
+				if np.sum(MF * tmp[y-1:y+2, x-1:x+2]) >= 255:
+					out[y-1, x-1] = 255
+
+	return out
+
+# Opening morphology
+def Morphology_Opening(img, time=1):
+    dil = Dilate(img, Dil_time=time)
+    erode = Erode(dil, Erode_time=time)
+    return erode
+
 # Read image
 img = cv2.imread("imori.jpg").astype(np.float32)
-H, W, C = img.shape
-
-# Otsu binary
-## Grayscale
-out = 0.2126 * img[..., 2] + 0.7152 * img[..., 1] + 0.0722 * img[..., 0]
-out = out.astype(np.uint8)
-
-## Determine threshold of Otsu's binarization
-max_sigma = 0
-max_t = 0
-
-for _t in range(1, 255):
-    v0 = out[np.where(out < _t)]
-    m0 = np.mean(v0) if len(v0) > 0 else 0.
-    w0 = len(v0) / (H * W)
-    v1 = out[np.where(out >= _t)]
-    m1 = np.mean(v1) if len(v1) > 0 else 0.
-    w1 = len(v1) / (H * W)
-    sigma = w0 * w1 * ((m0 - m1) ** 2)
-    if sigma > max_sigma:
-        max_sigma = sigma
-        max_t = _t
-
-## Binarization
-#print("threshold >>", max_t)
-th = max_t
-out[out < th] = 0
-out[out >= th] = 255
-
-# Morphology filter
-MF = np.array(((0, 1, 0),
-               (1, 0, 1),
-               (0, 1, 0)), dtype=np.int)
-
-# Morphology - erode
-Erode_time = 3
-mor = out.copy()
-
-for i in range(Erode_time):
-    tmp = np.pad(mor, (1, 1), 'edge')
-    for y in range(1, H+1):
-        for x in range(1, W+1):
-            if np.sum(MF * tmp[y-1:y+2, x-1:x+2]) < 255*4:
-                mor[y-1, x-1] = 0
-
-# Morphology - dilate
-Dil_time = 3
-
-for i in range(Dil_time):
-    tmp = np.pad(mor, (1, 1), 'edge')
-    for y in range(1, H+1):
-        for x in range(1, W+1):
-            if np.sum(MF * tmp[y-1:y+2, x-1:x+2]) >= 255:
-                mor[y-1, x-1] = 255
-
-out = out - mor
+
+# Grayscale
+gray = BGR2GRAY(img)
+
+# Otsu's binarization
+otsu = otsu_binarization(gray)
+
+# Opening process
+opened = Morphology_Opening(otsu, time=3)
+
+# Tophat
+out = np.abs(otsu - opened) * 255
 
 # Save result
 cv2.imwrite("out.jpg", out)