def similarity(prefix, img1, img2, arr, mode, lock):
img1_path = 'subset\subset_images\\' + img1 + '.jpg'
img2_path = 'subset\subset_images\\' + img2 + '.jpg'
if mode == 'ssim':
gaussian_kernel_sigma = 1.5
gaussian_kernel_width = 11
gaussian_kernel_1d = get_gaussian_kernel(gaussian_kernel_width, gaussian_kernel_sigma)
size = None
ssim = pyssim.SSIM(img1_path, gaussian_kernel_1d, size=size)
sim = ssim.ssim_value(img2_path)
else:
sim = pyssim.SSIM(img1_path).cw_ssim_value(img2_path)
with lock:
arr.append([img1, img2, sim])
def get_image_similarity(img1, img2, algorithm='SIFT'):
""" Returns the normalized similarity value (from 0.0 to 1.0) for
the provided pair of images.
The following algorithms are supported:
* SIFT: Scale-invariant Feature Transform
* SSIM: Structural Similarity Index
* CW-SSIM: Complex Wavelet Structural Similarity Index
* MSE: Mean Squared Error
"""
# Converting to grayscale and resizing
i1 = cv2.resize(cv2.imread(img1, cv2.IMREAD_GRAYSCALE), SIM_IMAGE_SIZE)
i2 = cv2.resize(cv2.imread(img2, cv2.IMREAD_GRAYSCALE), SIM_IMAGE_SIZE)
similarity = 0.0
if algorithm == 'SIFT':
# Using OpenCV for feature detection and matching
sift = cv2.xfeatures2d.SIFT_create()
k1, d1 = sift.detectAndCompute(i1, None)
k2, d2 = sift.detectAndCompute(i2, None)
bf = cv2.BFMatcher()
matches = bf.knnMatch(d1, d2, k=2)
for m, n in matches:
if m.distance < SIFT_RATIO * n.distance:
similarity += 1.0
# Custom normalization for better variance in the similarity matrix
if similarity == len(matches):
similarity = 1.0
elif similarity > 1.0:
similarity = 1.0 - 1.0 / similarity
elif similarity == 1.0:
similarity = 0.1
else:
similarity = 0.0
elif algorithm == 'CW-SSIM':
# FOR EXPERIMENTS ONLY!
# Very slow algorithm - up to 50x times slower than SIFT or SSIM.
similarity = pyssim.SSIM(img1).cw_ssim_value(img2)
elif algorithm == 'SSIM':
# Default SSIM implementation of Scikit-Image
similarity = ssim(i1, i2)
else:
# Using MSE algorithm with custom normalization
err = np.sum((i1.astype("float") - i2.astype("float"))**2)
err /= float(i1.shape[0] * i2.shape[1])
if err > 0.0:
similarity = MSE_NUMERATOR / err
else:
similarity = 1.0
return similarity
def get_image_similarity(img1, img2, algorithm='SIFT'):
# Converting to grayscale and resizing
i1 = cv2.resize(cv2.imread(img1, cv2.IMREAD_GRAYSCALE), SIM_IMAGE_SIZE)
i2 = cv2.resize(cv2.imread(img2, cv2.IMREAD_GRAYSCALE), SIM_IMAGE_SIZE)
similarity = 0.0
if algorithm == 'SIFT':
# Using OpenCV for feature detection and matching
sift = cv2.xfeatures2d.SIFT_create()
k1, d1 = sift.detectAndCompute(i1, None)
k2, d2 = sift.detectAndCompute(i2, None)
bf = cv2.BFMatcher()
matches = bf.knnMatch(d1, d2, k=2)
for m, n in matches:
if m.distance < SIFT_RATIO * n.distance:
similarity += 1.0
# Custom normalization for better variance in the similarity matrix
if similarity == len(matches):
similarity = 1.0
elif similarity > 1.0:
similarity = 1.0 - 1.0/similarity
elif similarity == 1.0:
similarity = 0.1
else:
similarity = 0.0
elif algorithm == 'CW-SSIM':
# FOR EXPERIMENTS ONLY!
# Very slow algorithm - up to 50x times slower than SIFT or SSIM.
# Optimization using CUDA or Cython code should be explored in the future.
similarity = pyssim.SSIM(img1).cw_ssim_value(img2)
elif algorithm == 'SSIM':
# Default SSIM implementation of Scikit-Image
similarity = ssim(i1, i2)
else:
# Using MSE algorithm with custom normalization
err = np.sum((i1.astype("float") - i2.astype("float")) ** 2)
err /= float(i1.shape[0] * i2.shape[1])
if err > 0.0:
similarity = MSE_NUMERATOR / err
else:
similarity = 1.0
return similarity
img_recor1 = cv2.idct(recor_temp)
return img_recor1
#dim = 30
similarity_1 = []
MSE = []
for i in range(val_data.shape[0]):
image1 = val_data_noise[i].reshape(50, 60, 1)[:, :, 0]
image2 = val_data[i].reshape(50, 60, 1)[:, :, 0]
image1 = image1.astype('float')
image2 = image2.astype('float')
p1 = Image.fromarray(image2).convert('L')
p2 = Image.fromarray(DCT(image1, dim = 30)).convert('L')
similarity_temp_1 = pyssim.SSIM(p1).cw_ssim_value(p2)
similarity_1.append([similarity_temp_1])
mse_ = mean_squared_error(image1, DCT(image1, dim = 30))
MSE.append(mse_)
print('cw-ssim: %s'%np.mean(similarity_1))
print('MSE: %s'%np.mean(MSE))
#dim = 60
for i in range(val_data.shape[0]):
image1 = val_data_noise[i].reshape(50, 60, 1)[:, :, 0]
image2 = val_data[i].reshape(50, 60, 1)[:, :, 0]
image1 = image1.astype('float')
image2 = image2.astype('float')
import ssim.ssimlib as pyssim img1 = 'images/breast_img1.png' img2 = 'images/breast_img3.png' cw_ssim_value = pyssim.SSIM(img1).cw_ssim_value(img2) print(cw_ssim_value)