python删除相似度高的图片

1.参考博客:
python—–删除同一文件夹下相似的图片
Python-列表删除重复元素/图像相似度判断及删除相似图像
python 图像相似 phash和compare_ssim比较
利用Python轻松实现图片相似度对比(一)
利用Python轻松实现图片相似度对比(二)
因为输入是视频,切完帧之后都是连续图片,所以主要参考*篇博客的*种方法。我的目录结构如下:

%title插图%num

其中frame_output是视频切帧后的保存路径,1和2文件夹分别对应两个是视频切帧后的图片。

2.切帧的代码如下:
#encoding:utf-8
import os
import sys
import cv2

video_path = ‘/home/pythonfile/video/’ # *对路径,video下有两段视频
out_frame_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), ‘frame_output’) #frame_output是视频切帧后的保存路径
if not os.path.exists(out_frame_path):
os.makedirs(out_frame_path)
print(‘out_frame_path’, out_frame_path)
files = []
list1 = os.listdir(video_path)
print(‘list’, list1)
for i in range(len(list1)):
item = os.path.join(video_path, list1[i])
files.append(item)
print(‘files’,files)
for k,file in enumerate(files):
frame_dir = os.path.join(out_frame_path, ‘%d’%(k+1))
if not os.path.exists(frame_dir):
os.makedirs(frame_dir)
cap = cv2.VideoCapture(file)
j = 0
print(‘start prossing NO.%d video’ % (k + 1))
while True:
ret, frame = cap.read()
j += 1
if ret:
#每三帧保存一张
if j % 3 == 0:
cv2.imwrite(os.path.join(frame_dir, ‘%d.jpg’%j), frame)
else:
cap.release()
break
print(‘prossed NO.%d video’%(k+1))

3.删除相似度高的图片
根据我的文件结构参考*篇博客的*种方法修改后的代码如下:

# coding: utf-8
import os
import cv2
# from skimage.measure import compare_ssim
# from skimage.metrics import _structural_similarity
from skimage.metrics import structural_similarity as ssim

def delete(filename1):
os.remove(filename1)

def list_all_files(root):
files = []
list = os.listdir(root)
# os.listdir()方法:返回指定文件夹包含的文件或子文件夹名字的列表。该列表顺序以字母排序
for i in range(len(list)):
element = os.path.join(root, list[i])
# 需要先使用python路径拼接os.path.join()函数,将os.listdir()返回的名称拼接成文件或目录的*对路径再传入os.path.isdir()和os.path.isfile().
if os.path.isdir(element): # os.path.isdir()用于判断某一对象(需提供*对路径)是否为目录
# temp_dir = os.path.split(element)[-1]
# os.path.split分割文件名与路径,分割为data_dir和此路径下的文件名,[-1]表示只取data_dir下的文件名
files.append(list_all_files(element))

elif os.path.isfile(element):
files.append(element)
# print(‘2’,files)
return files

def ssim_compare(img_files):
count = 0
for currIndex, filename in enumerate(img_files):
if not os.path.exists(img_files[currIndex]):
print(‘not exist’, img_files[currIndex])
break
img = cv2.imread(img_files[currIndex])
img1 = cv2.imread(img_files[currIndex + 1])
#进行结构性相似度判断
# ssim_value = _structural_similarity.structural_similarity(img,img1,multichannel=True)
ssim_value = ssim(img,img1,multichannel=True)
if ssim_value > 0.9:
#基数
count += 1
imgs_n.append(img_files[currIndex + 1])
print(‘big_ssim:’,img_files[currIndex], img_files[currIndex + 1], ssim_value)
# 避免数组越界
if currIndex+1 >= len(img_files)-1:
break
return count

if __name__ == ‘__main__’:
path = ‘/home/dj/pythonfile/frame_output/’

img_path = path
imgs_n = []

all_files = list_all_files(path) #返回包含完整路径的所有图片名的列表
print(‘1’,len(all_files))

for files in all_files:
# 根据文件名排序,x.rfind(‘/’)是从右边寻找*个‘/’出现的位置,也就是*后出现的位置
# 注意sort和sorted的区别,sort作用于原列表,sorted生成新的列表,且sorted可以作用于所有可迭代对象
files.sort(key = lambda x: int(x[x.rfind(‘/’)+1:-4]))#路径中包含“/”
# print(files)
img_files = []
for img in files:
if img.endswith(‘.jpg’):
# 将所有图片名都放入列表中
img_files.append(img)
count = ssim_compare(img_files)
print(img[:img.rfind(‘/’)],”路径下删除的图片数量为:”,count)
for image in imgs_n:
delete(image)

4.关于导入skimage.measure import compare_ssim出错的解决方法:
from skimage.measure import compare_ssim as sk_cpt_ssim error,从skimage导入compare_ssim出错。

from skimage.measure import compare_ssim
1
改为

from skimage.metrics import _structural_similarity
1
参考官网:https://scikit-image.org/docs/stable/auto_examples/transform/plot_ssim.html#sphx-glr-auto-examples-transform-plot-ssim-py

SSIM(structural similarity)算法原理

5.查看python安装路径及依赖包路径
ubuntu查看python及安装包的位置

6.*后贴上_structural_similarity.py的源码,以后学习
from warnings import warn
import numpy as np
from scipy.ndimage import uniform_filter, gaussian_filter

from ..util.dtype import dtype_range
from ..util.arraycrop import crop
from .._shared.utils import warn, check_shape_equality

__all__ = [‘structural_similarity’]

def structural_similarity(im1, im2,
*,
win_size=None, gradient=False, data_range=None,
multichannel=False, gaussian_weights=False,
full=False, **kwargs):
“””
Compute the mean structural similarity index between two images.

Parameters
———-
im1, im2 : ndarray
Images. Any dimensionality with same shape.
win_size : int or None, optional
The side-length of the sliding window used in comparison. Must be an
odd value. If `gaussian_weights` is True, this is ignored and the
window size will depend on `sigma`.
gradient : bool, optional
If True, also return the gradient with respect to im2.
data_range : float, optional
The data range of the input image (distance between minimum and
maximum possible values). By default, this is estimated from the image
data-type.
multichannel : bool, optional
If True, treat the last dimension of the array as channels. Similarity
calculations are done independently for each channel then averaged.
gaussian_weights : bool, optional
If True, each patch has its mean and variance spatially weighted by a
normalized Gaussian kernel of width sigma=1.5.
full : bool, optional
If True, also return the full structural similarity image.

Other Parameters
—————-
use_sample_covariance : bool
If True, normalize covariances by N-1 rather than, N where N is the
number of pixels within the sliding window.
K1 : float
Algorithm parameter, K1 (small constant, see [1]_).
K2 : float
Algorithm parameter, K2 (small constant, see [1]_).
sigma : float
Standard deviation for the Gaussian when `gaussian_weights` is True.

Returns
——-
mssim : float
The mean structural similarity index over the image.
grad : ndarray
The gradient of the structural similarity between im1 and im2 [2]_.
This is only returned if `gradient` is set to True.
S : ndarray
The full SSIM image. This is only returned if `full` is set to True.

Notes
—–
To match the implementation of Wang et. al. [1]_, set `gaussian_weights`
to True, `sigma` to 1.5, and `use_sample_covariance` to False.

.. versionchanged:: 0.16
This function was renamed from “skimage.measure.compare_ssim“ to
“skimage.metrics.structural_similarity“.

References
———-
.. [1] Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P.
(2004). Image quality assessment: From error visibility to
structural similarity. IEEE Transactions on Image Processing,
13, 600-612.
https://ece.uwaterloo.ca/~z70wang/publications/ssim.pdf,
:DOI:`10.1109/TIP.2003.819861`

.. [2] Avanaki, A. N. (2009). Exact global histogram specification
optimized for structural similarity. Optical Review, 16, 613-621.
:arxiv:`0901.0065`
:DOI:`10.1007/s10043-009-0119-z`

“””
check_shape_equality(im1, im2)

if multichannel:
# loop over channels
args = dict(win_size=win_size,
gradient=gradient,
data_range=data_range,
multichannel=False,
gaussian_weights=gaussian_weights,
full=full)
args.update(kwargs)
nch = im1.shape[-1]
mssim = np.empty(nch)
if gradient:
G = np.empty(im1.shape)
if full:
S = np.empty(im1.shape)
for ch in range(nch):
ch_result = structural_similarity(im1[…, ch],
im2[…, ch], **args)
if gradient and full:
mssim[…, ch], G[…, ch], S[…, ch] = ch_result
elif gradient:
mssim[…, ch], G[…, ch] = ch_result
elif full:
mssim[…, ch], S[…, ch] = ch_result
else:
mssim[…, ch] = ch_result
mssim = mssim.mean()
if gradient and full:
return mssim, G, S
elif gradient:
return mssim, G
elif full:
return mssim, S
else:
return mssim

K1 = kwargs.pop(‘K1’, 0.01)
K2 = kwargs.pop(‘K2’, 0.03)
sigma = kwargs.pop(‘sigma’, 1.5)
if K1 < 0:
raise ValueError(“K1 must be positive”)
if K2 < 0:
raise ValueError(“K2 must be positive”)
if sigma < 0:
raise ValueError(“sigma must be positive”)
use_sample_covariance = kwargs.pop(‘use_sample_covariance’, True)

if gaussian_weights:
# Set to give an 11-tap filter with the default sigma of 1.5 to match
# Wang et. al. 2004.
truncate = 3.5

if win_size is None:
if gaussian_weights:
# set win_size used by crop to match the filter size
r = int(truncate * sigma + 0.5) # radius as in ndimage
win_size = 2 * r + 1
else:
win_size = 7 # backwards compatibility

if np.any((np.asarray(im1.shape) – win_size) < 0):
raise ValueError(
“win_size exceeds image extent. If the input is a multichannel ”
“(color) image, set multichannel=True.”)

if not (win_size % 2 == 1):
raise ValueError(‘Window size must be odd.’)

if data_range is None:
if im1.dtype != im2.dtype:
warn(“Inputs have mismatched dtype. Setting data_range based on ”
“im1.dtype.”, stacklevel=2)
dmin, dmax = dtype_range[im1.dtype.type]
data_range = dmax – dmin

ndim = im1.ndim

if gaussian_weights:
filter_func = gaussian_filter
filter_args = {‘sigma’: sigma, ‘truncate’: truncate}
else:
filter_func = uniform_filter
filter_args = {‘size’: win_size}

# ndimage filters need floating point data
im1 = im1.astype(np.float64)
im2 = im2.astype(np.float64)

NP = win_size ** ndim

# filter has already normalized by NP
if use_sample_covariance:
cov_norm = NP / (NP – 1) # sample covariance
else:
cov_norm = 1.0 # population covariance to match Wang et. al. 2004

# compute (weighted) means
ux = filter_func(im1, **filter_args)
uy = filter_func(im2, **filter_args)

# compute (weighted) variances and covariances
uxx = filter_func(im1 * im1, **filter_args)
uyy = filter_func(im2 * im2, **filter_args)
uxy = filter_func(im1 * im2, **filter_args)
vx = cov_norm * (uxx – ux * ux)
vy = cov_norm * (uyy – uy * uy)
vxy = cov_norm * (uxy – ux * uy)

R = data_range
C1 = (K1 * R) ** 2
C2 = (K2 * R) ** 2

A1, A2, B1, B2 = ((2 * ux * uy + C1,
2 * vxy + C2,
ux ** 2 + uy ** 2 + C1,
vx + vy + C2))
D = B1 * B2
S = (A1 * A2) / D

# to avoid edge effects will ignore filter radius strip around edges
pad = (win_size – 1) // 2

# compute (weighted) mean of ssim
mssim = crop(S, pad).mean()

if gradient:
# The following is Eqs. 7-8 of Avanaki 2009.
grad = filter_func(A1 / D, **filter_args) * im1
grad += filter_func(-S / B2, **filter_args) * im2
grad += filter_func((ux * (A2 – A1) – uy * (B2 – B1) * S) / D,
**filter_args)
grad *= (2 / im1.size)

if full:
return mssim, grad, S
else:
return mssim, grad
else:
if full:
return mssim, S
else:
return mssim