def start_kmeans(args):
imlist = imtools.get_imlist(args.data_dir)
imnbr = len(imlist) # get the number of images
print("The number of images is %d" % imnbr)
# Create matrix to store all flattened images
immatrix = np.array([np.array(cv2.imread(imname)).flatten() for imname in imlist], 'f')
# PCA reduce dimension
V, S, immean = pca.pca(immatrix)
immatrix = np.array([np.array(cv2.imread(im)).flatten() for im in imlist])
immatrix_src = np.array([np.array(cv2.imread(im)) for im in imlist])
# project on the 40 first PCs
immean = immean.flatten()
projected = np.array([dot(V[:40], immatrix[i] - immean) for i in range(imnbr)])
# k-means
projected = whiten(projected)
centroids, distortion = kmeans(projected, args.num_class)
code, distance = vq(projected, centroids)
output_path = os.path.join(args.output_dir, 'kmeans_result')
if not os.path.exists(output_path):
os.mkdir(output_path)
# plot clusters
for k in range(args.num_class):
ind = where(code == k)[0]
print("class:", k, len(ind))
os.mkdir(os.path.join(output_path, str(k)))
i = rdm.randint(0,len(ind))
cv2.imwrite(os.path.join(os.path.join(output_path, str(k)), str(i) + '.jpg'), immatrix_src[ind[i]])
# -*- coding: utf-8 -*-
from PCV.tools import imtools
import pickle
from scipy import *
import os
from pylab import *
from PIL import Image
from scipy.cluster.vq import *
from PCV.tools import pca
# Uses sparse pca codepath.
imlist = imtools.get_imlist('data1/selectedfontimages/a_selected_thumbs/')
# 获取图像列表和他们的尺寸
im = array(Image.open(imlist[0])) # open one image to get the size
m, n = im.shape[:2] # get the size of the images
imnbr = len(imlist) # get the number of images
print "The number of images is %d" % imnbr
# Create matrix to store all flattened images
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist],
'f')
# PCA降维
V, S, immean = pca.pca(immatrix)
# 保存均值和主成分
#f = open('./a_pca_modes.pkl', 'wb')
f = open('./a_pca_modes.pkl', 'wb')
pickle.dump(immean, f)
pickle.dump(V, f)
import pickle
from PCV.imagesearch import imagesearch
from PCV.localdescriptors import sift
from sqlite3 import dbapi2 as sqlite
from PCV.tools.imtools import get_imlist
imlist = get_imlist('./first500/')
nbr_images = len(imlist)
featlist = [imlist[i][:-3]+'sift' for i in range(nbr_images)]
f = open('./first500/vocabulary.pkl', 'rb')
voc = pickle.load(f)
f.close()
src = imagesearch.Searcher('web.db',voc)
locs,descr = sift.read_features_from_file(featlist[0])
iw = voc.project(descr)
print 'ask using a histogram...'
print src.candidates_from_histogram(iw)[:10]
src = imagesearch.Searcher('web.db',voc)
print 'try a query...'
nbr_results = 12
res = [w[1] for w in src.query(imlist[39])[:nbr_results]]
imagesearch.plot_results(src,res)
# -*- coding: utf-8 -*-
import pickle
from PCV.imagesearch import imagesearch
from PCV.localdescriptors import sift
from sqlite3 import dbapi2 as sqlite
from PCV.tools.imtools import get_imlist
#获取图像列表
imlist = get_imlist('first1000/')
nbr_images = len(imlist)
#获取特征列表
featlist = [imlist[i][:-3] + 'sift' for i in range(nbr_images)]
# load vocabulary
#载入词汇
with open('first1000/vocabulary.pkl', 'rb') as f:
voc = pickle.load(f)
#创建索引
indx = imagesearch.Indexer('testImaAdd.db', voc)
indx.create_tables()
# go through all images, project features on vocabulary and insert
#遍历所有的图像，并将它们的特征投影到词汇上
for i in range(nbr_images)[:1000]:
locs, descr = sift.read_features_from_file(featlist[i])
indx.add_to_index(imlist[i], descr)
# commit to database
#提交到数据库
indx.db_commit()
con = sqlite.connect('testImaAdd.db')
print(con.execute('select count (filename) from imlist').fetchone())
from PCV.tools.imtools import get_imlist #导入原书的PCV模块
from PIL import Image
import os
import pickle
filelist = get_imlist('E:/python/Python Computer Vision/test jpg/') #获取convert_images_format_test文件夹下的图片文件名(包括后缀名)
imlist = open('E:/python/Python Computer Vision/test jpg/imlist.txt','wb+')
#将获取的图片文件列表保存到imlist.txt中
pickle.dump(filelist,imlist) #序列化
imlist.close()
for infile in filelist:
outfile = os.path.splitext(infile)[0] + ".png" #分离文件名与扩展名
if infile != outfile:
try:
Image.open(infile).save(outfile)
except IOError:
print ("cannot convert", infile)
from PIL import Image
from pylab import *
from numpy import *
from PCV.tools import imtools, pca
# Get list of images and their size
imlist = imtools.get_imlist(
'fontimages/') # fontimages.zip is part of the book data set
im = array(Image.open(imlist[0])) # open one image to get the size
m, n = im.shape[:2]
# Create matrix to store all flattened images
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist],
'f')
# Perform PCA
V, S, immean = pca.pca(immatrix)
# Show the images (mean and 7 first modes)
# This gives figure 1-8 (p15) in the book.
figure()
gray()
subplot(2, 4, 1)
imshow(immean.reshape(m, n))
for i in range(7):
subplot(2, 4, i + 2)
imshow(V[i].reshape(m, n))
show()
# -*- coding: utf-8 -*-
import pickle
from PIL import Image
from numpy import *
from pylab import *
from PCV.tools import imtools, pca
# Uses sparse pca codepath.
# imlist = imtools.get_imlist('../data/selectedfontimages/a_selected_thumbs')
# 获取图像列表和他们的尺寸
imlist = imtools.get_imlist('../data/fontimages/a_thumbs') # fontimages.zip is part of the book data set
im = array(Image.open(imlist[0])) # open one image to get the size
m, n = im.shape[:2] # get the size of the images
imnbr = len(imlist) # get the number of images
print("The number of images is %d" % imnbr)
# Create matrix to store all flattened images
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist], 'f')
# PCA降维
V, S, immean = pca.pca(immatrix)
# 保存均值和主成分
f = open('../data/fontimages/font_pca_modes.pkl', 'wb')
pickle.dump(immean, f)
pickle.dump(V, f)
f.close()
# Show the images (mean and 7 first modes)
# This gives figure 1-8 (p15) in the book.
# -*- coding: utf-8 -*-
import pickle
from PCV.imagesearch import imagesearch
from PCV.localdescriptors import sift
from sqlite3 import dbapi2 as sqlite
from PCV.tools.imtools import get_imlist
# 获取图像列表
imlist = get_imlist('./first500/')
nbr_images = len(imlist)
# 获取特征列表
featlist = [imlist[i][:-3] + 'sift' for i in range(nbr_images)]
# 载入词汇
f = open('./first500/vocabulary.pkl', 'rb')
voc = pickle.load(f)
f.close()
src = imagesearch.Searcher('testImaAdd.db', voc)
locs, descr = sift.read_features_from_file(featlist[0])
iw = voc.project(descr)
print('ask using a histogram...')
print(src.candidates_from_histogram(iw)[:10])
src = imagesearch.Searcher('testImaAdd.db', voc)
print('try a query...')
nbr_results = 12
res = [w[1] for w in src.query(imlist[0])[:nbr_results]]
imagesearch.plot_results(src, res)
from PCV.tools import imtools, pca
from PIL import Image, ImageDraw
from pylab import *
from PCV.clustering import hcluster
imlist = imtools.get_imlist('../data/selectedfontimages/a_selected_thumbs')
imnbr = len(imlist)
# Load images, run PCA.
immatrix = array([array(Image.open(im)).flatten() for im in imlist], 'f')
V, S, immean = pca.pca(immatrix)
# Project on 2 PCs.
projected = array([dot(V[[0, 1]], immatrix[i] - immean)
for i in range(imnbr)]) # P131 Fig6-3左图
#projected = array([dot(V[[1, 2]], immatrix[i] - immean) for i in range(imnbr)]) # P131 Fig6-3右图
# height and width
h, w = 1200, 1200
# create a new image with a white background
img = Image.new('RGB', (w, h), (255, 255, 255))
draw = ImageDraw.Draw(img)
# draw axis
draw.line((0, h / 2, w, h / 2), fill=(255, 0, 0))
draw.line((w / 2, 0, w / 2, h), fill=(255, 0, 0))
# scale coordinates to fit
scale = abs(projected).max(0)
scaled = floor(
from PCV.tools import imtools
import pickle
from scipy.cluster.vq import *
from PIL import Image
from PCV.tools import pca
from pylab import *
imlist = imtools.get_imlist('../data/fontimages/a_thumbs/')
im = array(Image.open(imlist[0]))
n, m = im.shape[:2]
imlist = imlist[:200]
imnbr = len(imlist)
immatrix = np.array([np.array(Image.open(im)).flatten() for im in imlist], 'f')
V, S, immean = pca.pca(immatrix)
figure()
gray()
subplot(2, 4, 1)
imshow(immean.reshape(m, n))
for i in range(7):
subplot(2, 4, i + 2)
imshow(V[i].reshape(m, n))
show()
immean = immean.flatten()
projected = array([dot(V[:40], immatrix[i] - immean) for i in range(imnbr)])
projected = whiten(projected)
# -*- coding: utf-8 -*-
from PCV.tools import imtools, pca
from PIL import Image, ImageDraw
from pylab import *
from scipy.cluster.vq import *
imlist = imtools.get_imlist('data/line/watercolor/')
imnbr = len(imlist)
# Load images, run PCA.
immatrix = array([array(Image.open(im)).flatten() for im in imlist], 'f')
V, S, immean = pca.pca(immatrix)
# Project on 2 PCs.
projected = array([dot(V[[0, 1]], immatrix[i] - immean)
for i in range(imnbr)]) # P131 Fig6-3左图
#projected = array([dot(V[[1, 2]], immatrix[i] - immean) for i in range(imnbr)]) # P131 Fig6-3右图
n = len(projected)
# compute distance matrix
S = array([[sqrt(sum((projected[i] - projected[j])**2)) for i in range(n)]
for j in range(n)], 'f')
# create Laplacian matrix
rowsum = sum(S, axis=0)
D = diag(1 / sqrt(rowsum))
I = identity(n)
L = I - dot(D, dot(S, D))
# compute eigenvectors of L
U, sigma, V = linalg.svd(L)
k = 5
# create feature vector from k first eigenvectors
#
## Create matrix to store all flattened images
#immatrix = array([array(Image.open(imname)).flatten() for imname in imlist], 'f')
#
## PCA降维
#V, S, immean = pca.pca(immatrix)
#
## 保存均值和主成分
##f = open('./a_pca_modes.pkl', 'wb')
#f = open('./a_pca_modes.pkl', 'wb')
#pickle.dump(immean,f)
#pickle.dump(V,f)
#f.close()
# get list of images
imlist = imtools.get_imlist('F:/python/pic/201710162100/')
imnbr = len(imlist)
# load model file
with open('../data/selectedfontimages/a_pca_modes.pkl', 'rb') as f:
immean = pickle.load(f)
V = pickle.load(f)
# create matrix to store all flattened images
immatrix = array([array(Image.open(im)).flatten() for im in imlist], 'f')
# project on the 40 first PCs
immean = immean.flatten()
projected = array([dot(V[:40], immatrix[i] - immean) for i in range(imnbr)])
# k-means
projected = whiten(projected)
接下来是将前面的预处理更改为同名，即不重命名操作，为此，在demo3_my_6077_test.py文件的基础上，新建spectral_clustering.py文件。
并对灰度化和压缩图像的代码文件进行重写，灰度化对应的代码文件是grayscale_processing.py，压缩图像的代码文件是picture_resize_2.py，
将这两个代码文件处理的时候不对图像进行重命名。
"""
# -*- coding: utf-8 -*-
from PCV.tools import imtools, pca
from PIL import Image, ImageDraw
from pylab import *
from scipy.cluster.vq import *
import os
import random
# imlist = imtools.get_imlist('./dir_my')
imlist = imtools.get_imlist('./dir_my_gray_rescale')
imnbr = len(imlist)
# Load images, run PCA.
immatrix = array([array(Image.open(im)).flatten() for im in imlist], 'f')
V, S, immean = pca.pca(immatrix)
# Project on 2 PCs.
projected = array([dot(V[[0, 1]], immatrix[i] - immean)
for i in range(imnbr)]) # P131 Fig6-3左图
#projected = array([dot(V[[1, 2]], immatrix[i] - immean) for i in range(imnbr)]) # P131 Fig6-3右图
n = len(projected)
# compute distance matrix
S = array([[sqrt(sum((projected[i] - projected[j])**2)) for i in range(n)]
for j in range(n)], 'f')
# -*- coding: utf-8 -*-
import pickle
from PIL import Image
from numpy import *
from pylab import *
from PCV.tools import imtools, pca
# Uses sparse pca codepath.
#imlist = imtools.get_imlist('../data/selectedfontimages/a_selected_thumbs')
# 获取图像列表和他们的尺寸
imlist = imtools.get_imlist('../data/fontimages/a_thumbs') # fontimages.zip is part of the book data set
im = array(Image.open(imlist[0])) # open one image to get the size
m, n = im.shape[:2] # get the size of the images
imnbr = len(imlist) # get the number of images
print "The number of images is %d" % imnbr
# Create matrix to store all flattened images
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist], 'f')
# PCA降维
V, S, immean = pca.pca(immatrix)
# 保存均值和主成分
f = open('../data/fontimages/font_pca_modes.pkl', 'wb')
pickle.dump(immean,f)
pickle.dump(V,f)
f.close()
# Show the images (mean and 7 first modes)
# This gives figure 1-8 (p15) in the book.
# -*- coding: utf-8 -*-
from PCV.tools import imtools, pca
from PIL import Image, ImageDraw
from pylab import *
imlist = imtools.get_imlist('../data/selectedfontimages/a_selected_thumbs')
imnbr = len(imlist)
# Load images, run PCA.
immatrix = array([array(Image.open(im)).flatten() for im in imlist], 'f')
V, S, immean = pca.pca(immatrix)
# Project on 2 PCs.
projected = array([dot(V[[0, 1]], immatrix[i] - immean) for i in range(imnbr)]) # P131 Fig6-3左图
#projected = array([dot(V[[1, 2]], immatrix[i] - immean) for i in range(imnbr)]) # P131 Fig6-3右图
# height and width
h, w = 1200, 1200
# create a new image with a white background
img = Image.new('RGB', (w, h), (255, 255, 255))
draw = ImageDraw.Draw(img)
# draw axis
draw.line((0, h/2, w, h/2), fill=(255, 0, 0))
draw.line((w/2, 0, w/2, h), fill=(255, 0, 0))
# scale coordinates to fit
scale = abs(projected).max(0)
scaled = floor(array([(p/scale) * (w/2 - 20, h/2 - 20) + (w/2, h/2)
for p in projected])).astype(int)
# -*- coding: utf-8 -*-
from PCV.tools.imtools import get_imlist
from PIL import Image
import os
import pickle
filelist = get_imlist('../data/convert_images_format_test/'
) # 获取convert_images_format_test文件夹下的图片文件名(包括后缀名)
imlist = open('../data/convert_images_format_test/imlist.txt',
'wb') # 将获取的图片文件列表保存到imlist.txt中
pickle.dump(filelist, imlist) # 序列化
imlist.close()
for infile in filelist:
outfile = os.path.splitext(infile)[0] + ".png" # 分离文件名与扩展名
if infile != outfile:
try:
Image.open(infile).save(outfile)
except IOError:
print("cannot convert", infile)
imlist1 = open('../data/convert_images_format_test/imlist.txt',
'rb') # 将获取的图片文件列表保存到imlist.txt中
ss = pickle.load(imlist1)
print(ss)
from PCV.tools import imtools
import pickle
from scipy import *
from pylab import *
from PIL import Image
from scipy.cluster.vq import *
from PCV.tools import pca
imlist = imtools.get_imlist(
'/home/constantine/PycharmProjects/tf_playground/clustering/data/a_selected_thumbs/'
)
im = array(Image.open(imlist[0])) # open one image to get the size
m, n = im.shape[:2] # get the size of the images
imnbr = len(imlist) # get the number of images
print("The number of images is %d" % imnbr)
# Create matrix to store all flattened images
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist],
'f')
# PCA降维
V, S, immean = pca.pca(immatrix)
import pickle
from PIL import Image
from numpy import *
from pylab import *
from PCV.tools import imtools,pca
# Uses sparse pca codepath
# 获取图像列表和尺寸
imlist=imtools.get_imlist('E:/python/Python Computer Vision/Image data/fontimages/a_thumbs')
# open ont image to get the size
im=array(Image.open(imlist[0]))
# get the size of the images
m,n=im.shape[:2]
# get the number of images
imnbr=len(imlist)
print("The number of images is %d" % imnbr)
# create matrix to store all flattened images
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist],'f')
# PCA降维
V,S,immean=pca.pca(immatrix)
# 保存均值和主成分
#f = open('../ch01/font_pca_modes.pkl', 'wb')
#pickle.dump(immean,f)
#pickle.dump(V,f)
#f.close()
# Show the images (mean and 7 first modes)
# -*- coding: utf-8 -*-
from PCV.tools.imtools import get_imlist
from PIL import Image
import os
import pickle
filelist = get_imlist('../data/convert_images_format_test/') #获取convert_images_format_test文件夹下的图片文件名(包括后缀名)
imlist = file('../data/convert_images_format_test/imlist.txt','w') #将获取的图片文件列表保存到imlist.txt中
pickle.dump(filelist,imlist) #序列化
imlist.close()
for infile in filelist:
outfile = os.path.splitext(infile)[0] + ".png" #分离文件名与扩展名
if infile != outfile:
try:
Image.open(infile).save(outfile)
except IOError:
print "cannot convert", infile
from PCV.tools import imtools
import numpy as np
import pickle
from scipy import *
from pylab import *
from PIL import Image
from scipy.cluster.vq import *
from PCV.tools import pca
img_dir = r'E:\DataSet\fiber\cluster_roi'
N = 15
# Uses sparse pca codepath.
imlist = imtools.get_imlist(img_dir)
# 获取图像列表和他们的尺寸
im = array(Image.open(imlist[0])) # open one image to get the size
m, n = im.shape[:2] # get the size of the images
imnbr = len(imlist) # get the number of images
print("The number of images is %d" % imnbr)
# Create matrix to store all flattened images
# ValueError: setting an array element with a sequence.
# immatrix = array([array(Image.open(imname)).flatten() for imname in imlist], 'f')
immatrix = np.array([
array(Image.open(imname).resize((50, 50)).convert('L')).flatten()
for imname in imlist
])
Modify Date: 2018-07-02 descirption: "some utils" ''' import pickle import numpy as np from PCV.tools import imtools, pca from PIL import Image from pylab import * from scipy import * from scipy.cluster.vq import * temp_image_path = "G:\python\pcv_data\data\selectedfontimages\\a_selected_thumbs" imlist = imtools.get_imlist(temp_image_path) print imlist[0] # 获取图像列表和他们的尺寸 im = np.array(Image.open(imlist[0])) print type(im) m, n = im.shape[:2] imnbr = len(imlist) print "The number of images is %d" % imnbr immatrix = np.array([np.array(Image.open(imname)).flatten() for imname in imlist[:10]], 'f') print immatrix.shape V, S, immean = pca.pca(immatrix) print V[0][:10]
from PCV.tools.imtools import get_imlist
from PIL import Image
from pylab import *
from PCV.tools import imtools
# 添加中文字体支持
from matplotlib.font_manager import FontProperties
font = FontProperties(fname=r"c:\windows\fonts\SimSun.ttc", size=14)
filelist = get_imlist('E:/python/Python Computer Vision/test average/')
#获取convert_images_format_test文件夹下的图片文件名(包括后缀名)
avg = imtools.compute_average(filelist)
for impath in filelist:
im1 = array(Image.open(impath))
subplot(2, 2, filelist.index(impath) + 1)
imshow(im1)
imNum = str(filelist.index(impath) + 1)
title(u'待平均图像' + imNum, fontproperties=font)
axis('off')
subplot(2, 2, 4)
imshow(avg)
title(u'平均后的图像', fontproperties=font)
axis('off')
show()
from skimage import io
def falter_image(path):
for i in os.listdir(path):
file = os.path.join(path,i)
image = io.imread(file)
image = np.where(image > 1,0,1)
new_image = np.ones((100,100))
row,col = image.shape
new_image[0:row,0:col] = image
io.imsave(file,(new_image * 255).astype(np.int))
# Uses sparse pca codepath.
# imlist = imtools.get_imlist('C:/Users/Zqc/Desktop/PCV-book-data/data/selectedfontimages/a_selected_thumbs/')
# falter_image("D:/datebase/test11")
imlist = imtools.get_imlist('D:/datebase/test11/')
print(imlist)
# 获取图像列表和他们的尺寸
im = array(Image.open(imlist[0])) # open one image to get the size
m, n = im.shape[:2] # get the size of the images
imnbr = len(imlist) # get the number of images
print("The number of images is %d" % imnbr)
# Create matrix to store all flattened images
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist], 'f')
# PCA降维
V, S, immean = pca.pca(immatrix)
# 保存均值和主成分
#f = open('./a_pca_modes.pkl', 'wb')
def PCA_Kmeans(train_path,result_path):
# Uses sparse pca codepath.
# imlist = imtools.get_imlist('C:/Users/Zqc/Desktop/PCV-book-data/data/selectedfontimages/a_selected_thumbs/')
# falter_image("D:/datebase/test")
imlist = imtools.get_imlist(train_path)
# print(imlist)
# 获取图像列表和他们的尺寸
im = array(Image.open(imlist[0])) # open one image to get the size
m, n = im.shape[:2] # get the size of the images
imnbr = len(imlist) # get the number of images
print("The number of images is %d" % imnbr)
# Create matrix to store all flattened images
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist], 'f')
# PCA降维
V, S, immean = pca.pca(immatrix)
# 保存均值和主成分
# f = open('./a_pca_modes.pkl', 'wb')
# f = open('C:/Users/Zqc/Desktop/PCV-book-data/data/selectedfontimages/a_pca_modes.pkl', 'wb')
f = open(train_path + "\\a_pca_modes.pkl", 'wb')
pickle.dump(immean, f)
pickle.dump(V, f)
f.close()
# get list of images
# imlist = imtools.get_imlist('C:/Users/Zqc/Desktop/PCV-book-data/data/selectedfontimages/a_selected_thumbs/')
print("go")
imlist = imtools.get_imlist(train_path)
imnbr = len(imlist)
# load model file
# with open('C:/Users/Zqc/Desktop/PCV-book-data/data/selectedfontimages/a_pca_modes.pkl','rb') as f:
with open(train_path + "a_pca_modes.pkl", 'rb') as f:
immean = pickle.load(f)
V = pickle.load(f)
# create matrix to store all flattened images
immatrix = array([array(Image.open(im)).flatten() for im in imlist], 'f')
# project on the 40 first PCs
immean = immean.flatten()
projected = array([dot(V[:30], immatrix[i] - immean) for i in range(imnbr)])
print("PCA")
# k-means
projected = whiten(projected)
centroids, distortion = kmeans(projected, 370)
code, distance = vq(projected, centroids)
filepath = result_path
# plot clusters
for k in range(370):
tempath = filepath + str(k)
os.makedirs(tempath)
ind = where(code == k)[0]
for i in range(len(ind)):
io.imsave(tempath + "\\" + str(i) + ".png", immatrix[ind[i]].reshape((100, 100)).astype(np.uint8),
cmap="gray")
# -*- coding: utf-8 -*-
from PCV.tools.imtools import get_imlist #导入PCV模块
from PIL import Image
import os
import pickle
filelist = get_imlist('results/1/') #获取convert_images_format_test文件夹下的图片文件名(包括后缀名)
os.mkdir('last')
imlist = file('last/imlist.txt','w') #将获取的图片文件列表保存到imlist.txt中
pickle.dump(filelist,imlist) #序列化
imlist.close()
for infile in filelist:
outfile = os.path.splitext(infile)[0] + ".tif" #分离文件名与扩展名
if infile != outfile:
try:
Image.open(infile).save(outfile)
except IOError:
print ("cannot convert", infile)
from PIL import Image
from pylab import *
from numpy import *
from PCV.tools import imtools, pca
# Get list of images and their size
imlist = imtools.get_imlist('fontimages/') # fontimages.zip is part of the book data set
im = array(Image.open(imlist[0])) # open one image to get the size
m,n = im.shape[:2]
# Create matrix to store all flattened images
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist],'f')
# Perform PCA
V,S,immean = pca.pca(immatrix)
# Show the images (mean and 7 first modes)
# This gives figure 1-8 (p15) in the book.
figure()
gray()
subplot(2,4,1)
imshow(immean.reshape(m,n))
for i in range(7):
subplot(2,4,i+2)
imshow(V[i].reshape(m,n))
show()
from PIL import Image
from scipy.cluster.vq import *
from PCV.tools import pca
img_w = 128
img_h = 128
img_deep = 3
pca_demension = 40 # 亦即取40张图去和特征做dot点乘
k_category = 8 # k-means聚类,设置为8类
#
imgs_path = "/Users/zac/5-Algrithm/algrithm-data/ImageCluster/images_resized"
imlist = imtools.get_imlist(imgs_path)
# 获取图像列表和其尺寸
im = array(Image.open(imlist[0])) # open one image to get the size
m, n = im.shape[:2] # get the size of the images
imnbr = len(imlist) # get number of images
print " the number of images is %d" % imnbr
# Create matrix to store all flattened images
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist], 'f')
# PCA降维
V, S, immean = pca.pca(immatrix)
# 保存均值和主成分
pkl_path = "/Users/zac/5-Algrithm/algrithm-data/ImageCluster/pca_model.pkl"
#f = open('./a_pca_modes.pkl', 'wb')
import pickle
from PCV.imagesearch import imagesearch
from PCV.localdescriptors import sift
from sqlite3 import dbapi2 as sqlite
from PCV.tools.imtools import get_imlist
imlist = get_imlist("./first500/")
nbr_images = len(imlist)
featlist = [imlist[i][:-3] + "sift" for i in range(nbr_images)]
# load vocabulary
with open("./vocabulary.pkl", "rb") as f:
voc = pickle.load(f)
# create indexer
indx = imagesearch.Indexer("web.db", voc)
indx.create_tables()
# go through all images, project features on vocabulary and insert
for i in range(nbr_images)[:500]:
locs, descr = sift.read_features_from_file(featlist[i])
indx.add_to_index(imlist[i], descr)
# commit to database
indx.db_commit()
con = sqlite.connect("web.db")
print con.execute("select count (filename) from imlist").fetchone()
print con.execute("select * from imlist").fetchone()
# -*- coding: utf-8 -*-
from PCV.tools import imtools, pca
from PIL import Image, ImageDraw
from pylab import *
from scipy.cluster.vq import *
import scipy.sparse as ss
import myTools as mt
import numpy as np
import pickle
np.seterr(divide='ignore',invalid='ignore')
save_A_path = './A.pkl'
save_feat_path = './result/feat.pkl'
imlist = imtools.get_imlist('./data/fer2013/cluTest/')
imnbr = len(imlist)
# Load images, run PCA.
immatrix = array([array(Image.open(im)).flatten() for im in imlist], 'f')
V, S, immean = pca.pca(immatrix)
# Project on 2 PCs.
#projected = array([dot(V[[0, 1]], immatrix[i] - immean) for i in range(imnbr)]) # P131 Fig6-3左图
#projected = array([dot(V[[1, 2]], immatrix[i] - immean) for i in range(imnbr)]) # P131 Fig6-3右图
projected = array([dot(V[:40],immatrix[i]-immean) for i in range(imnbr)]) #463*40 = n*40
n = len(projected)
nn_opt = 'pdist'
if nn_opt == 'pdist':
# -*- coding: utf-8 -*-
from PCV.tools import imtools, pca
from PIL import Image, ImageDraw
from pylab import *
from scipy.cluster.vq import *
imlist = imtools.get_imlist('tmp/test/')
imnbr = len(imlist)
# Load images, run PCA.
immatrix = array([array(Image.open(im)).flatten() for im in imlist], 'f')
V, S, immean = pca.pca(immatrix)
projected = array([dot(V[[0, 1]], immatrix[i] - immean) for i in range(imnbr)])
n = len(projected)
# compute distance matrix
S = array([[sqrt(sum((projected[i] - projected[j])**2)) for i in range(n)]
for j in range(n)], 'f')
# create Laplacian matrix
rowsum = sum(S, axis=0)
D = diag(1 / sqrt(rowsum))
I = identity(n)
L = I - dot(D, dot(S, D))
# compute eigenvectors of L
U, sigma, V = linalg.svd(L)
k = 20
# create feature vector from k first eigenvectors
# by stacking eigenvectors as columns
features = array(V[:k]).T
# k-means
"""
Created on 2013-3-19
@author: liaoyuhua
"""
from PCV.localdescriptors import sift
from PCV.tools import imtools as itl
import pickle
from PCV.imagesearch import vocabulary
from PCV.imagesearch import imagesearch
if __name__ == "__main__":
path = r"D:\Python_Computer_Vision\data\sunsets\flickr-sunsets-small"
imlist = itl.get_imlist(path)
nbr_images = len(imlist)
featlist = [i[:-3] + "sft" for i in imlist]
# print '\n'.join(featlist)
# for i in range(nbr_images):
# sift.process_image(imlist[i], featlist[i])
# print "Sift Processing Ok!"
# voc=vocabulary.Vocabulary('ukbenchtest')
# voc.train(featlist,100,1)
# print "voc constructed!"
# with open('ukbentest.pkl','wb') as f:
# pickle.dump(voc,f)
# print 'vocabulary is,',voc.name,voc.nbr_words
with open("ukbentest.pkl", "rb") as f:
voc = pickle.load(f)
indx = imagesearch.Indexer("test.db", voc)
from PIL import Image
from PCV.localdescriptors import sift
from PCV.tools import imtools
import pydot
""" This is the example graph illustration of matching images from Figure 2-10.
To download the images, see ch2_download_panoramio.py."""
#download_path = "panoimages" # set this to the path where you downloaded the panoramio images
#path = "/FULLPATH/panoimages/" # path to save thumbnails (pydot needs the full system path)
download_path = "F:\\dropbox\\Dropbox\\translation\\pcv-notebook\\data\\panoimages" # set this to the path where you downloaded the panoramio images
path = "F:\\dropbox\\Dropbox\\translation\\pcv-notebook\\data\\panoimages\\" # path to save thumbnails (pydot needs the full system path)
# list of downloaded filenames
imlist = imtools.get_imlist(download_path)
nbr_images = len(imlist)
# extract features
featlist = [imname[:-3] + 'sift' for imname in imlist]
#for i, imname in enumerate(imlist):
# sift.process_image(imname, featlist[i])
matchscores = zeros((nbr_images, nbr_images))
for i in range(nbr_images):
for j in range(i, nbr_images): # only compute upper triangle
print 'comparing ', imlist[i], imlist[j]
l1, d1 = sift.read_features_from_file(featlist[i])
l2, d2 = sift.read_features_from_file(featlist[j])
matches = sift.match_twosided(d1, d2)
from PCV.tools import imtools
from PCV.clustering import hcluster
import pickle
from scipy import *
from pylab import *
import matplotlib.pyplot as plt
from PIL import Image
from scipy.cluster.vq import *
from PCV.tools import pca
# Uses sparse pca codepath.
bank_hl = r'E:\CheckDS\bank_hualing'
bank_dn = r'E:\CheckDS\bank_logo0927'
imlist = imtools.get_imlist(bank_dn)
# imlist = imlist + imtools.get_imlist(bank_hl)
# 获取图像列表和他们的尺寸
im = array(Image.open(imlist[0])) # open one image to get the size
m, n = im.shape[:2] # get the size of the images
print("The number of images is %d" % len(imlist))
# Create matrix to store all flattened images
imss = [Image.open(imname) for imname in imlist]
immatrix = array([array(Image.open(imname)).flatten() for imname in imlist],
'f')
from PIL import Image
from PCV.localdescriptors import sift
from PCV.tools import imtools
import pydot
"""
This is the example graph illustration of matching images from Figure 2-10.
To download the images, see ch2_download_panoramio.py.
"""
download_path = "panoimages" # set this to the path where you downloaded the panoramio images
path = "/FULLPATH/panoimages/" # path to save thumbnails (pydot needs the full system path)
# list of downloaded filenames
imlist = imtools.get_imlist(download_path)
nbr_images = len(imlist)
# extract features
featlist = [imname[:-3] + 'sift' for imname in imlist]
for i, imname in enumerate(imlist):
sift.process_image(imname, featlist[i])
matchscores = zeros((nbr_images, nbr_images))
for i in range(nbr_images):
for j in range(i, nbr_images): # only compute upper triangle
print 'comparing ', imlist[i], imlist[j]
l1, d1 = sift.read_features_from_file(featlist[i])
l2, d2 = sift.read_features_from_file(featlist[j])
matches = sift.match_twosided(d1, d2)
from PIL import Image
from numpy import *
from pylab import *
from PCV.tools import imtools, pca
path = '/home/duan/pycv/PCV-data/a_thumbs'
imlist = imtools.get_imlist(path)
im = array(Image.open(imlist[0]))
m, n = im.shape[0:2]
imnbr = len(imlist)
immatrix = array([ array(Image.open(im)).flatten()
for im in imlist ], 'f')
V, S, immean = pca.pca(immatrix)
figure()
gray()
subplot(2,4,1)
imshow(immean.reshape(m,n))
for i in range(7):
subplot(2,4,i+2)
imshow(V[i].reshape(m,n))
show()
# -*- coding: utf-8 -*-
import pickle
from PCV.imagesearch import imagesearch
from PCV.localdescriptors import sift
import sqlite3
from PCV.tools.imtools import get_imlist
#获取图像列表
imlist = get_imlist('training/')
nbr_images = len(imlist)
#获取特征列表
featlist = [imlist[i][:-3] + 'sift' for i in range(nbr_images)]
# load vocabulary
with open('training/vocabulary.pkl', 'rb') as f:
voc = pickle.load(f)
# 创建索引
indx = imagesearch.Indexer('testImaAdd_training.db', voc)
indx.create_tables()
# go through all images, project features on vocabulary and insert
for i in range(nbr_images):
locs, descr = sift.read_features_from_file(featlist[i])
indx.add_to_index(imlist[i], descr)
# commit to database
indx.db_commit()
con = sqlite3.connect('testImaAdd_training.db')
print(con.execute('select count (filename) from imlist').fetchone())
from PCV.tools import imtools, pca
from PIL import Image, ImageDraw
from PCV.localdescriptors import sift
from pylab import *
import glob
from scipy.cluster.vq import *
#download_path = "panoimages" # set this to the path where you downloaded the panoramio images
#path = "/FULLPATH/panoimages/" # path to save thumbnails (pydot needs the full system path)
download_path = "F:/dropbox/Dropbox/translation/pcv-notebook/data/panoimages" # set this to the path where you downloaded the panoramio images
path = "F:/dropbox/Dropbox/translation/pcv-notebook/data/panoimages/" # path to save thumbnails (pydot needs the full system path)
# list of downloaded filenames
imlist = imtools.get_imlist('../data/panoimages/')
nbr_images = len(imlist)
# extract features
#featlist = [imname[:-3] + 'sift' for imname in imlist]
#for i, imname in enumerate(imlist):
# sift.process_image(imname, featlist[i])
featlist = glob.glob('../data/panoimages/*.sift')
matchscores = zeros((nbr_images, nbr_images))
for i in range(nbr_images):
for j in range(i, nbr_images): # only compute upper triangle
print 'comparing ', imlist[i], imlist[j]
l1, d1 = sift.read_features_from_file(featlist[i])
