def save_vis(filename_list, number_list, pred_pca, output_hcluster, output_PCA):
imlist = filename_list
imnbr = len(imlist)
# Load images, run PCA.
immatrix = array(pred_pca)
V, S, immean = pca.pca(immatrix)
# Project on 2 PCs.
projected = array([dot(V[[0, 1]], immatrix[i] - immean) for i in range(imnbr)])
# 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)
# paste thumbnail of each image
for i in range(imnbr):
nodeim = Image.open(imlist[i])
nodeim.thumbnail((25, 25))
ns = nodeim.size
box = (scaled[i][0] - ns[0] // 2, scaled[i][1] - ns[1] // 2,
scaled[i][0] + ns[0] // 2 + 1, scaled[i][1] + ns[1] // 2 + 1)
img.paste(nodeim, box)
tree = hcluster.hcluster(projected)
hcluster.draw_dendrogram(tree,imlist,filename=output_hcluster)
for i, num in enumerate(number_list):
if num < 8:
color1 = mod(370*num,255)
color2 = mod(170*num,255)
color3 = mod(270*num,255)
draw.text((scaled[i][0],scaled[i][1]),str(num),fill = (color1,color2,color3))
else:
draw.text((scaled[i][0],scaled[i][1]),str(num),fill = (255,0,0))
figure()
imshow(img)
axis('off')
img.save(output_PCA)
show()
#
# print len(clusters)
# for c in clusters:
# print c.get_cluster_elements()
path = r'D:\Python_Computer_Vision\data\sunsets\flickr-sunsets-small'
imlist= [ os.path.join(path,f) for f in os.listdir(path) if f.endswith('.jpg')]
features = zeros([len(imlist),512])
for i,f in enumerate(imlist):
im=array(Image.open(f))
h,edges=histogramdd(im.reshape(-1,3), 8, normed=True, range=[(0,255),(0,255),(0,255)])
features[i]=h.flatten()
tree = hcluster.hcluster(features)
hcluster.draw_dendrogram(tree, imlist, filename='sunset.pdf')
#visualize clusters with some threshold
clusters = tree.extract_clusters(0.23* tree.distance)
for c in clusters:
elements = c.get_cluster_elements()
nbr_elements = len(elements)
if nbr_elements>3:
figure()
for p in range(minimum(nbr_elements,20)):
subplot(4,5,p+1)
im = array(Image.open(imlist[elements[p]]))
imshow(im)
axis('off')
show()
h, edges = histogramdd(im.reshape(-1, 3), 8, normed=True, range=[(0, 255), (0, 255), (0, 255)])
features[i] = h.flatten()
tree = hcluster.hcluster(features)
# visualize clusters with some (arbitrary) threshold
clusters = tree.extract_clusters(img_distance * tree.distance)
base_dir = 'datas/'
# plot images for clusters with more than 3 elements
for i,c in enumerate(clusters):
elements = c.get_cluster_elements()
nbr_elements = len(elements)
if nbr_elements >= clusters_num:
for e in elements:
print(imlist[e], i, c.get_depth(), c.get_height())
dst = base_dir + str(i)
if not os.path.isdir(dst):
os.makedirs(dst)
src = imlist[e]
shutil.copy(src, dst)
#figure(figsize=(18,10))
#for p in range(minimum(nbr_elements,20)):
#subplot(4, 5, p + 1)
#subplots_adjust(wspace =0.01, hspace =0.01, left=0, right=1, bottom=0,top=1)
#im = array(Image.open(imlist[elements[p]]))
#imshow(im)
#axis('off')
#show()
hcluster.draw_dendrogram(tree,imlist,filename='./sunset.png')
# 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)
# paste thumbnail of each image
for i in range(imnbr):
nodeim = Image.open(imlist[i])
nodeim.thumbnail((25, 25))
ns = nodeim.size
box = (scaled[i][0] - ns[0] // 2, scaled[i][1] - ns[1] // 2,
scaled[i][0] + ns[0] // 2 + 1, scaled[i][1] + ns[1] // 2 + 1)
img.paste(nodeim, box)
tree = hcluster.hcluster(projected)
hcluster.draw_dendrogram(tree,imlist,filename='fonts.png')
figure()
imshow(img)
axis('off')
img.save('./pca_font.png')
show()
from numpy import *
# create a list of images
path = 'data/first1000/'
imlist = [os.path.join(path, f) for f in os.listdir(path) if f.endswith('.jpg')]
# extract feature vector (8 bins per color channel)
features = zeros([len(imlist), 512])
for i, f in enumerate(imlist):
im = array(Image.open(f))
# multi-dimensional histogram
h, edges = histogramdd(im.reshape(-1, 3), 8, normed=True, range=[(0, 255), (0, 255), (0, 255)])
features[i] = h.flatten()
tree = hcluster.hcluster(features)
# visualize clusters with some (arbitrary) threshold
clusters = tree.extract_clusters(0.23 * tree.distance)
# plot images for clusters with more than 3 elements
for c in clusters:
elements = c.get_cluster_elements()
nbr_elements = len(elements)
if nbr_elements > 3:
figure()
for p in range(minimum(nbr_elements,20)):
subplot(4, 5, p + 1)
im = array(Image.open(imlist[elements[p]]))
imshow(im)
axis('off')
show()
hcluster.draw_dendrogram(tree,imlist,filename='sunset.pdf')