import imtools
from PIL import Image
from pylab import *
imlist = imtools.get_imlist('/Users/thakis/Downloads/data/flickr-sunsets-small')
# extract histogram as feature vector (8 bins per color channel)
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='out_sunset.png')
# visualize clusters
clusters = tree.extract_clusters(dist=0.23 * tree.distance)
for c in clusters:
elements = c.get_cluster_elements()
if len(elements) > 3:
figure()
for p in range(minimum(len(elements), 20)):
subplot(4, 5, p + 1)
im = array(Image.open(imlist[elements[p]]))
imshow(im)
axis('off')
show()
from PIL import Image
from pylab import *
import imtools
import pickle
from scipy.cluster.vq import *
# 画像のリストを得る
imlist = imtools.get_imlist('selected_fontimages/')
imnbr = len(imlist)
# モデルのファイルを読み込む
with open('font_pca_modes.pkl','rb') as f:
immean = pickle.load(f)
V = pickle.load(f)
# 平板化した画像を格納する行列を作る
immatrix = array([array(Image.open(im)).flatten()
for im in imlist],'f')
# 第40主成分までを射影する
immean = immean.flatten()
projected = array([dot(V[:40],immatrix[i]-immean)
for i in range(imnbr)])
import hcluster
tree = hcluster.hcluster(projected)
hcluster.draw_dendrogram(tree,imlist,filename='fonts.jpg')
imlist = [os.path.join(path,f) for f in os.listdir(path)
if f.endswith('.jpg')]
# 特徴量ベクトルを抽出する（色チャンネルに8つのビン）
features = zeros([len(imlist), 512])
for i,f in enumerate(imlist):
im = array(Image.open(f))
# 多次元ヒストグラム
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')
# 任意の閾値についてクラスタを可視化する
clusters = tree.extract_clusters(0.23*tree.distance)
# 3要素以上のクラスタの画像を描画する
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')
imlist = imtools.get_imlist(
'/Users/thakis/Downloads/data/flickr-sunsets-small')
# extract histogram as feature vector (8 bins per color channel)
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='out_sunset.png')
# visualize clusters
clusters = tree.extract_clusters(dist=0.23 * tree.distance)
for c in clusters:
elements = c.get_cluster_elements()
if len(elements) > 3:
figure()
for p in range(minimum(len(elements), 20)):
subplot(4, 5, p + 1)
im = array(Image.open(imlist[elements[p]]))
imshow(im)
axis('off')
show()
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)
hcluster.draw_dendrogram(tree, imlist, filename='sunset.pdf')
# 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()
tree = hcluster.hcluster(projected)
def draw_tree(observations, filename):
node = hcluster([o[0] for o in observations])
draw_dendrogram(node, [o[1] for o in observations], filename)
return filename
