Day #283 - Clustering to group similar Images

For large retail datasets, before object detection. Clustering becomes essential to focus on each cluster to take it forward. Today's post is clustering images into similar groups

• Generate Feature Data based on VGG / Resnet
• Cluster them using Kmeans
• Result output to their respective cluster directory

	#Base Code - https://medium.com/@franky07724_57962/using-keras-pre-trained-models-for-feature-extraction-in-image-clustering-a142c6cdf5b1
	#Modified for our custom need
	from keras.preprocessing import image
	from keras.applications.vgg16 import VGG16
	from keras.applications.resnet50 import ResNet50
	import numpy as np
	import os
	from sklearn.cluster import KMeans
	from keras.applications.resnet50 import preprocess_input, decode_predictions
	import shutil
	datadir = r'E:\Code_Repo\Images'
	output_dir = r'E:\Code_Repo\results'
	def createFolder(directory):
	try:
	if not os.path.exists(directory):
	os.makedirs(directory)
	except OSError:
	print('Error: Creating directory. ' + directory)
	def VGG_Cluster(numberofclusters):
	feature_list = []
	model = VGG16(weights='imagenet', include_top=False)
	files = os.listdir(datadir)
	for file in files:
	img_path = datadir+ str('\\') + file
	img = image.load_img(img_path, target_size=(224, 224))
	img_data = image.img_to_array(img)
	img_data = np.expand_dims(img_data, axis=0)
	img_data = preprocess_input(img_data)
	feature = model.predict(img_data)
	feature_np = np.array(feature)
	feature_list.append(feature_np.flatten())
	feature_list_np = np.array(feature_list)
	kmeans = KMeans(n_clusters=numberofclusters, random_state=0).fit(feature_list_np)
	labelresult = kmeans.labels_
	print(kmeans.labels_)
	print(kmeans.cluster_centers_)
	print('VGG Results')
	#Create Directory based on number of clusters
	for i in range(numberofclusters):
	directoryname = output_dir + str('\\') + str(i) + str('\\')
	createFolder(directoryname)
	for i in range(len(files)):
	img_path = datadir+ str('\\') + files[i]
	#Copy image according to the directory
	print(files[i])
	shutil.copy(img_path, output_dir + '\\' + str(labelresult[i]) + '\\')
	print(labelresult[i])
	def Resnet_Cluster(numberofclusters):
	feature_list = []
	model = ResNet50(weights='imagenet', include_top=False)
	files = os.listdir(datadir)
	for file in files:
	img_path = datadir+ str('\\') + file
	img = image.load_img(img_path, target_size=(224, 224))
	img_data = image.img_to_array(img)
	img_data = np.expand_dims(img_data, axis=0)
	img_data = preprocess_input(img_data)
	feature = model.predict(img_data)
	feature_np = np.array(feature)
	feature_list.append(feature_np.flatten())
	feature_list_np = np.array(feature_list)
	kmeans = KMeans(n_clusters=numberofclusters, random_state=0).fit(feature_list_np)
	labelresult = kmeans.labels_
	print(kmeans.labels_)
	print(kmeans.cluster_centers_)
	print('Resnet Results')
	#Create Directory based on number of clusters
	for i in range(numberofclusters):
	directoryname = output_dir + str('\\') + str(i) + str('\\')
	createFolder(directoryname)
	for i in range(len(files)):
	#Copy image according to the directory
	img_path = datadir+ str('\\') + files[i]
	print(files[i])
	shutil.copy(img_path, output_dir + '\\' + str(labelresult[i]) + '\\')
	print(labelresult[i])
	#VGG_Cluster(3)
	Resnet_Cluster(3)

view raw Image_Clustering.py hosted with ❤ by GitHub

Input - Mixed Set of Images

Output 
Cluster 1

Cluster 2

Cluster 3

More Reads - Example (in R)

Happy Learning!!!