Learn how to use K-Means for Image Clustering. Using transfer learning model for feature extraction from the images
In an image classification problem we have to classify a given set of images into a given number of categories. Training data is available in classification problem but what to do when there is no training data available, to solve this problem we can use clustering to group similar images together.
Clustering is an unsupervised machine learning where we group similar features together. It interprets the input data and finds natural groups or clusters in feature space.
Here I have used k-means for image clustering. I have taken cats vs dogs dataset.
I have separated cat and dog images into separate folders and show how clustering can be done in images.
Images from the dataset
I have used transfer learning model InceptionV3 to extract features from images and use those features for clustering.
#deep-learning #machine-learning #artificial-intelligence #data-science #python
