1. Apply K-means algorithm for image compression
Read a picture
Observe the image file size, memory size, image data structure, linearization
Use kmeans to cluster image pixel colors
Get the color category of each pixel, the color of each category
Compressed image generation: replace the original pixel color with clustering and return to two-dimensional
Observe the file size of compressed pictures, occupying memory size
The source code is as follows:
The results are as follows:
2. Observe the problems that can be solved with K-means in learning and life.
Complete an application case from data-model training-test-prediction.
This case will be scored separately as one of the course outcomes.