Reduce image
Or called down-sampling (subsampled) or down-sampling (downsampled), there are two main purposes: 1. Make the image fit the size of the display area; 2. Generate a thumbnail of the corresponding image.
Zoom in image
Or called upsampling or image interpolation, the main purpose is to enlarge the original image so that it can be displayed on a higher resolution display device.
The zoom operation on the image will inevitably affect the image quality. However, there are indeed some zooming methods that can increase the information of the image, so that the quality of the zoomed image exceeds the quality of the original image.
Downsampling is pooling
The sampling layer is implemented using pooling related technology, the purpose is to reduce the dimension of the feature and retain effective information, to a certain extent to avoid overfitting. But the purpose of pooling is not only these, its purpose is to maintain rotation, translation, expansion and contraction. Sampling includes maximum sampling, average sampling, summation area sampling and random area sampling. Pooling is also like this, such as maximum pooling, average pooling, random pooling, summation area pooling, etc.
Principle of Downsampling
For an image I with a size of M N, perform s times downsampling to obtain a resolution image of (M/s) (N/s) size. Of course, s should be the common divisor of M and N. If the image in the form of a matrix is considered, the image in the s*s window of the original image is turned into a pixel, and the value of this pixel is the average value of all pixels in the window
Upsampling principle
Image magnification almost always uses interpolation methods, that is, on the basis of the original image pixels, appropriate interpolation algorithms are used to insert new elements between pixels.