TF’s Image Processing Module (Part 1)

Digital images are stored in a variety of formats. Images can be in different sizes and scales. Moreover, we might have to adjust the brightness and contrast of the images to make them look visually better. The TF framework provides us with the tf.image module to perform image processing. This module consists of numerous image processing functions for geometric and color transformations. Let’s explore the functions of the tf.image module for geometric transformations.

Geometric transformations

Geometric transformations change the geometry of images without altering their pixel values. Some of the geometric transformations are given below.

Image resizing

The tf.image.resize function accepts the arguments size (of the output image) and the interpolation method, e.g., "bilinear", "bicubic", and "gaussian", for resizing an input image.