I am implementing a CNN model for Detection of Forged Images. The paper I am referring to asks to initialize the kernel weights of the first layer with 30 basic high pass filters (the ones used in calculation of residual maps in SRM). What is this high pass filter and how to do this? Also, is there any function that instead of a single image at a time, these filters can be applied to a batch of images...similar to ImageDataGenerator?
Research Paper Reference: https://ieeexplore.ieee.org/document/7823911