Method for image data augmentation, method for training model with augmented image data and non-transitory computer-readable medium

Abstract

A method for image data augmentation, a method for training model with augmented image data and a non-transitory computer-readable medium are provided. In the method for image data augmentation, multiple images are firstly obtained, and a data augmentation procedure is performed on each of the multiple images. In the data augmentation procedure, each of the multiple images is cropped into a first size image, and the first size image is modified to be a second size image. The second size image is randomly cropped from different positions into multiple image blocks multiple times. The multiple image blocks are then randomly arranged and recombined to be an augmented image. After repeatedly performing the data augmentation procedure on the multiple images, multiple augmented images that are configured to be a training dataset to train an intelligent model are generated.

Images