Generation of microbial colonies dataset with deep learning style transfer
This provides a resource-efficient solution for researchers in microbiology and related fields needing labeled datasets for object detection, though it is incremental as it builds on existing style transfer and computer vision techniques.
The paper tackles the problem of generating annotated synthetic microbiological images for training deep learning models, achieving comparable detection and counting performance (mAP 0.416 vs. 0.520, MAE 4.49 vs. 4.31) with only 100 real images instead of thousands.
We introduce an effective strategy to generate an annotated synthetic dataset of microbiological images of Petri dishes that can be used to train deep learning models in a fully supervised fashion. The developed generator employs traditional computer vision algorithms together with a neural style transfer method for data augmentation. We show that the method is able to synthesize a dataset of realistic looking images that can be used to train a neural network model capable of localising, segmenting, and classifying five different microbial species. Our method requires significantly fewer resources to obtain a useful dataset than collecting and labeling a whole large set of real images with annotations. We show that starting with only 100 real images, we can generate data to train a detector that achieves comparable results (detection mAP = 0.416, and counting MAE = 4.49) to the same detector but trained on a real, several dozen times bigger dataset (mAP = 0.520, MAE = 4.31), containing over 7k images. We prove the usefulness of the method in microbe detection and segmentation, but we expect that it is general and flexible and can also be applicable in other domains of science and industry to detect various objects.