Applying convolutional neural networks to extremely sparse image datasets using an image subdivision approach
This work addresses a domain-specific challenge in image analysis for sparse data, but it is incremental as it adapts existing CNN methods.
The authors tackled the problem of applying convolutional neural networks to extremely sparse image datasets by using an image subdivision approach, enabling analysis and assessment of regions with predominant features.
Purpose: The aim of this work is to demonstrate that convolutional neural networks (CNN) can be applied to extremely sparse image libraries by subdivision of the original image datasets. Methods: Image datasets from a conventional digital camera was created and scanning electron microscopy (SEM) measurements were obtained from the literature. The image datasets were subdivided and CNN models were trained on parts of the subdivided datasets. Results: The CNN models were capable of analyzing extremely sparse image datasets by utilizing the proposed method of image subdivision. It was furthermore possible to provide a direct assessment of the various regions where a given API or appearance was predominant.