Tuning of data augmentation hyperparameters in deep learning to building construction image classification with small datasets

Deep Learning methods have important applications in the building construction image classification field. One challenge of this application is Convolutional Neural Networks adoption in a small datasets. This paper proposes a rigorous methodology for tuning of Data Augmentation hyperparameters in Deep Learning to building construction image classification, especially to vegetation recognition in facades and roofs structure analysis. In order to do that, Logistic Regression models were used to analyze the performance of Convolutional Neural Networks trained from 128 combinations of transformations in the images. Experiments were carried out with three architectures of Deep Learning from the literature using the Keras library. The results show that the recommended configuration (Height Shift Range = 0.2; Width Shift Range = 0.2; Zoom Range =0.2) reached an accuracy of 95.6% in the test step of first case study. In addition, the hyperparameters recommended by proposed method also achieved the best test results for second case study: 93.3%.

Automated summary

This paper discusses the importance and challenges of using deep learning methods in building construction image classification, and proposes a method for tuning data augmentation hyperparameters to improve classification accuracy. Experimental results show that the recommended hyperparameter configuration achieved high accuracy in both case studies.