Transformer models improve activated sludge image recognition accuracy
Effects of model architecture and learning strategies on deep learning-based recognition of activated sludge microscopic images and comparison with quantitative image analysis
Computer Vision and Pattern Recognition
Summary
Identifying what’s in sludge under a microscope helps keep water clean, but it’s tricky. The authors tested different computer methods to recognize sludge images and found that newer transformer-based models worked better than older ones. They also learned that keeping the overall scene in images matters more for accuracy than just zooming in on details. Finally, their advanced models beat older image analysis techniques in correctly identifying sludge types.
What this means in practice
- •For wastewater plant operators: Classify sludge microscopic images with higher accuracy to improve process monitoring and control.
- •For environmental monitoring teams: Use improved deep learning models to automate identification of activated sludge characteristics in water quality studies.
Authors
Suguru Hakoshima, Tomohiro Tobino, Fumiyuki Nakajima
Abstract
Microscopic image analysis has long been recognized as a promising approach for monitoring activated sludge. In recent years, deep learning-based image analysis has been increasingly adopted in this field because of its high performance. However, previous studies on microscopic image analysis of activated sludge have rarely explored transformer-based models or self-supervised foundation models and have instead relied on CNNs and supervised ImageNet pretraining. In addition, previous studies often downsampled image sizes, but the effects of downsampling have not been sufficiently investigated, and the relationship between downsampling strategies and image analysis performance remains unclear. Furthermore, no study has quantitatively compared deep learning performance with quantitative image analysis (QIA), which was widely used before the emergence of deep learning. In this study, to examine how model architecture and learning strategies affect performance in microscopic image analysis of activated sludge and to quantitatively determine whether deep learning outperforms QIA, we prepared three types of activated sludge samples, classified their microscopic images, and evaluated classification accuracy. Our results showed that transformer-based architectures and alternative pretraining methods were effective in terms of classification accuracy. Our downsampling analysis showed that using overly small images reduced accuracy, but increasing image size beyond a certain point did not improve it further. In addition, the analysis indicated that, to achieve high classification accuracy, maintaining the field of view was a more effective downsampling strategy than maintaining resolution. Finally, our comparison between deep learning and QIA showed that deep learning outperformed QIA in terms of accuracy.