Pollen Grain Microscopic Image Classification Using an Ensemble of Fine-Tuned Deep Convolutional Neural Networks

TL;DR

This paper introduces an ensemble of fine-tuned deep convolutional neural networks for classifying pollen grain images, significantly improving accuracy and F1-score over previous methods in a challenging benchmark.

Contribution

The study presents a novel ensemble approach combining four state-of-the-art CNN models trained on multiple image sizes for improved pollen classification accuracy.

Findings

Achieved 94.48% accuracy on training data

Reached 96.28% accuracy on test data in the challenge

Outperformed many existing approaches in benchmark results

Abstract

Pollen grain micrograph classification has multiple applications in medicine and biology. Automatic pollen grain image classification can alleviate the problems of manual categorisation such as subjectivity and time constraints. While a number of computer-based methods have been introduced in the literature to perform this task, classification performance needs to be improved for these methods to be useful in practice. In this paper, we present an ensemble approach for pollen grain microscopic image classification into four categories: Corylus Avellana well-developed pollen grain, Corylus Avellana anomalous pollen grain, Alnus well-developed pollen grain, and non-pollen (debris) instances. In our approach, we develop a classification strategy that is based on fusion of four state-of-the-art fine-tuned convolutional neural networks, namely EfficientNetB0, EfficientNetB1, EfficientNetB2 and SeResNeXt-50 deep models. These models are trained with images of three fixed sizes (224x224, 240x240, and 260x260 pixels) and their prediction probability vectors are then fused in an ensemble method to form a final classification vector for a given pollen grain image. Our proposed method is shown to yield excellent classification performance, obtaining an accuracy of of 94.48% and a weighted F1-score of 94.54% on the ICPR 2020 Pollen Grain Classification Challenge training dataset based on five-fold cross-validation. Evaluated on the test set of the challenge, our approach achieved a very competitive performance in comparison to the top ranked approaches with an accuracy and a weighted F1-score of 96.28% and 96.30%, respectively.