Automated Pollen Recognition in Optical and Holographic Microscopy Images

TL;DR

This paper demonstrates the application of deep learning models, YOLOv8s and MobileNetV3L, to automate pollen detection and classification in optical and holographic microscopy images, improving accuracy and addressing challenges in holographic imaging.

Contribution

It introduces a novel approach combining deep learning with lensless holographic microscopy for pollen analysis, including techniques to enhance performance on holographic images.

Findings

Achieved 91.3% mAP50 in optical image detection

Reached 97% accuracy in optical image classification

Improved holographic image detection from 2.49% to 13.3% mAP50

Abstract

This study explores the application of deep learning to improve and automate pollen grain detection and classification in both optical and holographic microscopy images, with a particular focus on veterinary cytology use cases. We used YOLOv8s for object detection and MobileNetV3L for the classification task, evaluating their performance across imaging modalities. The models achieved 91.3% mAP50 for detection and 97% overall accuracy for classification on optical images, whereas the initial performance on greyscale holographic images was substantially lower. We addressed the performance gap issue through dataset expansion using automated labeling and bounding box area enlargement. These techniques, applied to holographic images, improved detection performance from 2.49% to 13.3% mAP50 and classification performance from 42% to 54%. Our work demonstrates that, at least for image classification tasks, it is possible to pair deep learning techniques with cost-effective lensless digital holographic microscopy devices.