Automated Palynological Analysis System: Integrating Deep Metric Learning and $U^{2}$-Net Detection in $H\infty$ bright field microscopy
This work addresses the bottleneck of time-consuming and subjective manual palynological analysis for researchers in fields like ecology and allergy monitoring.
The authors developed an automated microscopy system for pollen analysis that integrates U²-Net detection and DINOv2-based deep metric learning, achieving 95.8% classification recall and a 6x speedup over manual analysis.
Traditional melissopalynology is a time-consuming and subjective process, often taking 4-6 hours per sample. We present an automated, high-throughput microscopy system that integrates $H\infty$ robust mechanical control with advanced deep learning pipelines for the precise counting, classification, and morphological analysis of pollen grains from Bio Bio region in south central territory in Chile. Our system employs $U^{2}$-Net for salient object detection and a DINOv2 Vision Transformer backbone trained via Deep Metric Learning for classification. By integrating Gradient-Weighted Attention, the model provides human-interpretable texture and diagnostic feature annotations. The system achieves a 95.8$\%$ classification recall and a 6x processing speedup compared to manual expert analysis.