Automated Palynological Analysis System: Integrating Deep Metric Learning, Detection and Classification in Bright Field Microscopy
cs.CV, physics.optics
Submitted: 2026-04-17
Updated: 2026-09-23
Comments: 12 pages, 16 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: Traditional melissopalynology is a time-consuming and subjective process, often taking 4-6 hours per sample.
Terminology
Abstract
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 infinity 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 at least 6x processing speedup compared to manual expert analysis.
Sources
- DINOv2: Learning Robust Visual Features without Supervision
- Three-Dimensional Volumetric Reconstruction of Native Chilean Pollen via Lens-Free Digital In-line Holographic Microscopy
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models