Automatic Pollen Classification and Segmentation Using U-Nets and Synthetic Data

Mihai Boldeanu

doi:10.1109/ACCESS.2022.3189012

Automatic Pollen Classification and Segmentation Using U-Nets and Synthetic Data

2022-01-01

2

OA

AI

M

Mihai Boldeanu *

M

Mónica González-Alonso

José María Maya‐Manzano

J

Jeroen Buters

DOI：10.1109/ACCESS.2022.3189012

Original

Original request for help

Save

Abstract

En 中文

Pollen allergies have become one of the most wide-spread afflictions that impact quality of life. This has made automatic pollen detection, classification and monitoring a very important topic of research. This paper introduces a new public annotated image data-set of pollen with almost 45 thousand samples obtained from an automatic instrument. In this work we apply some of the best performing convolutional neural networks architectures on the task of pollen classification as well as some fully convolutional networks optimized for image segmentation on complex microscope images. We obtain an F1 scores of 0.95 on the new data-set when the best trained model is used as a fully convolutional classifier and a class mean Intersection over Union (IoU) of 0.88 when used as an object detector.

Keywords:

Image segmentation

Data models

Training

Task analysis

Monitoring

Licenses

Convolutional neural networks

BAA-500

pollen classification

pollen image segmentation

U-net

artificial pollen dataset

Automatic Pollen Classification and Segmentation Using U-Nets and Synthetic Data

Abstract

Journal

Organization