A General Framework for Multi-focal Image Classification and Authentication: Application to Microscope Pollen Images

TL;DR

This paper introduces a versatile, automatic framework for multi-focal image classification and authentication, demonstrated on microscope pollen images, achieving high accuracy across various pollen types and image conditions.

Contribution

The proposed framework is generic, efficient, and adaptable to any multi-focal images, with an automatic pipeline from focus selection to classification and authentication.

Findings

Classification accuracy above 97% with Random Forest.

Framework effective on any number of pollen types.

Automatic multi-stage image processing pipeline.

Abstract

In this article, we propose a general framework for multi-focal image classification and authentication, the methodology being demonstrated on microscope pollen images. The framework is meant to be generic and based on a brute force-like approach aimed to be efficient not only on any kind, and any number, of pollen images (regardless of the pollen type), but also on any kind of multi-focal images. All stages of the framework's pipeline are designed to be used in an automatic fashion. First, the optimal focus is selected using the absolute gradient method. Then, pollen grains are extracted using a coarse-to-fine approach involving both clustering and morphological techniques (coarse stage), and a snake-based segmentation (fine stage). Finally, features are extracted and selected using a generalized approach, and their classification is tested with four classifiers: Weighted Neighbor Distance, Neural Network, Decision Tree and Random Forest. The latter method, which has shown the best and more robust classification accuracy results (above 97\% for any number of pollen types), is finally used for the authentication stage.