An effective and friendly tool for seed image analysis

TL;DR

This paper introduces a user-friendly software tool with plugins for seed image analysis, enabling feature extraction and classification to aid research in biology, botany, and related fields.

Contribution

It presents a novel framework with ImageJ plugins for seed image feature extraction and classification, enhancing analysis capabilities in life sciences.

Findings

Features and classification predictions are accurate and valid.

The tool is easily extendable to other image analysis fields.

Experimental results confirm the effectiveness of the software.

Abstract

Image analysis is an essential field for several topics in the life sciences, such as biology or botany. In particular, the analysis of seeds (e.g. fossil research) can provide significant information on their evolution, the history of agriculture, plant domestication and knowledge of diets in ancient times. This work aims to present software that performs image analysis for feature extraction and classification from images containing seeds through a novel and unique framework. In detail, we propose two plugins \emph{ImageJ}, one able to extract morphological, textual and colour features from seed images, and another to classify seeds into categories using the extracted features. The experimental results demonstrated the correctness and validity of both the extracted features and the classification predictions. The proposed tool is easily extendable to other fields of image analysis.