Preprint Article Version 1 This version is not peer-reviewed

Application of 2D Modification of Hjorth Descriptors to Distinguish Defined Classes of Bee Pollen Images

Version 1 : Received: 8 August 2024 / Approved: 9 August 2024 / Online: 12 August 2024 (07:59:22 CEST)

How to cite: Tkacz, E.; Rujna, P.; Więcławek, W.; Lewandowski, B.; Mika, B.; Sieciński, S. Application of 2D Modification of Hjorth Descriptors to Distinguish Defined Classes of Bee Pollen Images. Preprints 2024, 2024080762. https://doi.org/10.20944/preprints202408.0762.v1 Tkacz, E.; Rujna, P.; Więcławek, W.; Lewandowski, B.; Mika, B.; Sieciński, S. Application of 2D Modification of Hjorth Descriptors to Distinguish Defined Classes of Bee Pollen Images. Preprints 2024, 2024080762. https://doi.org/10.20944/preprints202408.0762.v1

Abstract

Adulteration of food products, including honey, is a serious problem in today’s economy. Honey has become the third most counterfeited food product in the world, which requires effective authentication methods. This article presents considerations regarding the development of meteorology to test the quality of honey based on the analysis of bee pollen. The justification for conducting such analyses is the relatively high need for the authentication of honey and its derivatives. It turns out that the honey market and honey itself are the third products in the world in which undesirable, inappropriate, and quality-reducing components may appear, affecting the final quality of a product such as honey. The analyses mentioned above thus come down to issues related to the analysis and processing of images. A certain novelty of the approach to this analysis is an attempt to parameterize them using the so-called Hjorth descriptors, which have been a tool known for almost 50 years from the analysis of electroencephalographic (EEG) signals. In this paper, after an introduction to the issues related to testing honey, the issues related to the method of obtaining bee pollen images, improving their quality by applying appropriate filtration, performing normalization, and finally calculating Hjorth distributors such as: Activity, Mobility, and Complexity will be discussed. In the next stage described in this article, the authors perform a detailed statistical analysis leading to the initial construction of a simple classifier that distinguishes defined gropus of bee pollen images.

Keywords

Bee pollen analysis; Hjorth descriptors; Food product adulteration; pollen images parametrisation; food product classification

Subject

Biology and Life Sciences, Food Science and Technology

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.