Application of 2D Extension of Hjorth’s Descriptors to Distinguish Defined Groups of Bee Pollen Images

Abstract

Adulteration of food products is a serious problem in the current economy. Honey has become the third most counterfeit food product in the world and requires effective authentication methods. This article presents a new approach to the differentiation of bee pollen, which can support the development of a methodology to test honey quality based on the analysis of bee pollen. The proposed method is built on applying the Hjorth descriptors—Activity, Mobility, and Complexity—known from electroencephalography (EEG) analysis, for 2D bee pollen images. The sources for extracting the bee pollen images were the photos of honey samples, which were taken using a digital camera with a resolution of 5 megapixels connected to the tube of an optical microscope. The honey samples used were prepared according to the Polish standard PN-88/A-77626 (related to the European standard CELEX-32001L0110-PL-TXT). The effectiveness of the proposed method was positively verified for three selected groups of bee pollen—Brassica napus, Helianthus, and Phacelia—containing 35 images. Statistical analysis confirms the ability of the Hjorth descriptors to differentiate the indicated bee pollen groups. Based on the results obtained, there is a significant difference between the bee pollen groups under consideration regarding Activity p0.00001, Mobility p0.0001, and Complexity p0.00001.

Keywords

• bee pollen analysis
• Hjorth’s descriptors
• food product adulteration
• pollen image parametrization
• food product classification