AI-Driven Forensic Palynology Advancements in Investigative Technology

Abstract

Forensic palynology applies pollen grains and spores as trace evidence in scenes of crime. Identi𿿿cation by hand is labor intensive and subject to observer bias anderror. Major objective is to highlight a conceptual model for automating the analysis of pollen grains with imaging and arti𿿿cial intelligence (AI). Alab-basedsimulationstudy created from online available datasets and microscopic images of pollen grains. This study presents a conceptual model for automating pollen analysis through imaging and arti𿿿cial intelligence (AI). A lab-based simulationutilizedpublicly available microscopy datasets of 25 pollen species to develop a theoretical framework. The morphology of pollen grains and spores were assessed. The workÁow that was proposed consisted of: data acquisition, image pre-processing, image analysis, and dataset generation; and classi𿿿ed pollen grains andsporesusing arti𿿿cial intelligence models (Arti𿿿cial Neural Networks, Convolutional Neural Networks (CNN) and support vector machine (SVM). AI and automation present a signi𿿿cant number of possibilities to enhance the effectiveness andspeedof forensic palynology. There is a requirement for a properly curated dataset in the development for effective automated tools.