Application of Pattern Recognition and Computer Vision Tools to Improve the Morphological Analysis of Microplastic Items in Biological Samples

• Published in: Toxics (Basel) Vol. 11; no. 9; p. 779
• Main Authors: Astel, Aleksander Maria, Piskuła, Paulina
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2023; MDPI
• Subjects: Algorithms; binary image; Binocular vision; Biological properties; Biological samples; Cameras; Computation; Computer vision; contour tracking; Correlation coefficient; Correlation coefficients; Deep learning; Digital cameras; Digital imaging; Fibers; Image acquisition; Image analysis; Image processing; Libraries; Machine vision; Mathematical analysis; Methods; Microplastics; Microscopy; Morphology; Object recognition (Computers); Open source software; OpenCV; Pattern recognition; Personal computers; Plastic pollution; shape descriptors; Software; Union–Find algorithm; Poland
• ISSN: 2305-6304; 2305-6304
• DOI: 10.3390/toxics11090779

Since, in many routine analytical laboratories, a stereomicroscope coupled with a digital camera is not equipped with advanced software enabling automatic detection of features of observed objects, in the present study, a procedure of feature detection using open-source software was proposed and validated. Within the framework of applying microscopic expertise coupled with image analysis, a set of digital images of microplastic (MP) items identified in organs of fish was used to determine shape descriptors (such as length, width, item area, etc.). The edge points required to compute shape characteristics were set manually in digital images acquired by the camera coupled with a binocular, and respective values were computed via the use of built-in MotiConnect software. As an alternative, a new approach consisting of digital image thresholding, binarization, the use of connected-component labeling, and the computation of shape descriptors on a pixel level via using the functions available in an OpenCV library or self-written in C++ was proposed. Overall, 74.4% of the images were suitable for thresholding without any additional pretreatment. A significant correlation was obtained between the shape descriptors computed by the software and computed using the proposed approach. The range of correlation coefficients at a very high level of significance, according to the pair of correlated measures, was higher than 0.69. The length of fibers can be satisfactorily approximated using a value of half the length of the outer perimeter (r higher than 0.75). Compactness and circularity significantly differ for particles and fibers.