Methodology and Results of the Study of Seed Potato Tuber Parameters Using Digital Tools

Abstract

Abstract The article presents a methodology for the quantitative assessment of seed potato tuber and mini-tuber parameters, comparing traditional manual measurements with an automated digital method using a machine vision system based on OpenCV in Python. Five major Kazakh potato varieties—Astana, Alliance, Janaysan, Narly, and Eden—were analyzed. Each tuber’s mass and linear dimensions (length, width, thickness) were measured manually and digitally. The automated setup uses two cameras to capture images from perpendicular planes, allowing calculation of mass, dimensions, area, and perimeter from images. An algorithm was developed to convert image data from pixels to millimeters and ensure accurate physical measurements. Results showed close agreement between manual and digital methods, with a relative error not exceeding 1.6% for mass and 3.0% for dimensions. Shape descriptors such as index and form coefficient were also calculated. Regression models for mass prediction were developed, offering high accuracy and potential for refinement. The digital method increased measurement productivity by seven times compared to manual approaches. The findings and regression equations will contribute to the development of machine learning algorithms for automated varietal classification of potato tubers based on their physical traits.

Code and data availability

The article describes a machine-vision methodology for measuring potato tuber parameters, but contains no data availability statement, no public dataset or image deposit, and no author code release. The program is described as developed in Python/OpenCV, but no repository, URL, or availability language for it appears.

No evidence-backed public reproduction asset is currently recorded.