Identifying Irregular Potatoes Using Hausdorff Distance and Intersection over Union.

Abstract

Further processing and the added value of potatoes are limited by irregular potatoes. An ellipse-fitting-based Hausdorff distance and intersection over union (IoU) method for identifying irregular potatoes is proposed to solve the problem. First, the acquired potato image is resized, translated, segmented, and filtered to obtain the potato contour information. Secondly, a least-squares fitting method fits the extracted contour to an ellipse. Then, the similarity between the irregular potato contour and the fitted ellipse is characterized using the perimeter ratio, area ratio, Hausdorff distance, and IoU. Next, the characterization ability of the four features is analyzed, and an identification standard of irregular potatoes is established. Finally, we discuss the algorithm's shortcomings in this paper and draw the advantages of the algorithm by comparison. The experimental results showed that the characterization ability of perimeter ratio and area ratio was inferior to that of Hausdorff distance and IoU, and using Hausdorff distance and IoU as feature parameters can effectively identify irregular potatoes. Using Hausdorff distance separately as a feature parameter, the algorithm achieved excellent performance, with precision, recall, and F1 scores reaching 0.9423, 0.98, and 0.9608, respectively. Using IoU separately as a feature parameter, the algorithm achieved a higher overall recognition rate, with precision, recall, and F1 scores of 1, 0.96, and 0.9796, respectively. Compared with existing studies, the proposed algorithm identifies irregular potatoes using only one feature, avoiding the complexity of high-dimensional features and significantly reducing the computing effort. Moreover, simple threshold segmentation does not require data training and saves algorithm execution time.

Plant phenotyping relevance

ジャガイモ画像から輪郭形状を抽出し、楕円適合、Hausdorff距離、IoUで不整形という器官形態を判定する画像解析手法が研究の中心であり、性能評価も実施している。

Code and data availability

The paper describes a potato image dataset (273 potatoes) and an ellipse-fitting/Hausdorff/IoU algorithm, but the Data Availability Statement explicitly states data are not publicly available. No author code, dataset, or model deposit is mentioned. The allowed URLs are only the license, a news article, and a genericpot

No evidence-backed public reproduction asset is currently recorded.