Machine vision-based detection of key traits in shiitake mushroom caps.

Abstract

This study puts forward a machine vision-based prediction method to solve the problem regarding the measurement of traits in shiitake mushroom caps during the shiitake mushroom breeding process. It enables precise phenotyping through accurate image acquisition and analysis. In practical applications, this method improves the breeding process by rapidly and non-invasively assessing key traits such as the size and color of shiitake mushroom caps, which helps in efficiently screening strains and reducing human errors. Firstly, an edge detection model was established. This model is called KL-Dexined. It achieved an per-image best threshold (OIS) rate of 93.5%. Also, it reached an Optimal Dynamic Stabilization (ODS) rate of 96.3%. Moreover, its Average Precision (AP) was 97.1%. Secondly, the edge information detected by KL-Dexined was mapped onto the original image of shiitake mushroom caps, and using the OpenCV model,11 phenotypic key features including shiitake mushroom caps area, perimeter, and external rectangular length were obtained. Experimental results demonstrated that the R² between predicted values and true values was 0.97 with an RMSE as low as 0.049. After conducting correlation analysis between phenotypic features and shiitake mushroom caps weight, four most correlated phenotypic features were identified: Area, Perimeter, External rectangular width, and Long axis; they were divided into four groups based on their correlation rankings. Finally,M3 group using GWO_SVM algorithm achieved optimal performance among six mainstream machine learning models tested with an R²value of 0.97 and RMSE only at 0.038 when comparing predicted values with true values. Hence, this study provided guidance for predicting key traits in shiitake mushroom caps.