A Novel Hyperspectral Method to Detect Moldy Core in Apple Fruits

Abstract

An innovative low-cost device based on hyperspectral spectroscopy in the near infrared (NIR) spectral region is proposed for the non-invasive detection of moldy core (MC) in apples. The system, based on light collection by an integrating sphere, was tested on 70 apples cultivar (cv) Golden Delicious infected by Alternaria alternata, one of the main pathogens responsible for MC disease. Apples were sampled in vertical and horizontal positions during five measurement rounds in 13 days’ time, and 700 spectral signatures were collected. Spectral correlation together with transmittance temporal patterns and ANOVA showed that the spectral region from 863.38 to 877.69 nm was most linked to MC presence. Then, two binary classification models based on Artificial Neural Network Pattern Recognition (ANN-AP) and Bagging Classifier (BC) with decision trees were developed, revealing a better detection capability by ANN-AP, especially in the early stage of infection, where the predictive accuracy was 100% at round 1 and 97.15% at round 2. In subsequent rounds, the classification results were similar in ANN-AP and BC models. The system proposed surpassed previous MC detection methods, needing only one measurement per fruit, while further research is needed to extend it to different cultivars or fruits.

Research Progress of Rapid Non-Destructive Detection Technology in the Field of Apple Mold Heart Disease

“…They found that the artificial neural network pattern recognition (ANN-AP) model combined with the infection growth rate showed a predictive accuracy of 100% at round 1 and 97.15% at round 2 for diseased apples. The research results indicate that the model exhibits consistency in infection rate and development on the test set, thus having greater potential for industrial applicability [33]. Tian et al designed an online NIR transmission spectroscopy system for detecting apple mold heart disease.…”

Advance in application of rapid non-destructive testing technology in the detection of apple mold heart disease

“…Andrea et al designed and manufactured a low-cost innovative device for early detection based on near infrared spectroscopy technology. After multiple rounds of detection, it was found that the ANN-AP model combined with the infection growth rate showed a better correlation, with the highest accuracy and a prediction accuracy of 97% [18] . Tian et al designed and assembled an online spectral measurement system for apple mold heart disease using near-infrared transmission spectrum technology.…”

Phytoplasma-Induced Leaf Reddening as a Monitoring Symptom of Apple Proliferation Disease with Regard to the Development of Remote Sensing Strategies

“…AP-induced reflectance changes due to leaf reddening can be detected using RGB cameras, as they are visible to the human eye. Multispectral and hyperspectral imaging may yield potentials for early detection as well as improved discrimination from other stresses [20][21][22]. However, focusing on a single symptom requires prior investigation of its significance.…”