Feasibility of nondestructive detection of apple crispness based on spectroscopy and machine vision

Abstract

Texture is an important attribute affecting apple quality and consumer preferences.In general, apple texture is evaluated by such parameters as crispness and hardness.To explore the feasibility of nondestructive detection of apple crispness based on spectroscopy and machine vision, a calibration model based on optical fiber spectroscopy (in the range of 500-1,000 nm) was developed using the partial least squares. A compensation model based on appearance images was established to improve the prediction performance, and a quantitative prediction model based on the fusion of spectra and appearance images was subsequently obtained. The results showed that the determination coefficient of prediction (R 2 p ) and root mean square error (RMSE) of prediction (RMSEP) of the calibration model were 0.8921 and 0.1226 N, respectively. The determination coefficients (R 2 ) of the compensation model for positive derivation and negative derivation were 0.9310 and 0.9051, respectively, with a RMSE of 0.0515 N and 0.0420 N, respectively. The mean value and standard deviation that occurred in relative errors both decreased from 8.52 to 6.44% and 6.22 to 5.30% before and after positive derivation compensation and decreased from 8.29 to 5.55% and 5.62 to 4.49% before and after negative derivation compensation using the appearance images. This result indicated that the prediction of apple crispness was more accurate and reliable after the fusion of spectra and appearance images.Therefore, it is feasible to nondestructively detect apple crispness based on spectroscopy and machine vision. Practical ApplicationsThis study provides a method for nondestructively and accurately detecting apple crispness via spectroscopy and machine vision. According to the crispness of apples, enterprises can not only sell apples to different consumer groups, but also distribute apples in different levels to improve their benefits.

A quality grade classification method for fresh tea leaves based on an improved YOLOv8x-SPPCSPC-CBAM model

“…Additionally, the grading of high-quality tea leaves was further enhanced by employing an air sorter following the initial screening. Chen et al 5 addressed quality control during the air sorting process of tea leaves. The research was conducted on the efficiency and quality changes of tea leaf sorting at different wind speeds, ultimately determining the optimal wind speed.…”

Bruise detection and classification in jujube using thermal imaging and DenseNet

“…However, after a product quality inspector works for a long time, the efficiency will rapidly decrease, which may lead to incorrect and inconsistent grading results. In addition to visual assessment for the detection of fruit bruises, X-ray technique, magnetic resonance imaging (MRI), timeresolved spectroscopy, spatially resolved spectroscopy, electronic nose, structured-illumination reflectance imaging and Vis-NIR spectroscopy have great potential in assessing fruit bruising (ElMasry, Wang, Vigneault, Qiao, & ElSayed, 2008;Herremans et al, 2014;Kafle, Khot, Jarolmasjed, Yongsheng, & Lewis, 2016;Liu, Zhang, Ni, & Hu, 2021;Lu, Cen, Huang, & Ariana, 2010;Lu & Lu, 2017a;Lu & Lu, 2017b;Valero et al, 2005;Wang, He, Zhang, & Li, 2021;Ying, Liu, & Hui, 2015;Zhang et al, 2018). However, these methods are expensive and complicated for fruit detection, and the speed and visibility of these methods are also limited that cause significant difficulties in the online classification of sample datasets (Ghosh, Rana, Nayak, & Pradhan, 2016;Qin & Lu, 2008;Zeng, Miao, Ubaid, Gao, & Zhuang, 2020).…”

“…A simple, convenient, and fast thermal imaging system is of enormous significance for detecting fruit bruises. In previous studies, this classification was mostly performed using machine vision algorithms (Liu et al, 2021;Xu et al, 2021). At present, many algorithms have been used for the classification of bruises in fruits, for example, linear discriminant analysis, decision trees, Principal component analysis, Bayesian classifiers, support vector machines, and artificial neural networks (Baranowski, Mazurek, & Pastuszka-Woźniak, 2013;Boulent, Foucher, Theau, & St-Charles, 2019;ElMasry et al, 2008;Singh, Garg, & Iyengar, 2021;Wang et al, 2011;Zheng et al, 2019).…”

Grading detection of “Red Fuji” apple in Luochuan based on machine vision and near-infrared spectroscopy

“…Additionally, in terms of injury-free detection technology for agricultural products, spectroscopy technology has undergone rapid development [7][8][9]. Zhao Miao et al developed a robotic system for the automatic detection and classification of internal quality attributes of apples using near-infrared spectroscopy [10]; Liu Penghui et al used machine vision and spectroscopy for the non-destructive detection of apple crispness with accurate and reliable results [11]. Tan Wenyi et al used hyperspectral imaging to propose an accurate algorithm for apple abrasion identification, which provided a new method for non-destructive detection [12].…”