A Method for Rapid Identification of Rice Origin by Hyperspectral Imaging Technology

Abstract

The potential of hyperspectral imaging system was evaluated for the rapid identification of rice origin. 240 samples from four different regions of China were imaged by a hyperspectral imaging system. Hyperspectral images were studied from the three principal aspects (spectral, morphological and texture features). Support vector machine was used for developing the identification models. Seven models based on spectral, morphological, texture, combined spectral and morphological, combined spectral and texture, combined morphological and texture and combined spectral, morphological and texture features were developed for seeking the optimal feature combination. Nine important wavelengths were determined by principal component analysis. The results showed that the highest accuracy (91.67%) was obtained from combined spectral, morphological and texture features. This study demonstrated that hyperspectral imaging could provide a rapid identification of rice origin and the method of feature combination could be very helpful to improve the performance of identification models. Practical Applications The price and quality of rice mainly depends on its geographical origin in the food market. Traditional methods for identification of rice origin mainly focus on the appearance of rice and depend on the feelings of professionals, which are tedious, time‐consuming, expensive and greatly influenced by subjective factors. Therefore, the results in our paper can provide a foundational basis to develop a real‐time inspection system for the rapid, precise and non‐destructive identification of rice origin.

Multispectral Imaging for Plant Food Quality Analysis and Visualization

“…The discrimination accuracies of variety, chalkiness degree, and shape features of rice kernels from different regions reached over 89.91% based on the BPNN model with 7 optimal spectral variables (Wang and others ). The SVM model together with wavelength selection method of PCA achieved the highest accuracy (91.67%) for the rapid identification of rice origin using multispectral imaging (Sun and others ). For identification of tomato varieties regarding genetic purity, the stepwise PLSDA model displayed an overall classification accuracy of more than 86% (Shrestha and others ).…”

Visual detection of sprouting in potatoes using ensemble‐based classifier

“…Qiu, Wang, Tang, and Du () used extreme learning machine, random forest, and support vector machine (SVM) for qualitative classification and quantitative prediction of mandarin. According to the spectral, morphological, and texture features, Sun, Lu, Mao, Jin, and Wu () used hyperspectral imaging technology and SVM for rapid identification of rice origin. Using artificial neural networks (ANN) as the color space transformation model, Oliveira, Leme, Barbosa, and Rodarte () applied Bayes classifier to classify the coffee beans into four groups: whitish, cane green, green, and bluish‐green.…”

“…Qiu, Wang, Tang, and Du (2015) used extreme learning machine, random forest, and support vector machine (SVM) for qualitative classification and quantitative prediction of mandarin. According to the spectral, morphological, and texture features, Sun, Lu, Mao, Jin, and Wu (2017) used hyperspectral imaging technology and SVM for rapid identification of rice origin.…”

A Short Update on the Advantages, Applications and Limitations of Hyperspectral and Chemical Imaging in Food Authentication

“…The authors of this study analysed rice samples (n = 240) from four geographic regions in China using a HSI system [15]. The highest accuracy in terms of classification (>91%) was reported using a combination of spectral, morphological, and texture properties that were measured using instrumental methods [15].…”

“…Hyperspectral imaging has also been evaluated for the prediction of the origin of rice [15]. The authors of this study analysed rice samples (n = 240) from four geographic regions in China using a HSI system [15].…”