Identification of wheat kernels by fusion of RGB, SWIR, and VNIR samples

Abstract

Background The sustainable management of agricultural resources requires the integration of cutting‐edge science with the observation and identification of crops. This assists experts to make correct decisions. The aim of this study is to assess the robustness of a commonly used deep learning tool, VGG16, in improving the categorization of wheat kernels. Two fusion methodologies were considered simultaneously. We performed experiments on visible light (RGB), short wave infrared (SWIR), and visible‐near infrared (VNIR) datasets, including 40 classes, with 200 samples in each class, giving 8000 samples in total. Results After making simulations with 6400 training and 1600 testing samples, we achieved excellent performance scores, with 98.19% and 100% accuracy rates, respectively. Conclusion The wheat identification system developed here serves as an effective identification framework and supports the view that deep learning tools can adequately discriminate between different types of wheat kernels. The proposed automated system would be useful for improving economic growth and in reducing the labor force, leading to greater efficiency and higher productivity in the wheat industry. © 2019 Society of Chemical Industry

Bread and durum wheat classification using wavelet based image fusion

“…LBP, proposed by Ojala et al ., 39 is a method of texture analysis consisting of ordered binary comparisons of a central pixel with its neighboring pixel values. A detailed explanation of both methods can be accessed from the literature 22, 27 . In this study, five features, including contrast, correlation, energy, homogeneity and entropy, are extracted with GLCM from the images of each grain of wheat.…”

“…This study examines the fusion of images of different structures unlike other studies. A study on wheat fusion classification was done by Özkan et al 27 Özkan et al, 27 classified the wheat types using the widely used Visual Geometry Group-16 (VGG16) deep learning (DL) architecture. Two hundred sample frames were taken from each of 40 wheat types with RGB, short-wave infrared (SWIR) and visible and near-infrared (VNIR) imaging techniques, that is, 8000 images were used in that study.…”

“…A detailed explanation of both methods can be accessed from the literature. 22,27 In this study, five features, including contrast, correlation, energy, homogeneity and entropy, are extracted with GLCM from the images of each grain of wheat. As a result of the LBP method, eight features such as LBP 1 , LBP 2 , …, LBP 8 are extracted.…”

“…This study examines the fusion of images of different structures unlike other studies. A study on wheat fusion classification was done by Özkan et al 27 . Özkan et al ., 27 classified the wheat types using the widely used Visual Geometry Group‐16 (VGG16) deep learning (DL) architecture.…”

Wheat Kernel Variety Identification Based on a Large Near-Infrared Spectral Dataset and a Novel Deep Learning-Based Feature Selection Method

“…Different deep architectures consisting of nonlinear processing units have been introduced for seed variety identification based on spectral datasets. Ozkan et al (2019) designed a convolutional neural network (CNN) for variety discrimination of wheat grain. Spectral images of the grains were collected by multiple spectroscopic sensors to make a dataset.…”