Automated quantification of defective maize kernels by means of Multivariate Image Analysis

Non-destructive detection of defective maize kernels using hyperspectral imaging and convolutional neural network with attention module

Rapid, effective and non-destructive detection of the defective maize kernels is crucial for their high-quality storage in granary. Hyperspectral imaging (HSI) coupled with convolutional neural network (CNN) based on spectral and spatial attention (Spl-Spal-At) module was proposed for identifying the different types of maize kernels. The HSI data within 380-1000 nm of six classes of sprouted, heat-damaged, insect-damaged, moldy, broken and healthy kernels was collected. The CNN-Spl-At, CNN-Spal-At and CNN-Spl-Spal-At models were established based on the spectra, images and their fusion features as inputs for the recognition of different kernels. Further compared the performances of proposed models and conventional models were built by support vector machine (SVM) and extreme learning machine (ELM). The results indicated that the recognition ability of CNN with attention series models was significantly better than that of SVM and ELM models and fused features were more conducive to expressing the appearance of different kernels than single features. And the CNN-Spl-Spal-At model had an optimal recognition result with high average classification accuracy of 98.04 % and 94.56 % for the training and testing sets, respectively. The recognition results were visually presented on the surface image of kernels with different colors. The CNN-Spl-Spal-At model was built in this study could effectively detect defective maize kernels, and it also had great potential to provide the analysis approaches for the development of non-destructive testing equipment based on HSI technique for maize quality.

Recent developments of e-sensing devices coupled to data processing techniques in food quality evaluation: a critical review

A greater demand for high-quality food is being driven by the growth of economic and technological advancements. In this context, consumers are currently paying special attention to organoleptic characteristics such as smell, taste, and appearance. Motivated to mimic human senses, scientists developed electronic devices such as e-noses, e-tongues, and e-eyes, to spot signals relative to different chemical substances prevalent in food systems. To interpret the information provided by the sensors' responses, multiple chemometric approaches are used depending on the aim of the study. This review based on the Web of Science database, endeavored to scrutinize three e-sensing systems coupled to chemometric approaches for food quality evaluation. A total of 122 eligible articles pertaining to the e-nose, e-tongue and e-eye devices were selected to conduct this review. Most of the performed studies used exploratory analysis based on linear factorial methods, while classification and regression techniques came in the second position. Although their applications have been less common in food science, it is to be noted that nonlinear approaches based on artificial intelligence and machine learning deployed in a big-data context have generally yielded better results for classification and regression purposes, providing new perspectives for future studies.

Assessing Grapevine Biophysical Parameters From Unmanned Aerial Vehicles Hyperspectral Imagery

Over the last 50 years, many approaches for extracting plant key parameters from remotely sensed data have been developed, especially in the last decade with the spread of unmanned aerial vehicles (UAVs) in agriculture. Multispectral sensors are very useful for the elaboration of common vegetation indices (VIs), however, the spectral accuracy and range may not be enough. In this scenario, hyperspectral (HS) technologies are gaining particular attention thanks to the highest spectral resolution, which allows deep characterization of vegetative/soil response. Literature presents few papers encompassing UAV-based HS applications in vineyard, a challenging conditions respect to other crops due to high presence of bare soil, grass cover, shadows and high heterogeneity canopy structure with different leaf inclination. The purpose of this paper is to present the first contribution combining traditional and multivariate HS data elaboration techniques, supported by strong ground truthing of vine ecophysiological, vegetative and productive variables. Firstly the research describes the UAV image acquisition and processing workflow to generate a 50 bands HS orthomosaic of a study vineyard. Subsequently, the spectral data extracted from 60 sample vines were elaborated both investigating the relationship between traditional narrowband VIs and grapevine traits. Then, multivariate calibration models were built using a double approach based on Partial Least Square (PLS) regression and interval-PLS (iPLS), to evaluate the correlation performance between the biophysical parameters and HS imagery using the whole spectral range and a selection of more relevant bands applying a variable selection algorithm, respectively. All techniques (VIs, PLS and iPLS) provided satisfactory correlation performances for the ecophysiological (R 2 = 0.65), productive (R 2 = 0.48), and qualitative (R 2 = 0.63) grape parameters. The novelty of this work is represented by the first assessment of a UAV HS dataset with the expression of the entire vine ecosystem, from the physiological and vegetative state to grapes production and quality, using narrowband VIs and multivariate PLS regressions. A correct non-destructive estimation of key parameters in vineyard, above all physiological parameters which must be measured in a short time as they are extremely influenced by the variability of environmental conditions during the day, represents a powerful tool to support the winegrower in vineyard management.

Research advancements in optical imaging and spectroscopic techniques for nondestructive detection of mold infection and mycotoxins in cereal grains and nuts

Cereal grains and nuts are represented as the economic backbone of many developed and developing countries. Kernels of cereal grains and nuts are prone to mold infection under high relative humidity and suitable temperature conditions in the field as well as storage conditions. Health risks caused by molds and their molecular metabolite mycotoxins are, therefore, important topics to investigate. Strict regulations have been developed by international trade regulatory bodies for the detection of mold growth and mycotoxin contamination across the food chain starting from the harvest to storage and consumption. Molds and aflatoxins are not evenly distributed over the bulk of grains, thus appropriate sampling for detection and quantification is crucial. Existing reference methods for mold and mycotoxin detection are destructive in nature as well as involve skilled labor and hazardous chemicals. Also, these methods cannot be used for inline sorting of the infected kernels. Thus, analytical methods have been extensively researched to develop the one that is more practical to be used in commercial detection and sorting processes. Among various analytical techniques, optical imaging and spectroscopic techniques are attracting growers' attention for their potential of nondestructive and rapid inline identification and quantification of molds and mycotoxins in various food products. This review summarizes the recent application of rapid and nondestructive optical imaging and spectroscopic techniques, including digital color imaging, X-ray imaging, near-infrared spectroscopy, fluorescent, multispectral, and hyperspectral imaging. Advance chemometric techniques to identify very low-level mold growth and mycotoxin contamination are also discussed. Benefits, limitations, and challenges of deploying these techniques in practice are also presented in this paper.

Automatic kernel counting on maize ear using RGB images

BACKGROUND

The number of kernels per ear is one of the major agronomic yield indicators for maize. Manual assessment of kernel traits can be time consuming and laborious. Moreover, manually acquired data can be influenced by subjective bias of the observer. Existing methods for counting of kernel number are often unstable and costly. Machine vision technology allows objective extraction of features from image sensor data, offering high-throughput and low-cost advantages.

RESULTS

Here, we propose an automatic kernel recognition method which has been applied to count the kernel number based on digital colour photos of the maize ears. Images were acquired under both LED diffuse (indoors) and natural light (outdoor) conditions. Field trials were carried out at two sites in China using 8 maize varieties. This method comprises five steps: (1) a Gaussian Pyramid for image compression to improve the processing efficiency, (2) separating the maize fruit from the background by Mean Shift Filtering algorithm, (3) a Colour Deconvolution (CD) algorithm to enhance the kernel edges, (4) segmentation of kernel zones using a local adaptive threshold, (5) an improved Find-Local-Maxima to recognize the local grayscale peaks and determine the maize kernel number within the image. The results showed good agreement (> 93%) in terms of accuracy and precision between ground truth (manual counting) and the image-based counting.

CONCLUSIONS

The proposed algorithm has robust and superior performance in maize ear kernel counting under various illumination conditions. In addition, the approach is highly-efficient and low-cost. The performance of this method makes it applicable and satisfactory for real-world breeding programs.