Search

The quality of fresh apple fruits is a major concern for consumers and manufacturers. Classification of these fruits according to their ripening stage is one of the most decisive factors in determining their quality. In this regard, the aim of this work is to develop a new method for non-destructive classification of the ripening state of Fuji apples using hyperspectral information in the visible and near-infrared (Vis/NIR) regions. Spectra of 172 apple samples in the range from 450 to 1000 nm were studied, which were selected from four different ripening stages. A convolutional neural network (CNN) model was proposed to perform the classification of the samples. The proposed method was compared with three alternative methods based on artificial neural networks (ANN), support vector machines (SVM), and k-nearest neighbors (KNN). The results revealed that the CNN method outperformed the alternative methods, achieving a correct classification rate (CCR) of 96.5%, compared with an average of 89.5%, 95.93%, and 91.68% for ANN, SVM, and KNN, respectively. These results will help in the development of a new device for fast and accurate estimation of the quality of apples. [ABSTRACT FROM AUTHOR]

Shadow, a natural phenomenon resulting from the absence of light, plays a pivotal role in agriculture, particularly in processes such as photosynthesis in plants. Despite the availability of generic shadow datasets, many suffer from annotation errors and lack detailed representations of agricultural shadows with possible human activity inside, excluding those derived from satellite or drone views. In this paper, we present an evaluation of a synthetically generated top-down shadow segmentation dataset characterized by photorealistic rendering and accurate shadow masks. We aim to determine its efficacy compared to real-world datasets and assess how factors such as annotation quality and image domain influence neural network model training. To establish a baseline, we trained numerous baseline architectures and subsequently explored transfer learning using various freely available shadow datasets. We further evaluated the out-of-domain performance compared to the training set of other shadow datasets. Our findings suggest that AgroSegNet demonstrates competitive performance and is effective for transfer learning, particularly in domains similar to agriculture. [ABSTRACT FROM AUTHOR]

Achieving a high level of classification accuracy in medical datasets is a capital need for researchers to provide effective decision systems to assist doctors in work. In many domains of artificial intelligence, ensemble classification methods are able to improve the performance of single classifiers. This paper reports the state of the art of ensemble classification methods in lung cancer detection. We have performed a systematic mapping study to identify the most interesting papers concerning this topic. A total of 65 papers published between 2000 and 2018 were selected after an automatic search in four digital libraries and a careful selection process. As a result, it was observed that diagnosis was the task most commonly studied; homogeneous ensembles and decision trees were the most frequently adopted for constructing ensembles; and the majority voting rule was the predominant combination rule. Few studies considered the parameter tuning of the techniques used. These findings open several perspectives for researchers to enhance lung cancer research by addressing the identified gaps, such as investigating different classification methods, proposing other heterogeneous ensemble methods, and using new combination rules. [ABSTRACT FROM AUTHOR]

Climbing plants, such as common beans (Phaseolus vulgaris L.), exhibit complex motion patterns that have long captivated researchers. In this study, we introduce a stereo vision machine system for the in-depth analysis of the movement of climbing plants, using image processing and computer vision. Our approach involves two synchronized cameras, one lateral to the plant and the other overhead, enabling the simultaneous 2D position tracking of the plant tip. These data are then leveraged to reconstruct the 3D position of the tip. Furthermore, we investigate the impact of external factors, particularly the presence of support structures, on plant movement dynamics. The proposed method is able to extract the position of the tip in 86–98% of cases, achieving an average reprojection error below 4 px, which means an approximate error in the 3D localization of about 0.5 cm. Our method makes it possible to analyze how the plant nutation responds to its environment, offering insights into the interplay between climbing plants and their surroundings. [ABSTRACT FROM AUTHOR]

Recent advances in hyperspectral imaging (HSI) have demonstrated its ability to detect defects in fruit that may not be visible in RGB images. HSIs can be considered 3D images containing two spatial dimensions and one spectral dimension. Therefore, the first question that arises is how to process this type of information, either using 2D or 3D models. In this study, HSI in the 550–900 nm spectral range was used to detect bruising in oranges. Sixty samples of Thompson oranges were subjected to a mechanical bruising process, and HSIs were taken at different time intervals: before bruising, and 8 and 16 h after bruising. The samples were then classified using two convolutional neural network (CNN) models, a shallow 7‐layer network (CNN‐7) and a deep 18‐layer network (CNN‐18). In addition, two different input processing approaches are used: using 2D information from each band, and using the full 3D data from each HSI. The 3D models were the most accurate, with 94% correct classification for 3D‐CNN‐18, compared to 90% for 3D‐CNN‐7, and less than 83% for the 2D models. Our study suggests that 3D HSI may be a more effective technique for detecting fruit bruising, allowing the development of a fast, accurate, and nondestructive method for fruit sorting. Practical Application: Orange bruises can reduce the market value of food, which is why the food processing industry needs to carry out quality inspections. An effective way to perform this inspection is by using hyperspectral images that can be processed with 2D or 3D models, either with deep or shallow neural networks. The results of the comparison performed in this work can be useful for the development of more accurate and efficient bruise detection methods for fruit inspection. [ABSTRACT FROM AUTHOR]

Tomato is an agricultural product of great economic importance because it is one of the most consumed vegetables in the world. The most crucial chemical element for the growth and development of tomato is nitrogen (N). However, incorrect nitrogen usage can alter the quality of tomato fruit, rendering it undesirable to customers. Therefore, the goal of the current study is to investigate the early detection of excess nitrogen application in the leaves of the Royal tomato variety using a non-destructive hyperspectral imaging system. Hyperspectral information in the leaf images at different wavelengths of 400–1100 nm was studied; they were taken from different treatments with normal nitrogen application (A), and at the first (B), second (C) and third (D) day after the application of excess nitrogen. We investigated the performance of nine machine learning classifiers, including two classic supervised classifiers, i.e., linear discriminant analysis (LDA) and support vector machines (SVMs), three hybrid artificial neural network classifiers, namely, hybrid artificial neural networks and independent component analysis (ANN-ICA), harmony search (ANN-HS) and bees algorithm (ANN-BA) and four classifiers based on deep learning algorithms by convolutional neural networks (CNNs). The results showed that the best classifier was a CNN method, with a correct classification rate (CCR) of 91.6%, compared with an average of 85.5%, 68.5%, 90.8%, 88.8% and 89.2% for LDA, SVM, ANN-ICA, ANN-HS and ANN-BA, respectively. This shows that modern CNN methods should be preferred for spectral analysis over other classical techniques. These CNN architectures can be used in remote sensing for the precise detection of the excessive use of nitrogen fertilizers in large extensions. [ABSTRACT FROM AUTHOR]

The race for automation has reached farms and agricultural fields. Many of these facilities use the Internet of Things technologies to automate processes and increase productivity. Besides, Machine Learning and Deep Learning allow performing continuous decision making based on data analysis. In this work, we fill a gap in the literature and present a novel architecture based on IoT and Machine Learning / Deep Learning technologies for the continuous assessment of agricultural crop quality. This architecture is divided into three layers that work together to gather, process, and analyze data from different sources to evaluate crop quality. In the experiments, the proposed approach based on data aggregation from different sources reaches a lower percentage error than considering only one source. In particular, the percentage error achieved by our approach in the test dataset was 6.59, while the percentage error achieved exclusively using data from sensors was 6.71. [ABSTRACT FROM AUTHOR]

Shadow detection is a challenging problem in computer vision due to the high variability in lighting conditions, object shapes, and scene layouts. Despite the positive results achieved by some existing technologies, the problem becomes particularly challenging with complex and heterogeneous images where shadow-casting objects coexist and shadows can have different depths, scales, and morphologies. As a result, more advanced and accurate solutions are still needed to deal with this type of complexities. To address these challenges, this paper proposes a novel deep learning model, called the Cross-Attentional Dual Decoder Network (CADDN), to improve shadow detection by using fine-grained image reconstruction features. Unlike other existing methods, the CADDN uses an innovative encoder-decoder architecture with two decoder segments that work together to reconstruct the input images and their corresponding shadow masks. In this way, the features used to reconstruct the original input image can be used to support the shadow detection process itself. The proposed model also incorporates a cross-attention mechanism to weight the most relevant features for detecting shadows and skip connections with noise to improve the quality of the transferred features. The experimental results, including several benchmark image datasets and state-of-the-art detection methods, demonstrate the suitability of the presented approach for detecting shadows in computer vision applications. [Display omitted] [ABSTRACT FROM AUTHOR]

The estimation of the ripening state in orchards helps improve post-harvest processes. Picking fruits based on their stage of maturity can reduce the cost of storage and increase market outcomes. Moreover, aerial images and the estimated ripeness can be used as indicators for detecting water stress and determining the water applied during irrigation. Additionally, they can also be related to the crop coefficient (Kc) of seasonal water needs. The purpose of this research is to develop a new computer vision algorithm to detect the existing fruits in aerial images of an apple cultivar (of Red Delicious variety) and estimate their ripeness stage among four possible classes: unripe, half-ripe, ripe, and overripe. The proposed method is based on a combination of the most effective color features and a classifier based on artificial neural networks optimized with genetic algorithms. The obtained results indicate an average classification accuracy of 97.88%, over a dataset of 8390 images and 27,687 apples, and values of the area under the ROC (receiver operating characteristic) curve near or above 0.99 for all classes. We believe this is a remarkable performance that allows a proper non-intrusive estimation of ripening that will help to improve harvesting strategies. [ABSTRACT FROM AUTHOR]

In recent years, farmers have often mistakenly resorted to overuse of chemical fertilizers to increase crop yield. However, excessive consumption of fertilizers might lead to severe food poisoning. If nutritional deficiencies are detected early, it can help farmers to design better fertigation practices before the problem becomes unsolvable. The aim of this study is to predict the amount of nitrogen (N) content (mg ​l − 1) in cucumber (Cucumis sativus L., var. Super Arshiya-F1) plant leaves using hyperspectral imaging (HSI) techniques and three different regression methods: a hybrid artificial neural networks-particle swarm optimization (ANN-PSO); partial least squares regression (PLSR); and unidimensional deep learning convolutional neural networks (CNN). Cucumber plant seeds were planted in 20 different pots. After growing the plants, pots were categorized and three levels of nitrogen overdose were applied to each category: 30%, 60% and 90% excesses, called N 30% , N 60% , N 90% , respectively. HSI images of plant leaves were captured before and after the application of nitrogen excess. A prediction regression model was developed for each individual category. Results showed that mean regression coefficients (R) for ANN-PSO were inside 0.937–0.965, PLSR 0.975–0.997, and CNN 0.965–0.985 ranges, test set. We conclude that regression models have a remarkable ability to accurately predict the amount of nitrogen content in cucumber plants from hyperspectral leaf images in a non-destructive way, being PLSR slightly ahead of CNN and ANN-PSO methods. • Automatic accurate machine learning regression system estimation nitrogen content in cucumber plant leaves from HSI imaging. • System provides fixed optimal spectra wavelength values optimized over each nitrogen-excess content category. • Numerical simulation results include: linear regression scatter plots, regression and determination coefficient boxplots. • Results also include the true versus mean estimated nitrogen content values. • Given its simplicity and accuracy it could potentially be used as a portable device under real food industry conditions. [ABSTRACT FROM AUTHOR]

To achieve healthy and optimal yields of agricultural products, the principles of nutrition must be observed and appropriate fertilizers must be applied. Nutritional deficiencies or overabundance reduce the quality and yield of the products. Thus, their early detection prevents physiological disorders and associated diseases. Most research efforts have focused on spectroscopy, which extracts only spectral data from a single point of the product. The present study aims to detect early excess nitrogen in cucumber plants by using a new hyperspectral imaging technique based on a hybrid of artificial neural networks and the imperialist competitive algorithm (ANN-ICA), which can provide spectral and spatial information on the leaves at the same time. First, cucumber seeds were planted in 18 pots. The same inputs were applied to all the pots until the plants grew; after that, 30% excess nitrogen was applied to nine pots with irrigation water, while it remained constant in the other nine pots. Each day, six leaves were collected from each pot, and their images were captured using a hyperspectral camera (in the range of 400–1100 nm). The wavelengths of 715, 783 and 821 nm were determined as the most effective for early detection of excess nitrogen using a hybrid of artificial neural networks and the artificial bee colony algorithm (ANN-ABC). The parameter of days of treatment was classified using ANN-ICA. The performance of the classifier was evaluated using different criteria, namely recall, accuracy, specificity, precision and the F-measure. The results indicate that the differences between different days were statistically significant. This means that the hyperspectral imaging technique was able to detect plants with excess nitrogen in the near-infrared range (NIR), with a correct classification rate of 96.11%. [ABSTRACT FROM AUTHOR]

• A new non-destructive ripeness estimation method for Fuji apples is presented. • Ensemble classifiers combined with the majority rule are applied on spectral data. • Narrow spectral bands prove to be superior to full visible/near-infrared and color. • The obtained classification accuracy is 99.37% for the 465–485 nm band. Non-destructive determination of the different stages of fruit ripening has important advantages over traditional methods, such as selective robotic harvesting or adapting fertilization operations depending on the ripening stage. In this regard, the purpose of the present study was to investigate the non-destructive estimation of the ripening stages of Fuji apples combining different classifiers with the majority voting (MV) method. This process is based on five constituent classifiers, including hybrids of artificial neural network (ANN) classifiers adjusted with the genetic algorithm, the particle swarm optimization algorithm and the firefly algorithm, and classifiers based on support vector machines, and the k-nearest neighbor algorithm. The input of the MV classifiers consists of four alternatives: (1) color data extracted from the second channel of L*a*b* color space, and the hue angle in L*a*b*; and multispectral data including wavelengths ranging: (2) from 465 to 485 nm; (3) from 675 to 700 nm; and (4) from 870 to 890 nm. The first two ranges are in the visible spectrum, while the second is within the near-infrared. To evaluate the reliability of the MV method, the classification procedure was repeated 1000 times with different seeds. In order to assess the obtained performance, the proposed method has been compared with an alternative technique based on an ANN classifier, in this case using all the spectral data in the range from 450 to 1000 nm, and with the hyperparameters adjusted by a grid search. The results indicate that the correct classification rate of the MV method using color data, and using spectral data from 465 to 485 nm, 675 to 700 nm, and 870 to 890 nm were 95.12%, 99.37%, 97.56% and 97.80% respectively, while the correct classification rate of the ANN method including all the spectral data from 450 to 1000 nm reached an average classification of 92.12%. Thus, the optimal selection is the MV method using spectral information from 465 to 485 nm, which is able to achieve a very accurate result, feasible to be used in practical applications. [ABSTRACT FROM AUTHOR]

Non-destructive estimation of the constituent properties of fruits and vegetables has led to a dramatic change in the agriculture and food industry, allowing accurate and efficient sorting of the products based on their internal properties. Therefore, the present study utilized visible (VIS) and near-infrared (NIR) spectroscopy data in the range from 200 to 1100 nm for the estimation of several properties of Red Delicious apples, namely Brix minus acid (BrimA), firmness, acidity and starch content, using a hybrid of Artificial Neural Networks and Artificial Bee Colony (ANN–ABC) algorithm. Furthermore, the hybrid Artificial Neural Network–Particle Swarm Optimization (ANN–PSO) algorithm was utilized to select the most effective properties to estimate these characteristics. The results indicated that there are different peaks within this spectral range, and the spectral range for each peak gives different results. To ensure the stability of the proposed method, 1000 replications were performed for each estimate. The highest coefficients of determination, R2, for estimating the studied properties among the 1000 replicates were 0.898 for BrimA, 0.8 for firmness, 0.825 for acidity and 0.973 for starch content. The selection of the most effective wavelengths for estimating the properties produced five effective wavelengths for BrimA, nine for firmness, seven for acidity and five for starch content. In this case, the best R2 of the hybrid ANN–ABC among the 1000 iterations were 0.828, 0.738, 0.9 and 0.923, respectively. [ABSTRACT FROM AUTHOR]

Color segmentation is one of the most thoroughly studied problems in agricultural applications of remote image capture systems, since it is the key step in several different tasks, such as crop harvesting, site specific spraying, and targeted disease control under natural light. This paper studies and compares five methods to segment plum fruit images under ambient conditions at 12 different light intensities, and an ensemble method combining them. In these methods, several color features in different color spaces are first extracted for each pixel, and then the most effective features are selected using a hybrid approach of artificial neural networks and the cultural algorithm (ANN-CA). The features selected among the 38 defined channels were the b* channel of L*a*b*, and the color purity index, C*, from L*C*h. Next, fruit/background segmentation is performed using five classifiers: artificial neural network-imperialist competitive algorithm (ANN-ICA); hybrid artificial neural network-harmony search (ANN-HS); support vector machines (SVM); k nearest neighbors (kNN); and linear discriminant analysis (LDA). In the ensemble method, the final class for each pixel is determined using the majority voting method. The experiments showed that the correct classification rate for the majority voting method excluding LDA was 98.59%, outperforming the results of the constituent methods. [ABSTRACT FROM AUTHOR]

There are about 90 different varieties of chickpeas around the world. In Iran, where this study takes place, there are five species that are the most popular (Adel, Arman, Azad, Bevanij and Hashem), with different properties and prices. However, distinguishing them manually is difficult because they have very similar morphological characteristics. In this research, two different computer vision methods for the classification of the variety of chickpeas are proposed and compared. The images were captured with an industrial camera in Kermanshah, Iran. The first method is based on color and texture features extraction, followed by a selection of the most effective features, and classification with a hybrid of artificial neural networks and particle swarm optimization (ANN-PSO). The second method is not based on an explicit extraction of features; instead, image patches (RGB pixel values) are directly used as input for a three-layered backpropagation ANN. The first method achieved a correct classification rate (CCR) of 97.0%, while the second approach achieved a CCR of 99.3%. These results prove that visual classification of fruit varieties in agriculture can be done in a very precise way using a suitable method. Although both techniques are feasible, the second method is generic and more easily applicable to other types of crops, since it is not based on a set of given features. [ABSTRACT FROM AUTHOR]