Rice Classification Research Articles

Fusion of machine learning and explainable AI for enhanced rice classification: a case study on Cammeo and Osmancik species

Fusion of machine learning and explainable AI for enhanced rice classification: a case study on Cammeo and Osmancik species

Mapping Rice Paddy Areas in Nueva Ecija Using Temporal Sentinel -1 SAR Imagery

Abstract. Remote Sensing is proven to be helpful in various ways, and for an agricultural country like the Philippines, mapping in farmlands is not that common. Using the Sentinel 1 Synthetic Aperture Radar (SAR) data, the study reveals rice paddy classification brought by supervised machine learning on the municipality of Guimba, in Nueva Ecija - the Rice Bowl Capital of the country. The study in Guimba, Nueva Ecija, addresses the absence of comprehensive rice classification studies, focusing on creating a classified rice paddy map and assessing spectral indices (NDMI, NDVI, NDWI) using synthetic aperture radar and optical imager. Results show successful differentiation between rice and non-rice paddies. Temporal analysis emphasizes monitoring water availability, soil moisture, and vegetation health. Despite signs of overprediction in the CART model, its effectiveness in mapping rice paddies is notable. The spatial distribution maps contribute to targeted monitoring, enabling efficient interventions and improved agricultural practices. This research highlights the inherent use of remote sensing in rice crop management, offering valuable insights for farmers and country's food security.

Classification of Rice Grains by Image Processing

General Background: The assessment of the surface quality of pre-treated rice grains is crucial for determining their market acceptability, storage stability, processing quality, and overall consumer satisfaction. Traditional evaluation methods are often time-consuming and yield subjective classifications. Specific Background: The lack of a comprehensive tagged image dataset hinders the application of advanced convolutional neural networks (CNN) for detailed damage classification of healthy rice grains. Knowledge Gap: Existing datasets and methods limit the effective exploration of sophisticated CNN models for categorizing rice types, particularly in identifying subtle damage characteristics. Aims: The study aims to create a robust rice grain classification system using image processing techniques, primarily deep learning algorithms, to improve the classification of rice varieties. Results: Utilizing a dataset of 75,000 images across five widely cultivated rice varieties in Turkey, we achieved classification accuracies of 100% for CNN, 99.95% for deep neural networks (DNN), and 99.87% for artificial neural networks (ANN). Novelty: The proposed approach represents a significant advancement in rice classification technology, employing a combination of image acquisition, feature extraction, and machine learning to streamline the process, effectively addressing the challenges faced in traditional methods. Implications: The findings underscore the potential for improved sorting and grading efficiency in the rice industry, facilitating better market outcomes and consumer satisfaction through enhanced quality control Highlights: Innovative: Uses CNN for accurate rice variety classification. Data-Driven: Analyzes 75,000 images for enhanced quality evaluation. Impactful: Increases efficiency in sorting and grading processes. Keywords: Rice Classification, Image Processing, CNN, Machine Learning, Agricultural Technology

Evaluating the Impact of Data Normalization on Rice Classification Using Machine Learning Algorithms

Evaluating the Impact of Data Normalization on Rice Classification Using Machine Learning Algorithms

Product differentiation of Sarawak premium rice using MOS gas sensors: comparison between transient and frequency response

In Malaysia, rice, ranked as the third most crucial crop, faces challenges due to domestic consumption outpacing production, resulting in increased instances of rice adulteration. This underscores the imperative of maintaining integrity and quality standards across the entire supply chain. This study uses an electronic nose, comprising four metal oxide semiconductor (MOS) gas sensors, and employing temperature modulation, Principal Component Analysis (PCA) and supervised machine learning (classification models) to distinguish rice varieties such as Bario, Bajong, Borneo Fragrant, Biris, and Jasmine. The study evaluated 30 classifiers based on their classification and validation accuracy. Sensor data was first extracted from the transient response of sensors output voltage, yielding a 12-dimension dataset with response times of 30 s, 50 s, and 95 s. Classification models trained from this dataset achieved classification (training) accuracy of up to 100% and validation accuracy of up to 96%, where the best performing models are subspace discriminant and kernel naïve bayes classifiers. An attempt was also made to analyze the sensor data frequency response for rice classification. Comparison between the prediction results in the transient and frequency domains showed that transient response is better suited for the classification of rice.

Improved Paddy Rice Classification Utilizing Sentinel-1/2 Imagery in Anhui China: Phenological Features, Algorithms, Validation and Analysis

Enhancing the accuracy of paddy rice mapping is crucial for bolstering global food security. Prior research incorporating Sentinel imagery with phenological characteristics has identified paddy rice fields effectively. However, challenges such as reliance on a single index, cloud cover interference, and a lack of sufficient training samples continue to complicate the mapping of paddy rice. This study introduces a comprehensive paddy rice mapping framework that incorporates annual phenological features throughout the entire growth phase. This was achieved by expanding the sample size through the extraction of phenological features, and the visually verified samples were then integrated with distinct phenological phases and relevant indices, utilizing hybrid Sentinel-1/2 imagery to map paddy rice distribution. The accuracy of the generated rice map was validated against trusted samples, corroborative agricultural statistics, and another high-resolution 10 m mapping product. Compared with ground-truth samples, the algorithm has achieved an overall accuracy of approximately 92% in most rice production regions with a confusion matrix. Additionally, the estimated rice area in Anhui and several other rice-producing regions shows less than 10% error when compared with governmental statistical records from the yearbook. When compared with another recent paddy rice map at the same spatial resolution (10 m), our approach provided cleaner details and more effectively reduced omission errors. It received values of R2 = 0.991 and slope = 1.08 in a prefecture-level statistical comparison with a counterpart. Our proposed approach is proven to be valid and is expected to offer significant benefits to agricultural sustainability and technological applications in farming.

Rapid classification of rice according to storage duration via near-infrared spectroscopy and machine learning

Rice is the most important staple crop for more than half of the world's population. As rice quality can deteriorate during storage, methods that can effectively classify rice according to its storage duration are essential. However, existing methods of assessing rice storage time are time-consuming, laborious, and incompatible with modern industrial processing technologies. Therefore, we investigated the ability of near-infrared spectroscopy combined with machine learning algorithms to distinguish rice storage duration. A total of 482 rice samples were analyzed, which included 74, 100, and 308 samples produced during 2015–2016, 2017–2018, and 2020–2021, respectively. Five pre-processing methods were initially applied to the spectra to enhance the accuracy of the discrimination model. Subsequently, two-dimensional correlation spectroscopy and competitive adaptive reweighted sampling (CARS) were used to extract the characteristic spectra associated with storage time. Finally, three pattern recognition methods (K-nearest neighbor analysis, linear discriminant analysis, and least squares support vector machine (LS-SVM)) were compared for their effectiveness in constructing classification models. The results indicated that the best model for identifying the storage duration of rice was established after spectral pre-processing with the standard normal variate and first derivative, using the CARS algorithm to select feature wavelengths, and applying the LS-SVM modeling method, which together yielded correct identification rates of 99.72 % and 91.67 % for the calibration and validation sets, respectively. Thus, we propose near-infrared spectroscopy coupled with machine learning algorithms as an effective approach for classifying rice according to storage duration, which can facilitate evaluations of rice freshness in the market.

DETECTION OF WHITE RICE ADULTERANTS IN LAMPUNG ROBUSTA COFFEE EXTRACT USING FT-IR METHOD BY FINGERPRINT ANALYSIS AND PRINCIPAL COMPONENT ANALYSIS

Lampung Province has 3 areas that produce coffee: West Lampung, Tanggamus, and Waykanan, which can produce 51,484 tons of coffee annually. The high demand for coffee and limited harvest are some factors that cause the addition of adulterants to coffee products such as corn, soybeans, rye, coffee beans, and rice. This study aims to detect rice adulterants in Lampung robusta coffee using the FTIR spectrophotometric method combined with chemometric analysis using the PCA (Principal Component Analysis) method. FTIR spectrophotometric method combined with chemometric analysis using PCA (Principal Component Analysis) method. The PCA method was validated using the cross-validation method. Samples were taken from 3 Lampung coffees on the market. The extraction process was carried out on Lampung coffee and Lampung rice from 3 regions using 96% ethanol. After concentrating, the coffee and rice extracts were measured using FTIR and read in the 4000-650 cm-1 wave number range. Different wave number curves were obtained between coffee and rice. A pre-processing chemometric analysis was performed, which resulted in the classification of Robusta coffee and rice using PC1 and PC2 (50% and 24%). The results of PCA analysis showed that PC1 and PC2 in the three Lampung coffee samples, samples A and C, did not contain adulterants, while sample B was suspected of containing white rice. Keywords: Alduteran, FTIR, Chemometrics, PCA, Lampung Robusta Coffee.

Classification of Rice Seeds Grown in Different Geographical Environments: An Approach Based on Improved Residual Networks

Rice is one of the most important crops for food supply, and there are multiple differences in the quality of rice in different geographic regions, which have a significant impact on subsequent yields and economic benefits. The traditional rice identification methods are time-consuming, inefficient, and delicate. This study proposes a deep learning-based method for fast and non-destructive classification of rice grown in different geographic environments. The experiment collected rice with the name of Ji-Japonica 830 from 10 different regions, and a total of 10,600 rice grains were obtained, and the fronts and backsides of the seeds were photographed with a camera in batches, and a total of 30,000 images were obtained by preprocessing the data. The proposed improved residual network architecture, High-precision Residual Network (HResNet), was used to compare the performance of the models. The results showed that HResNet obtained the highest classification accuracy result of 95.13%, which is an improvement of 7.56% accuracy with respect to the original model, and validation showed that HResNet achieves a 98.7% accuracy in the identification of rice grown in different soil classes. The experimental results show that the proposed network model can effectively recognize and classify rice grown in different soil categories. It can provide a reference for the identification of other crops and can be applied for consumer and food industry use.

Non-destructive Machine Vision System based Rice Classification using Ensemble Machine Learning Algorithms

Aims and Background: Agriculture plays a major role in the global economy, providing food, raw materials, and jobs to billions of people and driving economic growth and poverty reduction. Rice is the most widely consumed crop domestically, making it a particularly important crop for rural populations. The exact number of rice varieties worldwide is difficult to determine as new varieties are constantly being developed and marketed. Objectives: The most common method of rice variety identification is a comparison of its physical and chemical properties to a reference collection of known types. Methodology: This is a relatively quick and cost-effective approach that can be used to accurately differentiate between distinct varieties. In some cases, genetic testing may be used to confirm the identity of a variety, although this technique is more expensive and time-consuming. However, we can also utilize efficient, precise, and cost-effective digital image processing and machine vision techniques. Results: This study describes different types of ensemble methods, such as bagging (Decision Tree, Random Forest, Extra Tree), boosting (AdaBoost, Gradient Boost, and XGBoost), and voting classifiers to classify five different varieties of rice. Extreme Gradient Boosting (XGBoost) has achieved the highest average classification accuracy of 99.60% among all the algorithms. Conclusion: The findings of the performance measurement indicated that the proposed model was successful in classifying the various varieties of rice.

The Rapid Non-Destructive Differentiation of Different Varieties of Rice by Fluorescence Hyperspectral Technology Combined with Machine Learning.

A rice classification method for the fast and non-destructive differentiation of different varieties is significant in research at present. In this study, fluorescence hyperspectral technology combined with machine learning techniques was used to distinguish five rice varieties by analyzing the fluorescence hyperspectral features of Thai jasmine rice and four rice varieties with a similar appearance to Thai jasmine rice in the wavelength range of 475-1000 nm. The fluorescence hyperspectral data were preprocessed by a first-order derivative (FD) to reduce the background and baseline drift effects of the rice samples. Then, a principal component analysis (PCA) and t-distributed stochastic neighborhood embedding (t-SNE) were used for feature reduction and 3D visualization display. A partial least squares discriminant analysis (PLS-DA), BP neural network (BP), and random forest (RF) were used to build the rice classification models. The RF classification model parameters were optimized using the gray wolf algorithm (GWO). The results show that FD-t-SNE-GWO-RF is the best model for rice classification, with accuracy values of 99.8% and 95.3% for the training and test sets, respectively. The fluorescence hyperspectral technique combined with machine learning is feasible for classifying rice varieties.

Advancements in Artificial Intelligence (AI) for enhanced insights and automation in rice agriculture: A systematic review

With the rising global demand for rice, improving production efficiency through advanced technologies like artificial intelligence (AI) is crucial. This systematic review gathered recent literatures on learning algorithm models applied to automate rice agriculture tasks. The objectives were to analyze the performance accuracy of different machine learning algorithms for rice classification and determine the most effective models. The 116 studies from 2016-2023 were screened and 70 were included. The algorithms were evaluated by weighted mean accuracy percentage across studies while maintaining consideration to sample sizes. The results showed the DenseNet121 deep convolutional neural network achieved the overall highest accuracy of 99.98%, also topping rice disease detection. For variety classification, Deep Neural Networks reached 99.95% accuracy by learning complex visual differences. Adaptive Neuro-Fuzzy Inference System led in grading quality of 98.6% by discerning grain features. Larger datasets improved accuracy indicating that the more training data has, it enhances model accuracy. The review demonstrates AI’s significant potential to automate essential aspects of rice production. Further research expanding standardized algorithm evaluations is recommended to strengthen the evidence-base and support integration of AI for intelligent, sustainable rice agriculture.

Automatic Rice Early-Season Mapping Based on Simple Non-Iterative Clustering and Multi-Source Remote Sensing Images

Timely and accurate rice spatial distribution maps play a vital role in food security and social stability. Early-season rice mapping is of great significance for yield estimation, crop insurance, and national food policymaking. Taking Tongjiang City in Heilongjiang Province with strong spatial heterogeneity as study area, a hierarchical K-Means binary automatic rice classification method based on phenological feature optimization (PFO-HKMAR) is proposed, using Google Earth Engine platform and Sentinel-1/2, and Landsat 7/8 data. First, a SAR backscattering intensity time series is reconstructed and used to construct and optimize polarization characteristics. A new SAR index named VH-sum is built, which is defined as the summation of VH backscattering intensity for specific time periods based on the temporal changes in VH polarization characteristics of different land cover types. Then comes feature selection, optimization, and reconstruction of optical data. Finally, the PFO-HKMAR classification method is established based on Simple Non-Iterative Clustering. PFO-HKMAR can achieve early-season rice mapping one month before harvest, with overall accuracy, Kappa, and F1 score reaching 0.9114, 0.8240 and 0.9120, respectively (F1 score is greater than 0.9). Compared with the two crop distribution datasets in Northeast China and ARM-SARFS, overall accuracy, Kappa, and F1 scores of PFO-HKMAR are improved by 0.0507–0.1957, 0.1029–0.3945, and 0.0611–0.1791, respectively. The results show that PFO-HKMAR can be promoted in Northeast China to enable early-season rice mapping, and provide valuable and timely information to different stakeholders and decision makers.

Rice Classification and Quality Detection Success with Artificial Intelligence Technologies

Rice Classification and Quality Detection Success with Artificial Intelligence Technologies

Fine classification and phenological analysis of rice paddy based on multi-temporal general compact polarimetric SAR data.

Fine classification and phenological information of rice paddy are of great significance for precision agricultural management. General compact polarimetric (CP) synthetic aperture radar (SAR) offers the advantage of providing rich polarimetric information, making it an important means of monitoring rice growth. Therefore, in response to the current challenges of difficulty in rice type classification and the small differences in phenological polarimetric characteristics, a novel strategy for fine classification and phenological analysis of rice paddy is proposed. This strategy thoroughly explores the polarimetric information of general CP SAR data and the target scattering characterization capabilities under different imaging modes. Firstly, the general CP SAR data is formalized using the standard CP descriptors, followed by the extraction of general CP features through the ΔαB /αB target decomposition method. optimal CP features are generated to achieve fine classification of rice paddy. Finally, 6 phenological stages of rice are analyzed based on the general CP features. The experiment results of rice classification show that the classification accuracy based on this strategy exceeds 90%, with a Kappa coefficient above 0.88. The highest classification accuracies were observed for transplanting hybrid rice paddy (T-H) and direct-sown japonica rice paddy (D-J), at 80.9% and 89.9%, respectively. The phenological evolution rule of the two rice types indicate that from early June (seedling stage) to late July (elongation stage), the CP feature variation trends of T-H and D-J are generally consistent. However, from October (mature stage) to November (harvest stage), the variation trends of the CP features for T-H and D-J are significantly different. The study found that from the booting-heading stage to the harvest stage, the linear π/4 mode outperforms circular and elliptical polarimetric modes in distinguishing different types of rice. Throughout the entire phenological period of rice growth, CP SAR of linear π/4 mode is surpasses that of other linear modes in discriminating different type of rice. The proposed strategy enables high-precision fine classification rice paddy, and the extracted general CP αB parameter effectively reflects the phenological change trends in rice growth.

A comparative study of state-of-the-art deep learning architectures for rice grain classification

Accurate and efficient automated rice grain classification systems are vital for rice producers, distributors, and traders, offering improved quality control, cost optimization, and supply chain management. They also hold the potential to aid in the development of rice varieties that are more resistant to disease, pests, and environmental stress. While most existing studies in the rice classification domain rely on traditional machine-learning techniques that necessitate feature extraction engineering processes, our research explores the effectiveness of novel deep-learning models for this task. We evaluated the performance of various contemporary deep-learning models, including Residual Network (ResNet), Visual Geometry Group (VGG) network, EfficientNet, and MobileNet. These models were tested on a dataset comprising 75,000 images, classified into five different rice categories. We assessed each model using established evaluation metrics such as accuracy, F1 score, precision, recall, and per-class accuracy. Our findings showed that the EfficientNet-based model delivered the highest accuracy (99.67%), while the MobileNet-based model excelled in the speed of classification (2556 s). We concluded that, compared to traditional machine learning methods, the models employed in our study are highly scalable and capable of managing large volumes of complex data with millions of features and samples.

Rice Classification with K-Nearest Neighbor based on Color Feature Extraction and Invariant Moment

Rice Classification with K-Nearest Neighbor based on Color Feature Extraction and Invariant Moment

KLASIFIKASI MUTU BERAS MENGGUNAKAN K-NN BERBASIS BACKWARD ELIMINATION

CLASSIFICATION RICE QUALITY USING K-NN BACKWARD-BASED ELIMINATIONRice is one of the most important agricultural products. And it is a strategic commodity because almost all Indonesian people need it. Because of the importance of the function of rice as a staple food ingredient, the quality of the rice to be consumed must be ensured to be of high quality. Determination of the quality or quality of rice until now has been done by many previous researchers. However, of the several methods that have been selected, the majority use image processing. Rice quality data processing using data mining is still rarely done. In this study, the dataset that will be used comes from the Probolinggo Regency Agriculture Service database which has 1 special attribute and 9 regular attributes. The attributes are: variety, length, shape, color, taste, rice planting technique, season, pests, PH and quality. The method that will be used in this study is the backward elimination-based K-NN method.From the results of the analysis and computation of several methods, it can be concluded that the backward elimination-based K-NN method used to increase the accuracy of rice classification resulted in several conclusions. Namely the attributes that affect the determination of rice quality are variety, shape, color, technique, season, pests and PH. While the features that are considered to have no effect are taste and length. As for the data as much as 4952, the best accuracy is 83.08% when k = 1, while for the data as much as 2000, then the best accuracy is 87.70% at k = 1, while for the data as much as 1000, the best accuracy is 98.60%, namely when k=1.

Determining the Rice Seeds Quality Using Convolutional Neural Network

Seed inspection is crucial for plant nurseries and farmers as it ensures seed quality when growing seedlings. It is traditionally accomplished by expert inspectors filtering samples manually, but there are some challenges, such as cost, accuracy, and large numbers. Speed and accuracy were the main conditions for increasing agricultural productivity. Machine learning is a sub-science of Artificial Intelligence that can be applied in research on the classification of rice seed quality. The pipeline of a machine learning system is dataset collection, training, validation, and testing. Model making begins with taking data on the characteristics of rice seeds based on physical parameters in the form of seed shape and color. The dataset used is two thousand images divided into two categories, namely superior seeds and non-superior seeds. Training and Validation was conducted using the Convolutional Neural Network (CNN) algorithm with the concept of cross-validation on Google Collaboratory notebooks. The ratio split of train data and validation data in modeling from a dataset is 80:20. The result of the model formed is a model with the development of a Deep Convolutional Neural Network (Deep CNN) that can classify the digital image data of rice seeds from the results of data calls uploaded into the system. The results of the experiment conducted on 30 test data can be analyzed so that the system can classify superior and non-superior seeds with a precision value of 93% and a recall of 95%.

A Deep Learning Framework for Processing and Classification of Hyperspectral Rice Seed Images Grown under High Day and Night Temperatures.

A framework combining two powerful tools of hyperspectral imaging and deep learning for the processing and classification of hyperspectral images (HSI) of rice seeds is presented. A seed-based approach that trains a three-dimensional convolutional neural network (3D-CNN) using the full seed spectral hypercube for classifying the seed images from high day and high night temperatures, both including a control group, is developed. A pixel-based seed classification approach is implemented using a deep neural network (DNN). The seed and pixel-based deep learning architectures are validated and tested using hyperspectral images from five different rice seed treatments with six different high temperature exposure durations during day, night, and both day and night. A stand-alone application with Graphical User Interfaces (GUI) for calibrating, preprocessing, and classification of hyperspectral rice seed images is presented. The software application can be used for training two deep learning architectures for the classification of any type of hyperspectral seed images. The average overall classification accuracy of 91.33% and 89.50% is obtained for seed-based classification using 3D-CNN for five different treatments at each exposure duration and six different high temperature exposure durations for each treatment, respectively. The DNN gives an average accuracy of 94.83% and 91% for five different treatments at each exposure duration and six different high temperature exposure durations for each treatment, respectively. The accuracies obtained are higher than those presented in the literature for hyperspectral rice seed image classification. The HSI analysis presented here is on the Kitaake cultivar, which can be extended to study the temperature tolerance of other rice cultivars.