In Brazil and worldwide, commercialization of soybeans is of great importance to the economy, making their quality considered. The presence of damaged soybean seeds decreases the added value of the product. Businesses need fast and effective techniques to maintain the quality. The present research aimed to identify, through image processing, damage caused to soybean seeds, namely the presence of greenish seeds and wrinkled seeds due to variations of humidity and temperature, where it was possible to identify greenish and wrinkled soybean seeds from images. Results obtained for greenish seeds indicated that the red color scale is the most suitable for selection due to its more significant variation compared to the other color scales. For the separation of wrinkled seeds, it can be stated that it is possible to find a selection parameter with 74.3% accuracy in removing seeds with medium to high degrees of wrinkle damage.
The seed sector faces several challenges when it comes to ensuring a quick and accurate decision making when working with large amounts of data on physiological quality of seed lots, which makes the process time-consuming and inefficient. Thus, artificial intelligence (AI) emerges as a new technological option in the seed sector to solve database problems in the post-harvest stages. This study aims to use machine learning to classify maize seed lots. Data were obtained from eight maize seed crops from a private company. These data were mined using the following classifiers: J48 (DecisionTree), RandomForest, CVR (ClassificationViaRegression), lBk (lazy.IBK), MLP (MultiLayerPercepton), and NäiveBayes. Cross-validation was used for data measurement, with the data set, including training and testing data, being divided into 10 subsets. The described steps were performed using the Weka software. It is concluded that results obtained allow the classification of maize seed lots with high accuracy and precision, and these algorithms can better classify the maize seed lot through vigor attributes, thus enabling more accurate decision making based on vigor tests on a reduced evaluation time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.