外文摘要：Application of artificial intelligence methods in agriculture is gaining research attention with focus on improving planting, harvesting, post-harvesting, etc. Fruit quality recognition is crucial for farmers during harvesting and sorting, for food retailers for quality monitoring, and for consumers for freshness evaluation, etc. However, there is a lack of multi-fruit datasets to support real-time fruit quality evaluation. To address this gap, we present a new dataset of fruit images aimed at evaluating fruit freshness, which addresses the lack of multi-fruit datasets for real-time fruit quality evaluation. The dataset contains images of 11 fruits categorized into three freshness classes, and five well-known deep learning models (ShuffleNet, SqueezeNet, EfficientNet, ResNet18, and MobileNet-V2) were adopted as baseline models for fruit quality recognition using the dataset. The study provides a benchmark dataset for the classification task, which could improve research endeavors in the field of fruit quality recognition. The dataset is systematically organized and annotated, making it suitable for testing the performance of state-of-the-art methods and new learning classifiers. The research community in the fields of computer vision, machine learning, and pattern recognition could benefit from this dataset by applying it to various research tasks such as fruit classification and fruit quality recognition. The study achieved impressive results with the best classifier being ResNet-18 with an overall best performance of 99.8% for accuracy. The study also identified limitations, such as the small size of the dataset, and proposed future work to improve deep learning techniques for fruit quality classification tasks.
外文关键词：precision agriculture;computer vision;image processing;fruit freshness evaluation;fruit decay detection
作者：Abayomi-Alli, Olusola O O;Damasevicius, Robertas;Misra, Sanjay;Abayomi-Alli, Adebayo
作者单位：Kaunas Univ Technol;Inst Energy Technol;Fed Univ Agr
期刊名称：MULTIMEDIA TOOLS AND APPLICATIONS
期刊影响因子：0.0
出版年份：2024
出版刊次：83（4）
原文传递申请：江苏省科技资源（工程技术文献）统筹服务平台