7) 2,682 294 2,976 Fig 5 The Apple Fruit Varieties Collection (AFVC) distributions through 85 classes. Fig 6 The Apple Fruit Varieties Collection (AFVC) measurement was split through 85 classes; the overall training was 26,775, and the testing was 2,975 samples. The second collection, Apple Fruit Quality Categorization (AFQC) [ https://github.com/mustafa20999/AFQC ], was collected from the orchard ( Table 1 ). The study area was Beijing City, Huairou District, Beijing Shengshiguowang, with a mean temperature of 76°C − 19°C and an average monthly rainfall of 51.2 mm. Data was collected at two different periods between October 1st, 2023, and October 10th, 2023: in the morning, when shootin
Open resource ↗mustafa20999/AFQC · lines:66-100Unverified paper record
Apple varieties, diseases, and distinguishing between fresh and rotten through deep learning approaches.
PloS one · 15 May 2025 · 10.1371/journal.pone.0322586
Abstract
Apples are one of the most productive fruits in the world, in addition to their nutritional and health advantages for humans. Even with the continuous development of AI in agriculture in general and apples in particular, automated systems continue to encounter challenges identifying rotten fruit and variations within the same apple category, as well as similarity in type, color, and shape of different fruit varieties. These issues, in addition to apple diseases, substantially impact the economy, productivity, and marketing quality. In this paper, we first provide a novel comprehensive collection named Apple Fruit Varieties Collection (AFVC) with 29,750 images through 85 classes. Second, we distinguish fresh and rotten apples with Apple Fruit Quality Categorization (AFQC), which has 2,320 photos. Third, an Apple Diseases Extensive Collection (ADEC), comprised of 2,976 images with seven classes, was offered. Fourth, following the state of the art, we develop an Optimized Apple Orchard Model (OAOM) with a new loss function named measured focal cross-entropy (MFCE), which assists in improving the proposed model's efficiency. The proposed OAOM gives the highest performance for apple varieties identification with AFVC; accuracy was 93.85%. For the apples rotten recognition with AFQC, accuracy was 98.28%. For the identification of the diseases via ADEC, it was 99.66%. OAOM works with high efficiency and outperforms the baselines. The suggested technique boosts apple system automation with numerous duties and outstanding effectiveness. This research benefits the growth of apple's robotic vision, development policies, automatic sorting systems, and decision-making enhancement.
Plant phenotyping relevance
リンゴ画像から腐敗状態や病害を推定するデータセットと深層学習モデルを開発・評価しており、植物状態の画像ベース推定が中心である。
abstractwe first provide a novel comprehensive collection named Apple Fruit Varieties Collection (AFVC) with 29,750 images through 85 classes.
abstractSecond, we distinguish fresh and rotten apples with Apple Fruit Quality Categorization (AFQC), which has 2,320 photos.
abstractThird, an Apple Diseases Extensive Collection (ADEC), comprised of 2,976 images with seven classes, was offered.
abstractwe develop an Optimized Apple Orchard Model (OAOM) with a new loss function named measured focal cross-entropy (MFCE)
Code and data availability
The paper's three apple image datasets (AFVC, ADEC, AFQC) are explicitly released with free public access via the authors' GitHub repositories, and the Data Availability statement confirms all data is available at these URLs. These are paper-specific image datasets used directly for the paper's apple variety, disease,,
This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.