Mango crop maturity estimation using meta‐learning approach

Abstract

Abstract Mangos are a significant fruit crop that is widely cultivated in tropical and subtropical regions. However, manual detection of mango crop maturity is time‐consuming and labor‐intensive. It is a vital agricultural commodity, and accurate assessment of the mango maturity stage is critical for harvesting and post‐harvest handling. Accurately detecting mango crop maturity is essential for ensuring optimal harvesting and quality. This study introduced a specialized Meta‐learning method for classifying mango crop images with limited data. The conventional approach to maturity classification, often hindered by limited labeled data, is significantly enhanced by meta‐learning's ability to adapt quickly to new tasks with minimal examples. The proposed approach works as initial image segmentation to isolate mango crop regions, comprehensive feature extraction to capture meaningful data representations, and a critical meta‐training. This phase involves refining a classifier within a metric space by utilizing cosine distance and an adaptable scale parameter, this is followed by a meta‐testing stage. where the adapted classifier is utilized for maturity prediction with minimal support samples. This research holds substantial promise for the agricultural sector, offering practical solutions to optimize harvest management practices and improve mango crop yield predictions. Practical applications Optimized Harvest Scheduling : Scenario: Farmers can use crop maturity estimation to schedule harvest times more precisely. Application: Knowing crop maturity optimizes harvest, minimizing losses. Resource Management : Scenario: Efficient use of resources such as water, fertilizers, and pesticides is essential for sustainable agriculture. Application: Crop maturity guides resource use, for example, reducing late‐stage water/nutrients prevents overuse, saves resources. Quality Assurance : Scenario: Crop quality is often linked to its maturity level. Application: Maturity estimation assesses crop quality, guiding post‐harvest planning and determining market value. Data‐Driven Decision Making : Scenario: Modern agriculture relies on data for decision‐making. Application: Maturity estimation promotes data‐driven farming, aiding trend analysis, optimizing planting, and enhancing farm management.

Plant phenotyping relevance

マンゴー画像から成熟度という植物器官・果実の状態を推定する画像解析手法を、セグメンテーション、特徴抽出、メタ学習として中心的に開発しているため。

Code and data availability

公開本文の所在を確認できませんでした。非公開または購読が必要な可能性があります。

No evidence-backed public reproduction asset is currently recorded.