MARATTO

article · Journal of Food Quality

Design and Evaluation of a Hybrid Technique for Detecting Sunflower Leaf Disease Using Deep Learning Approach

202286 citationsOpen accessUniversity of Ghana

In plain language

Agriculture plays a vital role in national economies, making early plant disease detection essential for timely intervention and treatment. Traditional manual identification is labour-intensive and slow, prompting the adoption of automated deep learning techniques. A hybrid deep learning architecture has been developed to recognise and classify sunflower leaf diseases, specifically targeting Alternaria leaf blight, Phoma blight, downy mildew, and Verticillium wilt. The system integrates two established transfer learning models, VGG-16 and MobileNet, using a stacking ensemble learning approach. For training and evaluation, a custom dataset comprising 329 sunflower images across five categories was assembled from Google Images. The classification performance of this stacked ensemble model is benchmarked against several existing deep learning architectures using accuracy metrics.

Key takeaways

  • A hybrid deep learning architecture combines VGG-16 and MobileNet using stacking ensemble learning to identify sunflower leaf diseases.
  • The model classifies four specific conditions: Alternaria leaf blight, Phoma blight, downy mildew, and Verticillium wilt.
  • The evaluation relies on a dataset of 329 images across five categories collected via Google Images.
  • The hybrid approach is evaluated on classification accuracy against several existing deep learning models.

Why it matters

Protecting agricultural crops from disease is vital for safeguarding national economic output and food security. Manual inspection of crops is time-consuming and often delays crucial treatment. Automated image recognition models offer a method to identify specific leaf infections quickly, supporting faster interventions against common blights and wilts that threaten sunflower harvests.

Commercialisation angle

This research could support automated crop-scouting software for agronomists and sunflower farmers, potentially integrated into mobile diagnostic applications. Because the approach incorporates MobileNet, it is conceptually suited to mobile or edge devices. However, the reliance on a small dataset of 329 web-sourced images indicates early-stage research that requires validation on larger, field-collected datasets before commercial deployment is feasible.

AI-generated from the published abstract. Always read the original work before citing.

Abstract

Agriculture and plants, which are a component of a nation's internal economy, play an important role in boosting the economy of that country. It becomes critical to preserve plants from infection at an early stage in order to be able to treat them. Previously, recognition and classification were carried out by hand, but this was a time-consuming operation. Nowadays, deep learning algorithms are frequently employed for recognition and classification tasks. As a result, this manuscript investigates the diseases of sunflower leaves, specifically Alternaria leaf blight, Phoma blight, downy mildew, and Verticillium wilt, and proposes a hybrid model for the recognition and classification of sunflower diseases using deep learning techniques. VGG-16 and MobileNet are two transfer learning models that are used for classification purposes, and the stacking ensemble learning approach is used to merge them or create a hybrid model from the two models. This work makes use of a data set that was built by the author with the assistance of Google Images and comprises 329 images of sunflowers divided into five categories. On the basis of accuracy, a comparison is made between several existing deep learning models and the proposed model using the same data set as the original comparison.

Research topics

  • Smart Agriculture and AI
  • Spectroscopy and Chemometric Analyses

Sustainable Development Goals

Read the original research

This page summarises published work. The authoritative version sits with the publisher.

DOI: 10.1155/2022/9211700

Is something wrong with this record? Report it or request removal.

Discussion

Discuss this research

Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.

No discussion yet. Open the first thread.