Inicio  /  Agriculture  /  Vol: 12 Par: 6 (2022)  /  Artículo
ARTÍCULO
TITULO

Self-Supervised Clustering for Leaf Disease Identification

Muhammad Mostafa Monowar    
Md. Abdul Hamid    
Faris A. Kateb    
Abu Quwsar Ohi and M. F. Mridha    

Resumen

Plant diseases have been one of the most threatening scenarios to farmers. Although most plant diseases can be identified by observing leaves, it often requires human expertise. The recent improvements in computer vision have led to introduce disease classification systems through observing leaf images. Nevertheless, most disease classification systems are specific to diseases and plants, limiting method?s usability. The methods are also costly as they require vast labeled data, which can only be done by experts. This paper introduces a self-supervised leaf disease clustering system that can be used for classifying plant diseases. As self-supervision does not require labeled data, the proposed method can be inexpensive and can be implemented for most types of plants. The method implements a siamese deep convolutional neural network (DCNN) for generating clusterable embeddings from leaf images. The training strategy of the embedding network is conducted using AutoEmbedder approach with randomly augmented image pairs. The self-supervised embedding model training involves three different data pair linkage scenarios: can-link, cannot-link, and may-link pairs. The embeddings are further clustered using k-means algorithm in the final classification stage. The experiment is conducted to individually classify diseases of eight different fruit leaves. The results indicate that the proposed leaf disease identification method performs better than the existing self-supervised clustering systems. The paper indicates that end-to-end siamese networks can outperform well-designed sequentially trained self-supervised methods.

 Artículos similares

       
 
Fredrik Regler and Heinz Bernhardt    
This study addresses the challenge of subjective remounting decisions in calf and heifer rearing, typically driven by the animal caretaker?s feelings and experience, lacking a robust data foundation. Key factors such as developmental delays, diseases, or... ver más
Revista: Agriculture

 
Utpal Barman, Parismita Sarma, Mirzanur Rahman, Vaskar Deka, Swati Lahkar, Vaishali Sharma and Manob Jyoti Saikia    
Invading pests and diseases always degrade the quality and quantity of plants. Early and accurate identification of plant diseases is critical for plant health and growth. This work proposes a smartphone-based solution using a Vision Transformer (ViT) mo... ver más
Revista: Agronomy

 
Larissa Alves Rodrigues, Lázaro da Costa Corrêa Cañizares, Silvia Leticia Rivero Meza, Betina Bueno Peres, Silvia Naiane Jappe, Newiton da Silva Timm, Maurício de Oliveira and Paulo Carteri Coradi    
Red rice has achieved a lot of visibility due to its greater amounts of bioactive compounds compared to traditional white rice. The increased recognition of red rice by the industry is a consequence of the expansion of its study in the field of research.... ver más
Revista: Agronomy

 
Polina C. Tsalgatidou, Anastasia Papageorgiou, Anastasia Boutsika, Michael Chatzidimopoulos, Costas Delis, Dimitrios I. Tsitsigiannis, Epaminondas Paplomatas and Antonios Zambounis    
Brown rot disease caused by Monilinia fructicola is one of the most important peach fruit threats in the world. The use of biological control agents (BCAs), instead of synthetic fungicides, to successfully inhibit postharvest disease development is a cha... ver más
Revista: Agronomy

 
Zhichao Chen, Hongping Zhou, Haifeng Lin and Di Bai    
The tea industry, as one of the most globally important agricultural products, is characterized by pests and diseases that pose a serious threat to yield and quality. These diseases and pests often present different scales and morphologies, and some pest... ver más
Revista: Agronomy