Scholarlink

Tomato leaf diseases affects the superiority and amount of the crops to a large extent. Consequently, it is vital to notice the crop diseases at an initial phase to maintain a social, economic and ecological balance. In this direction this paper presents a framework which integrates both ML and DL-based technology for recognition and sorting of tomato leaf bugs. The proposed framework leverages fusion of deep-features and hand-crafted features for efficient feature representation. Further, the fused features obtained are utilized by LSTM-ANFIS based classification network. The proposed framework efficiently classifies the tomato plant leaf diseases by utilizing ANFIS-LSTM based classification module. To validate the effectiveness of proposed model extensive experiments are conducted on PlantVillage dataset. Furthermore, the proposed framework provided an accuracy of 98.83%.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Efficient Detection and Multi-level Classification of Tomato Plant Leaves Using Fused Deep and Hand-Crafted Features and LSTM-ANFIS

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Astha Sharma,
  • Ashwni Kumar

摘要

Tomato leaf diseases affects the superiority and amount of the crops to a large extent. Consequently, it is vital to notice the crop diseases at an initial phase to maintain a social, economic and ecological balance. In this direction this paper presents a framework which integrates both ML and DL-based technology for recognition and sorting of tomato leaf bugs. The proposed framework leverages fusion of deep-features and hand-crafted features for efficient feature representation. Further, the fused features obtained are utilized by LSTM-ANFIS based classification network. The proposed framework efficiently classifies the tomato plant leaf diseases by utilizing ANFIS-LSTM based classification module. To validate the effectiveness of proposed model extensive experiments are conducted on PlantVillage dataset. Furthermore, the proposed framework provided an accuracy of 98.83%.