Supervised Training of a Simple Digital Assistant for a Free Crop Clinic

  • Mariana da Silva Barros UFPE
  • Igor de Moura Philippini UFPE
  • Ladson Gomes Silva UFPE
  • Antonio Barros da Silva Netto UFPE
  • Rosana Blawid UFRPE
  • Edna Natividade da Silva Barros UFPE
  • Stefan Blawid UFPE


Family farming represents a critical segment of Brazilian agriculture, involving more than 5 million properties and generating 74% of rural jobs in the country. Yield losses caused by crop diseases and pests can be devastating for small-scale producers. However, successful disease control requires correct identification, which challenges smallholders, who often lack technical assistance. The present work proposes a system that detects disease symptoms in images of plant leaves to assist phytopathology experts. The objective is to decrease the experts’ workload and enable consulting services for free or at nominal cost. In addition, the required digital communication channel will promote the formation of a caring community ready to offer unpaid advice for family farmers. The machine learning and refinement of the assistance system are described in detail. The developed classification system achieves a recall value of 95%.
Palavras-chave: Disease identification, Machine learning, Family farming
BARROS, Mariana da Silva; PHILIPPINI, Igor de Moura; SILVA, Ladson Gomes; NETTO, Antonio Barros da Silva; BLAWID, Rosana; BARROS, Edna Natividade da Silva; BLAWID, Stefan. Supervised Training of a Simple Digital Assistant for a Free Crop Clinic. In: BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS), 10. , 2021, Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . ISSN 2643-6264.