Plant disease recognition
Recent advances in computer vision and the proliferation of smart mobile devices present an opportunity to expand and enhance the practice of precision plant protection and extend the market of computer vision applications in the field of precision agriculture. Today IC technologies are used to provide real-time micro-climate monitoring and recommendations with the resolution required for precision agriculture. The process of gathering on-site disease-related data has, however, not benefited greatly through the application of ICT, and still requires expert man-power. However, recent advances in visual object recognition and classification make it possible to design disease-recognition tools suitable for non-expert on-site use.
Having the above mentioned in mind, the idea of creating application for smart mobile devices that could recognize diseases in fruits, vegetables and other crops based on leaf photo occurred. Such application would serve as an aid to farmers for fast and efficient recognition of the diseases which would help decision-making process concerning the use of chemical pesticides.
Using the camera on a mobile device, farmers take photos of the diseased leaf. Based on the photos, the mobile device processes the image and sends key data called “features” to a server where disease recognition takes place. Information on the type of disease combined with disease description and the recommended treatment is then delivered to the user in a matter of seconds.