Fruit recognition and classification based on SVM method for production prediction of peaches

• Autor(a) principal: Pereira, Tiago M.
• Data de Publicação: 2019
• Outros Autores: Gaspar, Pedro Dinis, Simões, Maria Paula
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10400.6/7604
• topic: Precision Agriculture; Support vector machine (SVM); Production prediction; Fruit detection; Prunus persica

The concept of Precision Agriculture is usually associated with the usage of high-end technology equipment (hardware or software) to evaluate or monitor the conditions of a determined portion of land, adjusting afterwards the production factors, like seeds, fertilizers, pesticides, growing regulators, water, according to differential detected characteristics. This paper describes an algorithm developed to analyze and process images to recognize fruits, particularly peaches, and calculate it dimensions, like volume and weight. The recognition of peaches on their natural conditions on trees depends on several spatial- and time-variable parameters and requires complex segmentation algorithms. The proposed algorithm applies image segmentation for extraction of characteristics such as color and shape. These characteristics were used to train a classification method through a Support Vector Machine (SVM) to improve the recognition rate of fruits. The algorithm is designed to acquire images with a high-resolution camera installed in a drone that will fly between the tree lines. The production prediction of 29.3 tons per hectare was obtained based on volume and relation weight/volume calculated for the recognized peaches. An overall precision of 72% was achieved for the prediction rate of peaches in orchards (808 trees/ha). This is the first study regarding the application of these concepts under orchard trees aiming the production prediction along the fruit maturation. Other useful future applications are foreseen in orchard trees, related not only to production prediction, for this type of algorithm.