Simplificando a Interpretação de Laudos de Análise de Solo com Deep Learning em Nuvem

Since the soil impacts directly on agricultural productivity, its conservation through the correct application of nutrients and fertilization is of paramount importance. In this work, we propose a software architecture and a
mobile application capable of assisting farmers and agronomists in interpreting soil analyses generated from laboratories. The software architecture was designed for cloud environments and the mobile application is the interface for capturing and presenting data. Initially, it was necessary to create a database with different image types and configurations. All images from the dataset were treated to eliminate noise (such as brightness, shadows and distortions) and used to evaluate two Deep Learning solutions (Google Vision and Tesseract OCR), where Tesseract OCR proved to be more accurate using the same images. In addition to offering the mobile application, which is the first step, the research carried out reveals several technological deficiencies and opportunities for innovations in the field of soil science.