Pereira, Márcio DiasRamos, Amanda Karoliny Fernandes2021-04-292021-09-292021-04-292021-09-292020-11-10RAMOS, Amanda Karoliny Fernandes. Análise de radiografias digitais de sementes de Urochloa decumbens com uso de um novo sistema especialista. 2020. 43f. Trabalho de Conclusão de Curso (Graduação em Engenharia Agronômica) - Unidade Acadêmica Especializada em Ciências Agrárias, Universidade Federal do Rio Grande do Norte, Macaíba, 2020.https://repositorio.ufrn.br/handle/123456789/40282Seeking to make optical analysis increasingly faster and more accurate, it becomes necessary to develop efficient tools that further facilitate these assessments. Therefore, the objective of the present study was to develop and evaluate the efficiency of a specialized software for the analysis of digital radiographs of brachiaria seeds called SARS (Seed Radiography Analysis System). Five lots of 200 seeds of Urochloa decumbens cv. Basilisk were obtained from commercial batches produced in the 2018/2019 harvest. Radiographic imagens of the seeds were obtained and subsequently analyzed by SARS to obtain physical characteristics of the seeds. The seeds were submitted to the germination test, in which variables related to the physiological quality of the seeds were evaluated. It was possible to observe that the seeds with greater germination and vigor showed strong and significant correlations with some of the physical variables obtained with the SARS. Thus a high correlation between seedling length and relative seed density is important to validate the method of analyzing radiographic images in order to assess the quality of the seeds. SARS in an efficient tool for analyzing digital radiographs of brachiaria seeds. The software is capable of generating descriptors that support the morphometric analysis and the internal regions of the seeds. The physical parameters obtained from the analysis of the radiographs are closely related to the germination and vigor of the seeds.Espécies forrageirasAnálise de imagensimagens radiográficas de sementesSARSbachelorThesis