نوع مقاله : مقاله پژوهشی
نویسندگان
1 عضو هیات علمی سازمان تحقیقات کشاورزی
2 استاد بخش تحقیقات غلات، موسسه تحقیقات اصلاح و تهیه نهال و بذر، سازمان تحقیقات ، آموزش و ترویج کشاورزی، کرج، ایران.
3 گروه مهندسی بیوسیستم، دانشکده کشاورزی، دانشگاه فردوسی مشهد، مشهد، ایران
4 دانشگاه فردوسی مشهد
5 بخش تحقیقات فنی و مهندسی کشاورزی، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی خراسان رضوی، سازمان تحقیقات، آموزش و ترویج کشاورزی،
6 استادیار پژوهش، بخش تحقیقات فنی و مهندسی کشاورزی، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی خوزستان، سازمان تحقیقات ، آموزش و
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Yellow rust is one of the most important wheat diseases in Iran. One of the most fundamental points in the fight against yellow rust disease is to identify the points and foci of this disease in the field. This research aimed to identify yellow rust contamination in wheat by taking pictures of laboratory samples (with artificial pollution) using a visible camera. To prepare laboratory samples, yellow rust-sensitive variety (Bolani variety) was planted in pots and kept in a controlled environment. For pre-processing and processing, the images prepared using a visible camera were first checked with the help of software, and pre-processing including histogram expansion was done on the images to improve the contrast. Then, various vegetation indices were evaluated for visible images and the most suitable index for diagnosing yellow rust disease was introduced. The extracted features were evaluated by the differential stepwise analysis method separately. To determine the appropriate model for the diagnosis of yellow rust disease, various methods of supervised classification on images were evaluated. The results showed that the reflection index of red and green bands ranked first and second in the differential analysis. The accuracy of SVM neural network in supervised classification on visible images was 98.06% and 95.44% respectively in the learning and testing phase, which showed the highest accuracy compared to other classification methods.
کلیدواژهها [English]