An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image Data

Generation of a thematic map is important for scientists and agriculture engineers in analyzing different crops given field. Remote sensing data are well-accepted image classification on vast area crop investigation. However, most the research has currently focused pixel-based analysis. The study was carried out to develop multi-category hyperspectral system identify major Chiayi Golden Corridor. from CASI (Compact Airborne Spectrographic Imager) were used as experimental this study. A two-stage designed display performance classification. More specifically, multi-class by support vector machine (SVM) + convolutional neural network (CNN) SVM supervised learning model that analyzes CNN class deep networks applied visual imagery. comparison made among four (paddy rice, potatoes, cabbages, peanuts), roads, structures In first stage, handled through Then, convolution improved details various blocks (cells) segmentation second stage. series discussion analyses results presented. repair module also link usage remove errors.