Detection of Disease and Pest of Kenaf Plant Based on Image Recognition with VGGNet19

One of the advantages Kenaf fiber as an environmental management product that is currently in center attention use for luxury car interiors with environmentally friendly plastic materials. The opportunity to export raw material will provide significant benefits, especially agricultural sector Indonesia. However, there are problems several areas Kenaf's garden, namely plants attacked by diseases and pests, which cause reduced yields even death. This problem caused lack expertise working hours extension workers well farmers' knowledge about have a terrible effect on plants. development information technology can be overcome imparting into machines known artificial intelligence. In this study, Convolutional Neural Network method was applied, aims identify symptoms disease based images so early control plant carried out. Data processing trained directly from kenaf plantations obtained accuracy 57.56% first two classes introduction VGGNet19 architecture 25.37% four second architecture. 5×5 block matrix input feature has been added training get maximum results.