Browsing by Author "Junaidi, Ahmad fajri"

Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    KLASIFIKASI TANAMAN REMPAH MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK BERBASIS R
    (Elfitra, 2022-12) Junaidi, Ahmad fajri; Fitriansyah, Aidil
    Spices have many types. Some are used as seasoning for cooking and some are used as herbal medicine. Of the many spices that exist, it is not uncommon for spices to have a similar looks so few people have it difficult distinguishing them. For example, Ginger, Turmeric, Galangal, and Temulawak. This research aims to perform image recognition of the four spices and form a CNN classification model that can distinguish the four spices. This research will use 180 spice images as samples where each type has 45 image samples. Then the model is formed using the R programming language with the help of the Keras package and the tensorflow package. because making a neural network model using Keras does not need to write code to express mathematical calculations one by one. Testing with a sample of 40 spice images shows an accuracy rate of 85% which is considered to have been able to classify the differences between the types of spices that tested.