<![CDATA[Cayenne pepper (Capsicum frutescens L.) is one of the horticultural commodities with high economic value in Indonesia. Pest attacks and nutrient deficiencies can reduce crop quality and yield. Identification of these conditions is commonly conducted through visual observation, which can be subjective and time-consuming. This study aims to classify nutrient deficiency conditions in cayenne pepper leaves using the Convolutional Neural Network (CNN) method. The dataset consisted of primary data collected directly from the field and secondary data obtained from the Chili Plant Leaf Disease and Growth Stage Dataset from Bangladesh. The research stages included image preprocessing, data augmentation, CNN model training, and model evaluation. The CNN model was developed using three convolutional layers to classify cayenne pepper leaves into healthy and nutrient deficiency classes. The experimental results showed that the proposed model achieved high classification performance, with an accuracy of 98% on the primary dataset and 97% on the secondary dataset. These results indicate that the CNN method can effectively classify nutrient deficiency conditions in cayenne pepper leaves and maintain consistent performance across datasets.]]>
Copyrights © 2026
