Mobile Application Development for Chili Disease Detection with Convolutional Neural Network
Abstract
Demand for chili peppers continues to increase with population growth and the industrial sector, but the supply could be more stable due to weather factors. This causes diseases in chili plants, such as fruit rot due to anthracnose, begomovirus yellow virus, and leaf spot. This research aims to develop a chili plant disease identification system and evaluate the accuracy of disease image classification. With this system, farmers are expected to recognize diseases earlier and improve the quality and quantity of crops. The method used is a Convolutional Neural Network (CNN). The research stages include data collection, preprocessing, model design, and system testing. The dataset of chili plant disease images was obtained from a garden in Sumowono District, Semarang Regency, Central Java, with 4,500 images, divided by 70% for training data and 30% for validation. The accuracy results obtained were 99% in the training process and 94% in validation. Evaluation of the model with a new dataset of 150 images showed 94% accuracy. Functional testing and user testing on the mobile system by ten farmers resulted in an average score of 90. Thus, this mobile system can identify
Downloads
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
IJICOM is an open-access journal. Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
