Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal of Intelligent Decision Support System (IDSS)

Classification of Corn Seed and Cob Quality Based on Texture and RGB Color Features Using Backpropagation Method Pawening, Ratri Enggar; Zaskiya, Karina Desy; Hasanah, Syarifatul
Journal of Intelligent Decision Support System (IDSS) Vol 7 No 4 (2024): December: Intelligent Decision Support System
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/idss.v7i4.282

Abstract

The quality of agricultural products, such as corn, is greatly influenced by various factors, both environmental factors and agricultural engineering factors. This post-harvest quality affects product performance and is in line with consumer satisfaction, so it will greatly affect its selling price. Manual corn quality grouping requires a lot of time and effort. This study aims to develop a method for classifying corn kernel and cob quality based on digital image processing, using RGB color and texture features. The dataset consists of 150 corn kernel images divided into two quality categories, namely "good" and "bad". The research process involves preprocessing stages, color feature extraction using RGB color space, and texture features using the Gray Level Co-occurrence Matrix (GLCM) method. The classification model is built using the Backpropagation artificial neural network algorithm. The test results show that this method is able to achieve classification accuracy of up to 75%. The implementation of this method is expected to increase the efficiency of the corn quality selection process, reduce dependence on manual assessment, and provide significant benefits to the agricultural sector, especially farmers and the corn industry. These findings provide an important contribution to the development of digital-based post-harvest technology in Indonesia.