Self-involvement or approach in managing electronic devices such as computers, laptops, and smartphones lies in the fact that when managing a large number of them, it becomes difficult to categorize and record them, especially in corporate environments, schools, or service centers. Both devices are similar in shape and color, making them impossible to identify manually, which results in recording errors and wasted time. In this regard, this study focuses on the implementation of the K-Means Clustering algorithm in grouping electronic devices by digital image processing tools that will assist in automatic and accurate identification. This research will be conducted in the form of experimental research, with the main phases being the collection of electronic device image data (computers, laptops, and smartphones), image processing (RGB to LAB conversion), shape and texture feature extraction, and implementation of the K-Means Clustering algorithm using the Matlab application. Performance evaluation will be conducted using the sum of squared errors (SSE) to measure the quality of clustering. The results of this study show that the K-Means Clustering algorithm has 100 percent accuracy in classifying 30 images of electronic devices (10 computers, 10 laptops, and 10 smartphones). This method can be effective in separating objects using color, shape, and texture features, thereby contributing to automatic classification systems in the handling of electronic devices in various sectors.
Copyrights © 2026