Application of Image Processing for Identifying RAM, SSD, and Webcam Using the K-Means Clustering Method

Abstract

The development of computer hardware requires appropriate automatic identification methods to assist in inventory, maintenance, and learning processes. Manual identification methods for hardware such as RAM, SSD, and webcams are often ineffective due to the difficulty of distinguishing their visual forms, especially for those who are unfamiliar with them. This study aims to apply image processing techniques using the K-Means clustering method to identify these three types of devices. The system was created using MATLAB with a graphical user interface (GUI) for ease of use. The process begins by capturing images in RGB format, which are then converted to Lab* color space. Segmentation is performed using the K-Means clustering method, which divides objects from the background into two clusters. The segmentation results are then refined using morphological operations. Next, shape features and texture features are extracted using Gray Level Co-occurrence Matrix (GLCM), which includes contrast, correlation, energy, and homogeneity. The features obtained are compared with the database using Euclidean distance to determine the type of hardware. The test results show that the system is able to accurately distinguish between RAM, SSD, and webcams. In conclusion, the use of K-Means clustering, GLCM, and distance-based classification can be an effective solution in identifying computer hardware through images.