<![CDATA[The rapid technological developments have made significant contributions in various fields, but the main problem faced in animal research and conservation is the limitations of manual identification methods that are time-consuming and prone to human error. In addition, visual differences between species often cause difficulties in the process of accurately classifying animal images. This study aims to develop an automatic classification system based on the K-Means Clustering method in identifying three animal species, namely cattle (Bos taurus), elephants (Loxodonta africana and Elephas maximus), and iguanas (Iguanidae). The research method includes several main stages, namely image acquisition, preprocessing by converting RGB to LAB color space, image segmentation using the K-Means Clustering algorithm, and extraction of shape and texture features with Eccentricity, Energy, and Homogeneity parameters. The dataset used consists of 30 images, 10 for each species. The results were analyzed using a confusion matrix to measure the level of classification accuracy. The results showed that the system was able to classify all images with an accuracy level of 100% without any misclassification between classes. Confusion matrix analysis reinforced these findings by demonstrating fully correct identification for all samples. These findings demonstrate the effectiveness of the K-Means Clustering method in grouping animal images with striking visual differences and offer potential applications in conservation and intelligent farming systems.]]>
