The vastness of astronomical datasets and the complexity of celestial objects necessitate the use of robust classification techniques. In this context, machine learning emerges as an effective solution for identifying complex patterns and classifications. This study explores the application of machine learning techniques for classifying astronomical sources based on photometric data, including normal and emission line galaxies, quasars, and stars. The analysis is based on datasets from the Sloan Digital Sky Survey (SDSS) Data Release 18 (DR18). A comprehensive investigation is conducted, evaluating various classification models. The approach includes a detailed analysis of the metrics used and a meticulous feature selection process to optimize figures of merit. Different classification strategies, such as one-vs-one and one-vs-all, are explored. To mitigate the risk of overfitting or under-utilization of data, k-fold cross-validation is performed.