As benchmark image datasets expand in sample size and feature complexity, the challenge of managing increased dimensionality becomes apparent. Contrary to the expectation that more features equate to enhanced information and improved outcomes, the curse of dimensionality often hampers performance. This paper reviews existing literature on filter feature selection techniques applied to image features, highlighting when they are applied to both classical and deep-learning-based feature extraction methods. Additionally, this study explores how different feature selection methods behave when applied to image features through big data technologies. Different experiments were performed to compare the results when using feature selection techniques with various reduction percentages. Experimental results demonstrated that an important reduction of the extracted features provides classification results similar to those obtained with the full set of features. Furthermore, applying dimensionality reduction techniques outperforms, in some cases, the results achieved using broad feature vectors.