Information measures are often essential in image processing to assess and perform features suitable for representing quality images. Multiple criteria, including Entropy, mutual information, and divergence, are effective means of gaining insight into the nature of image data systems and their intricacy, organization, and connection. This paper discusses several methods that involve information theory to determineṁPer Springer style, both city and country names must be present in the affiliations. Accordingly, we have inserted the city and country name. Please check and confirm if the inserted city and country name is correct. If not, please provide us with the correct city and country name. the effectiveness of the methods when used for feature extraction, considering the various image datasets and applications. The measures of choice, conversion of images into suitable representations, computation of the chosen measures for each image or region of interest in a playing time instance, feature extraction, methods of dimensionality reduction, and evaluation and comparison of various Information-theoretic metrics are all essential steps in this analysis. By analyzing the behavior of different information-theoretic metrics, one can determine the best approaches to feature extraction strategies in image processing. The investigation outcomes improved the advancement of image analysis, Classification, and retrieval techniques, which are resilient and effective in medical imaging, remote sensing, computer vision, and multimedia processing.