The carp encompassing diverse species such as Labeo catla (Catla), Labeo rohita (Rohu), Cirrhinus mrigala (Mrigal), Cyprinus carpio (Common carp), Ctenopharyngodon idella (Grass carp), and Hypophthalmichthys molitrix (Silver carp) holds immense ecological and economic significance in India. The accurate identification and classification of these carp species are essential for sustainable fisheries management, aquaculture, and conservation efforts. In this research, we present an innovative ensemble approach designed to enhance the precision and robustness of carps classification. The ensemble framework employs a weighted voting scheme, where the contributions of each classifier are weighted based on their performance during training and validation. In the experimental evaluation, we utilized a comprehensive dataset comprising images of different carp species. Performance metrics such as classification accuracy, precision, recall, and F1 score were employed to assess the effectiveness of the ensemble approach. This research not only addresses the practical challenges associated with carp classification but also provides a foundation for the development of automated systems that can support fisheries management, ecological studies, and conservation initiatives. Further refinement and optimization of the ensemble approach, as well as its scalability to larger datasets and real-world applications, represent avenues for future research in advancing the field of carp classification.