Bird Species Recognition by Integrating EfficientNet-B0 Deep Learning Architecture and Broad Learning System

Accurate identification and classification of bird species are crucial for advancing research and conservation efforts, enhancing our understanding of population dynamics, and implementing targeted conservation strategies. Despite its importance, this task is challenging due to the wide variation in bird appearances and environmental noise, which can lead to poor generalization and increased complexity. To address these challenges, this paper proposes a novel bird species recognition method, EN-BLS, which integrates the EfficientNet-B0 deep learning architecture with a broad learning system. EfficientNet-B0 is used as the backbone network for feature extraction from bird images, with the final feature map layer serving as input for the broad learning system. The resulting hybrid model, EN-BLS, is designed for bird species classification. The model's performance is evaluated using the Birds 525 Species dataset, the latest publicly available benchmark dataset with the highest number of categories collected from diverse real-world environments. Experimental results show that EN-BLS achieves a recognition accuracy of 93.79<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> with lower computational complexity compared to existing methods, demonstrating its effectiveness for bird species diversity monitoring and conservation efforts.