• Anurag Mahajan
• Sangita Gudhade
• Abhishek Mahajan
• Tanish Laddha
• Vaishnavi Lichade , Sumedh Chobitkar

Abstract: Animal identification and species detection play crucial roles in wildlife conservation, ecological research, and biodiversity monitoring. In recent years, convolutional neural networks (CNNs), a type of deep learning algorithm, have shown remarkable success in various computer vision tasks, including animal identification and species detection. This paper comprehensively reviews current state-of-the-art animal identification and species detection techniques using CNN. The paper discusses the challenges associated with animal identification and species detection, including variations in animal appearance, complex backgrounds, and limited availability of labeled training data. In this study, we propose a deep learning solution based on Convolution Neural Networks (CNN) predict whether the animal belongs to which classes and their species. It also uses a pre-trained model and develops a solution to the same problem. We then explore a variety of CNN-based approaches that have been developed to address these challenges, including transfer learning, fine-tuning, and data augmentation techniques. This paper also describes, for example, various CNN architectures and their applications for animal identification and species discovery.

Animal detection; species identification; Convolutional neural Network (CNN);

"Animal Identification And Detection Of Species", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 4, page no.k489-k494, April-2023, Available :http://www.jetir.org/papers/JETIR2304A69.pdf

"Animal Identification And Detection Of Species", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 4, page no. ppk489-k494, April-2023, Available at : http://www.jetir.org/papers/JETIR2304A69.pdf