Animal Classification Using Cnn Architectures

This study addresses the problem of wild animal attacks and disappearance in areas such as farms or villages near forest and mountains, proposing a solution through deep learning algorithms. Using deep learning architectures, specifically convolution neural networks (CNNs), the study intends to accurately identify and classify animals based on categories. The dataset has been taken from Kaggle which consists of 90 different animal images, employing various CNN architectures those are LeNet-5, AlexNet, VGG16, ResNet50, Inception V3, and InceptionResnetV2. along with that implemented techniques such as data augmentation to fix the problem related to lack of data and, we used techniques like dropout to tackle the problem related to the model overfitting. The Study paper compares and analyses the accuracy of these algorithms, contributing to comprehensive understanding of their efficiency. Furthermore, different performance metrics are used names as accuracy, precision, recall and F1-score are used to check the accuracy and the model effectiveness. Furthermore, we have explored related works in automated classification and object detection, particularly focusing their application on animal classification. The results highlight the potential of deep learning in forest to create some sort of alert system or create a system which can provide information on endangered animal or rare animal.