Review on Snake Species Identification on Snake Bite Marks using Deep Learning

Snakebite incidents pose significant public health challenges, particularly in regions like Kaltungo, Nigeria, where identifying the snake species responsible for bites is crucial for administering proper treatment. Traditional methods relying on verbal descriptions or blood sample analysis are often inaccurate or impractical. Leveraging deep learning techniques, particularly Convolutional Neural Networks (CNNs), offers a promising solution for automated snake species identification from snake bite marks. This review explores the application of CNNs and Siamese Network Models for this purpose, emphasizing the need for improved datasets, model interpretability, and validation methods. The proposed methodology combines CNNs for initial feature extraction and classification with Siamese Networks for refining classification through image comparisons. By addressing challenges such as limited datasets and variable snake characteristics, this approach aims to enhance the accuracy and efficiency of snake species identification, thereby facilitating timely medical responses and ecological monitoring.