Snake pattern detection mobile application based on deep learning

• Main Author: Tan, Yue Jun
• Other Authors: Owen Noel Newton Fernando
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science; Engineering; Medicine, Health and Life Sciences
• Online Access: https://hdl.handle.net/10356/175288
• Institution: Nanyang Technological University

Snakebites are a global public health concern. They cause hundreds of thousands of deaths and disabilities annually, especially in snakebite-endemic countries including Bangladesh and India. This is due to the fact that many still rely on manual identification of snake species, which is prone to error and results in wrong treatment. Thus, this project aims to address these challenges by designing and developing an automated snake pattern identification system based on Deep Convolutional Neural Networks (CNN). Focusing on snake species found in Singapore's habitat, TensorFlow and TensorFlow Lite are leveraged to implement the proposed solution. The main objective is to develop an accurate CNN model capable of classifying snake species from photographs, reducing reliance on domain experts and expediting treatment. Additionally, the model will be deployed on a mobile-based system. This would facilitate real-time identification and geo-tagging of snake sightings, enhancing medical support in rural areas with limited access to treatment. By achieving timely and accurate identification, lives can be saved and health complications associated with snakebites minimised.