Malaria, a life-threatening disease transmitted by Anopheles mosquitoes, remains a leading cause of death in low-income countries, with hundreds of thousands of deaths annually. Long-lasting insecticidal nets (LLINs) are a proven, cost-effective method for reducing malaria mortality by preventing parasite transmission. However, their protective efficacy depends on maintaining physical integrity, requiring regular monitoring and timely replacement.

Currently, LLIN condition is assessed using the WHO standard, which counts and classifies holes by size. However, this technique is time-consuming and does not accurately reflect the total hole area.

This project aims to develop a fast, reliable alternative for assessing LLIN condition using Deep Learning. The resulting method will provide a faster and more reliable approach to assess LLIN condition, thus enabling national programs to effectively plan the mass-distribution of these nets, contributing to the protection of millions of people.