Microbiological Water Quality Test Results Extraction from Mobile Photographs

An emerging and promising approach to achieving access to water and sanitation for all leverages citizen science to collect valuable data on water quantity and quality, which can assist policymakers and water utility managers in sustainably managing water resources. This paper specifically considers water quality data collected using a mobile phone app wielded by citizen-scientists. The citizens use a microbiological water quality test kit to measure E. coli content. The test result is photographed by the citizens and passed on to scientists for interpretation. However, reading the results necessitates a trained scientific eye and is time consuming. This paper therefore puts forward an algorithm that can automatically infer the outcome of the test from a photograph. To this end, we evaluate several image processing and machine learning algorithms for the automatic extraction of results from photographs of microbiological water quality tests. We devise and present a new knowledge and rule-based algorithm and show that it performs satisfactorily.