A visual recognition supporting tool for mapping environmental data using handheld measurement instruments

Abstract

The environmental data mapping has become an important step to measure the mitigation plans from pollution impacts. It often requires an observer to measure environmental data in the field using portable measuring devices and combines them with geolocation data to produce geomapped data. One of its technical difficulties during this process is in the step of recording the data, since the observer usually has to record measurement data manually into certain program. In this paper, we developed a smartphone application that capable in reading digits on a handheld measuring device display using computer vision. The measured data is sent to a cloud-based data management system, Google Fusion Tables in order to be displayed in the form of interactive maps with web application. The template matching and pixel counting methods were used to recognize the digits of each respective digit. The variations of pre-processing techniques and template matching methods were also tested. It is shown that the combination of pixel counting and normalized correlation coefficient template matching method with binary digit and template images input resulted in maximum accuracy. From 120 sample images with varied lighting conditions, both in lab-scaled and in-field tests, the digit recognition rate has achieved 70.83% accuracy in lab-scaled and 67.92% when tested in-field. Nevertheless, digit recognition method shown unsatisfactory result which demands different digit recognition method.