Use of Metric Learning for the Recognition of Handwritten Digits, and its Application to Increase the Outreach of Voice-based Communication Platforms
This work addresses the challenge of data collection for development programs where digital devices are unaffordable or impractical, enabling outreach via voice-based platforms.
The paper tackled the problem of digitizing handwritten digits from paper forms in resource-constrained settings by developing a large dataset and deep learning models, resulting in the successful digitization of phone numbers to push nearly 4 million calls in a maternal and child health project.
Initiation, monitoring, and evaluation of development programmes can involve field-based data collection about project activities. This data collection through digital devices may not always be feasible though, for reasons such as unaffordability of smartphones and tablets by field-based cadre, or shortfalls in their training and capacity building. Paper-based data collection has been argued to be more appropriate in several contexts, with automated digitization of the paper forms through OCR (Optical Character Recognition) and OMR (Optical Mark Recognition) techniques. We contribute with providing a large dataset of handwritten digits, and deep learning based models and methods built using this data, that are effective in real-world environments. We demonstrate the deployment of these tools in the context of a maternal and child health and nutrition awareness project, which uses IVR (Interactive Voice Response) systems to provide awareness information to rural women SHG (Self Help Group) members in north India. Paper forms were used to collect phone numbers of the SHG members at scale, which were digitized using the OCR tools developed by us, and used to push almost 4 million phone calls. The data, model, and code have been released in the open-source domain.